[{"language":[{"iso":"eng"}],"date_updated":"2022-03-10T18:28:19Z","oa":"1","department":[{"_id":"75"}],"project":[{"name":"SFB 901: SFB 901","_id":"1"},{"_id":"4","name":"SFB 901 - C: SFB 901 - Project Area C"},{"name":"SFB 901 - C4: SFB 901 - Subproject C4","_id":"16"}],"title":"mobile-env: An Open Platform for Reinforcement Learning in Wireless Mobile Networks","type":"conference","citation":{"ieee":"S. B. Schneider, S. Werner, R. Khalili, A. Hecker, and H. Karl, “mobile-env: An Open Platform for Reinforcement Learning in Wireless Mobile Networks,” presented at the IEEE/IFIP Network Operations and Management Symposium (NOMS), Budapest, 2022.","short":"S.B. Schneider, S. Werner, R. Khalili, A. Hecker, H. Karl, in: IEEE/IFIP Network Operations and Management Symposium (NOMS), IEEE, 2022.","mla":"Schneider, Stefan Balthasar, et al. “Mobile-Env: An Open Platform for Reinforcement Learning in Wireless Mobile Networks.” IEEE/IFIP Network Operations and Management Symposium (NOMS), IEEE, 2022.","bibtex":"@inproceedings{Schneider_Werner_Khalili_Hecker_Karl_2022, title={mobile-env: An Open Platform for Reinforcement Learning in Wireless Mobile Networks}, booktitle={IEEE/IFIP Network Operations and Management Symposium (NOMS)}, publisher={IEEE}, author={Schneider, Stefan Balthasar and Werner, Stefan and Khalili, Ramin and Hecker, Artur and Karl, Holger}, year={2022} }","chicago":"Schneider, Stefan Balthasar, Stefan Werner, Ramin Khalili, Artur Hecker, and Holger Karl. “Mobile-Env: An Open Platform for Reinforcement Learning in Wireless Mobile Networks.” In IEEE/IFIP Network Operations and Management Symposium (NOMS). IEEE, 2022.","ama":"Schneider SB, Werner S, Khalili R, Hecker A, Karl H. mobile-env: An Open Platform for Reinforcement Learning in Wireless Mobile Networks. In: IEEE/IFIP Network Operations and Management Symposium (NOMS). IEEE; 2022.","apa":"Schneider, S. B., Werner, S., Khalili, R., Hecker, A., & Karl, H. (2022). mobile-env: An Open Platform for Reinforcement Learning in Wireless Mobile Networks. IEEE/IFIP Network Operations and Management Symposium (NOMS). IEEE/IFIP Network Operations and Management Symposium (NOMS), Budapest."},"year":"2022","conference":{"end_date":"2022-04-29","name":"IEEE/IFIP Network Operations and Management Symposium (NOMS)","start_date":"2022-04-25","location":"Budapest"},"_id":"30236","file":[{"access_level":"open_access","file_name":"author_version.pdf","date_created":"2022-03-10T18:25:41Z","date_updated":"2022-03-10T18:25:41Z","content_type":"application/pdf","relation":"main_file","file_size":223412,"creator":"stschn","file_id":"30237"}],"publication":"IEEE/IFIP Network Operations and Management Symposium (NOMS)","keyword":["wireless mobile networks","network management","continuous control","cognitive networks","autonomous coordination","reinforcement learning","gym environment","simulation","open source"],"file_date_updated":"2022-03-10T18:25:41Z","quality_controlled":"1","author":[{"full_name":"Schneider, Stefan Balthasar","orcid":"0000-0001-8210-4011","first_name":"Stefan Balthasar","id":"35343","last_name":"Schneider"},{"first_name":"Stefan","full_name":"Werner, Stefan","last_name":"Werner"},{"first_name":"Ramin","full_name":"Khalili, Ramin","last_name":"Khalili"},{"last_name":"Hecker","first_name":"Artur","full_name":"Hecker, Artur"},{"last_name":"Karl","id":"126","first_name":"Holger","full_name":"Karl, Holger"}],"publisher":"IEEE","date_created":"2022-03-10T18:28:14Z","status":"public","has_accepted_license":"1","abstract":[{"lang":"eng","text":"Recent reinforcement learning approaches for continuous control in wireless mobile networks have shown impressive\r\nresults. But due to the lack of open and compatible simulators, authors typically create their own simulation environments for training and evaluation. This is cumbersome and time-consuming for authors and limits reproducibility and comparability, ultimately impeding progress in the field.\r\n\r\nTo this end, we propose mobile-env, a simple and open platform for training, evaluating, and comparing reinforcement learning and conventional approaches for continuous control in mobile wireless networks. mobile-env is lightweight and implements the common OpenAI Gym interface and additional wrappers, which allows connecting virtually any single-agent or multi-agent reinforcement learning framework to the environment. While mobile-env provides sensible default values and can be used out of the box, it also has many configuration options and is easy to extend. We therefore believe mobile-env to be a valuable platform for driving meaningful progress in autonomous coordination of\r\nwireless mobile networks."}],"user_id":"35343","ddc":["004"]},{"_id":"25278","citation":{"mla":"Afifi, Haitham, et al. “Reinforcement Learning for Admission Control in Wireless Virtual Network Embedding.” 2021 IEEE International Conference on Advanced Networks and Telecommunications Systems (ANTS) (ANTS’21), 2021.","bibtex":"@inproceedings{Afifi_Sauer_Karl_2021, place={Hyderabad, India}, title={Reinforcement Learning for Admission Control in Wireless Virtual Network Embedding}, booktitle={2021 IEEE International Conference on Advanced Networks and Telecommunications Systems (ANTS) (ANTS’21)}, author={Afifi, Haitham and Sauer, Fabian Jakob and Karl, Holger}, year={2021} }","apa":"Afifi, H., Sauer, F. J., & Karl, H. (2021). Reinforcement Learning for Admission Control in Wireless Virtual Network Embedding. 2021 IEEE International Conference on Advanced Networks and Telecommunications Systems (ANTS) (ANTS’21).","ama":"Afifi H, Sauer FJ, Karl H. Reinforcement Learning for Admission Control in Wireless Virtual Network Embedding. In: 2021 IEEE International Conference on Advanced Networks and Telecommunications Systems (ANTS) (ANTS’21). ; 2021.","chicago":"Afifi, Haitham, Fabian Jakob Sauer, and Holger Karl. “Reinforcement Learning for Admission Control in Wireless Virtual Network Embedding.” In 2021 IEEE International Conference on Advanced Networks and Telecommunications Systems (ANTS) (ANTS’21). Hyderabad, India, 2021.","ieee":"H. Afifi, F. J. Sauer, and H. Karl, “Reinforcement Learning for Admission Control in Wireless Virtual Network Embedding,” 2021.","short":"H. Afifi, F.J. Sauer, H. Karl, in: 2021 IEEE International Conference on Advanced Networks and Telecommunications Systems (ANTS) (ANTS’21), Hyderabad, India, 2021."},"year":"2021","type":"conference","user_id":"65718","ddc":["000"],"abstract":[{"lang":"eng","text":"Using Service Function Chaining (SFC) in wireless networks became popular in many domains like networking and multimedia. It relies on allocating network resources to incoming SFCs requests, via a Virtual Network Embedding (VNE) algorithm, so that it optimizes the performance of the SFC. When the load of incoming requests -- competing for the limited network resources -- increases, it becomes challenging to decide which requests should be admitted and which one should be rejected. In this work, we propose a deep Reinforcement learning (RL) solution that can learn the admission policy for different dependencies, such as the service lifetime and the priority of incoming requests. We compare the deep RL solution to a first-come-first-serve baseline that admits a request whenever there are available resources. We show that deep RL outperforms the baseline and provides higher acceptance rate with low rejections even when there are enough resources."}],"status":"public","has_accepted_license":"1","date_created":"2021-10-04T10:42:20Z","file":[{"file_name":"Preprint___Reinforcement_Learning_for_Dynamic_Resource_Allocation_in_Wireless_Networks.pdf","date_created":"2021-10-04T10:43:19Z","access_level":"closed","creator":"hafifi","file_id":"25279","file_size":534737,"relation":"main_file","success":1,"content_type":"application/pdf","date_updated":"2021-10-04T10:43:19Z"}],"author":[{"id":"65718","last_name":"Afifi","full_name":"Afifi, Haitham","first_name":"Haitham"},{"full_name":"Sauer, Fabian Jakob","first_name":"Fabian Jakob","last_name":"Sauer"},{"id":"126","last_name":"Karl","full_name":"Karl, Holger","first_name":"Holger"}],"publication":"2021 IEEE International Conference on Advanced Networks and Telecommunications Systems (ANTS) (ANTS'21)","file_date_updated":"2021-10-04T10:43:19Z","keyword":["reinforcement learning","admission control","wireless sensor networks"],"date_updated":"2022-01-06T06:56:58Z","language":[{"iso":"eng"}],"title":"Reinforcement Learning for Admission Control in Wireless Virtual Network Embedding","place":"Hyderabad, India","project":[{"name":"Akustische Sensornetzwerke - Teilprojekt \"Verteilte akustische Signalverarbeitung über funkbasierte Sensornetzwerke","_id":"27"}]},{"title":"Reinforcement Learning-based Microphone Selection in Wireless Acoustic Sensor Networks considering Network and Acoustic Utilities","ddc":["620"],"user_id":"65718","abstract":[{"text":"Wireless Acoustic Sensor Networks (WASNs) have a wide range of audio signal processing applications. Due to the spatial diversity of the microphone and their relative position to the acoustic source, not all microphones are equally useful for subsequent audio signal processing tasks, nor do they all have the same wireless data transmission rates. Hence, a central task in WASNs is to balance a microphone’s estimated acoustic utility against its transmission delay, selecting a best-possible subset of microphones to record audio signals.\r\n\r\nIn this work, we use reinforcement learning to decide if a microphone should be used or switched off to maximize the acoustic quality at low transmission delays, while minimizing switching frequency. In experiments with moving sources in a simulated acoustic environment, our method outperforms naive baseline comparisons","lang":"eng"}],"has_accepted_license":"1","status":"public","date_created":"2021-10-04T10:59:50Z","project":[{"name":"Akustische Sensornetzwerke - Teilprojekt \"Verteilte akustische Signalverarbeitung über funkbasierte Sensornetzwerke","_id":"27"}],"author":[{"full_name":"Afifi, Haitham","first_name":"Haitham","id":"65718","last_name":"Afifi"},{"last_name":"Guenther","first_name":"Michael","full_name":"Guenther, Michael"},{"last_name":"Brendel","first_name":"Andreas","full_name":"Brendel, Andreas"},{"first_name":"Holger","full_name":"Karl, Holger","last_name":"Karl","id":"126"},{"full_name":"Kellermann, Walter","first_name":"Walter","last_name":"Kellermann"}],"publication":"14. ITG Conference on Speech Communication (ITG 2021)","keyword":["microphone utility","microphone selection","wireless acoustic sensor network","network delay","reinforcement learning"],"file_date_updated":"2021-10-04T10:58:07Z","file":[{"date_created":"2021-10-04T10:58:07Z","file_name":"ITG_2021_paper_26 (3).pdf","access_level":"closed","file_id":"25282","creator":"hafifi","file_size":283616,"success":1,"relation":"main_file","content_type":"application/pdf","date_updated":"2021-10-04T10:58:07Z"}],"_id":"25281","date_updated":"2022-01-06T06:56:59Z","year":"2021","citation":{"ieee":"H. Afifi, M. Guenther, A. Brendel, H. Karl, and W. Kellermann, “Reinforcement Learning-based Microphone Selection in Wireless Acoustic Sensor Networks considering Network and Acoustic Utilities,” 2021.","short":"H. Afifi, M. Guenther, A. Brendel, H. Karl, W. Kellermann, in: 14. ITG Conference on Speech Communication (ITG 2021), 2021.","mla":"Afifi, Haitham, et al. “Reinforcement Learning-Based Microphone Selection in Wireless Acoustic Sensor Networks Considering Network and Acoustic Utilities.” 14. ITG Conference on Speech Communication (ITG 2021), 2021.","bibtex":"@inproceedings{Afifi_Guenther_Brendel_Karl_Kellermann_2021, title={Reinforcement Learning-based Microphone Selection in Wireless Acoustic Sensor Networks considering Network and Acoustic Utilities}, booktitle={14. ITG Conference on Speech Communication (ITG 2021)}, author={Afifi, Haitham and Guenther, Michael and Brendel, Andreas and Karl, Holger and Kellermann, Walter}, year={2021} }","ama":"Afifi H, Guenther M, Brendel A, Karl H, Kellermann W. Reinforcement Learning-based Microphone Selection in Wireless Acoustic Sensor Networks considering Network and Acoustic Utilities. In: 14. ITG Conference on Speech Communication (ITG 2021). ; 2021.","apa":"Afifi, H., Guenther, M., Brendel, A., Karl, H., & Kellermann, W. (2021). Reinforcement Learning-based Microphone Selection in Wireless Acoustic Sensor Networks considering Network and Acoustic Utilities. 14. ITG Conference on Speech Communication (ITG 2021).","chicago":"Afifi, Haitham, Michael Guenther, Andreas Brendel, Holger Karl, and Walter Kellermann. “Reinforcement Learning-Based Microphone Selection in Wireless Acoustic Sensor Networks Considering Network and Acoustic Utilities.” In 14. ITG Conference on Speech Communication (ITG 2021), 2021."},"type":"conference","language":[{"iso":"eng"}]},{"publication_status":"accepted","project":[{"name":"SFB 901 - Project Area C","_id":"4"},{"name":"SFB 901 - Subproject C4","_id":"16"},{"name":"SFB 901","_id":"1"}],"department":[{"_id":"75"}],"title":"Learning Flow Scheduling","language":[{"iso":"eng"}],"doi":"https://doi.org/10.1109/CCNC49032.2021.9369514","date_updated":"2022-01-06T06:54:20Z","status":"public","date_created":"2020-10-19T14:27:17Z","publisher":"IEEE Computer Society","author":[{"id":"63288","last_name":"Hasnain","full_name":"Hasnain, Asif","first_name":"Asif"},{"last_name":"Karl","id":"126","first_name":"Holger","full_name":"Karl, Holger"}],"publication":"2021 IEEE 18th Annual Consumer Communications & Networking Conference (CCNC)","keyword":["Flow scheduling","Deadlines","Reinforcement learning"],"ddc":["000"],"user_id":"63288","abstract":[{"text":"Datacenter applications have different resource requirements from network and developing flow scheduling heuristics for every workload is practically infeasible. In this paper, we show that deep reinforcement learning (RL) can be used to efficiently learn flow scheduling policies for different workloads without manual feature engineering. Specifically, we present LFS, which learns to optimize a high-level performance objective, e.g., maximize the number of flow admissions while meeting the deadlines. The LFS scheduler is trained through deep RL to learn a scheduling policy on continuous online flow arrivals. The evaluation results show that the trained LFS scheduler admits 1.05x more flows than the greedy flow scheduling heuristics under varying network load.","lang":"eng"}],"year":"2021","type":"conference","citation":{"short":"A. Hasnain, H. Karl, in: 2021 IEEE 18th Annual Consumer Communications & Networking Conference (CCNC), IEEE Computer Society, n.d.","ieee":"A. Hasnain and H. Karl, “Learning Flow Scheduling,” in 2021 IEEE 18th Annual Consumer Communications & Networking Conference (CCNC), Las Vegas, USA.","chicago":"Hasnain, Asif, and Holger Karl. “Learning Flow Scheduling.” In 2021 IEEE 18th Annual Consumer Communications & Networking Conference (CCNC). IEEE Computer Society, n.d. https://doi.org/10.1109/CCNC49032.2021.9369514.","ama":"Hasnain A, Karl H. Learning Flow Scheduling. In: 2021 IEEE 18th Annual Consumer Communications & Networking Conference (CCNC). IEEE Computer Society. doi:https://doi.org/10.1109/CCNC49032.2021.9369514","apa":"Hasnain, A., & Karl, H. (n.d.). Learning Flow Scheduling. In 2021 IEEE 18th Annual Consumer Communications & Networking Conference (CCNC). Las Vegas, USA: IEEE Computer Society. https://doi.org/10.1109/CCNC49032.2021.9369514","bibtex":"@inproceedings{Hasnain_Karl, title={Learning Flow Scheduling}, DOI={https://doi.org/10.1109/CCNC49032.2021.9369514}, booktitle={2021 IEEE 18th Annual Consumer Communications & Networking Conference (CCNC)}, publisher={IEEE Computer Society}, author={Hasnain, Asif and Karl, Holger} }","mla":"Hasnain, Asif, and Holger Karl. “Learning Flow Scheduling.” 2021 IEEE 18th Annual Consumer Communications & Networking Conference (CCNC), IEEE Computer Society, doi:https://doi.org/10.1109/CCNC49032.2021.9369514."},"main_file_link":[{"url":"https://ieeexplore.ieee.org/document/9369514"}],"_id":"20125","conference":{"end_date":"2021-01-12","location":"Las Vegas, USA","name":"2021 IEEE 18th Annual Consumer Communications & Networking Conference (CCNC)","start_date":"2021-01-09"}},{"_id":"21005","conference":{"name":"IEEE INFOCOM 2021 - IEEE Conference on Computer Communications","start_date":"2021-05-10","location":"Vancouver BC Canada","end_date":"2021-05-13"},"type":"conference","citation":{"short":"A. Hasnain, H. Karl, in: IEEE INFOCOM 2021 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS), IEEE Communications Society, n.d.","ieee":"A. Hasnain and H. Karl, “Learning Coflow Admissions,” in IEEE INFOCOM 2021 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS), Vancouver BC Canada.","apa":"Hasnain, A., & Karl, H. (n.d.). Learning Coflow Admissions. In IEEE INFOCOM 2021 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS). Vancouver BC Canada: IEEE Communications Society. https://doi.org/10.1109/INFOCOMWKSHPS51825.2021.9484599","ama":"Hasnain A, Karl H. Learning Coflow Admissions. In: IEEE INFOCOM 2021 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS). IEEE Communications Society. doi:10.1109/INFOCOMWKSHPS51825.2021.9484599","chicago":"Hasnain, Asif, and Holger Karl. “Learning Coflow Admissions.” In IEEE INFOCOM 2021 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS). IEEE Communications Society, n.d. https://doi.org/10.1109/INFOCOMWKSHPS51825.2021.9484599.","bibtex":"@inproceedings{Hasnain_Karl, title={Learning Coflow Admissions}, DOI={10.1109/INFOCOMWKSHPS51825.2021.9484599}, booktitle={IEEE INFOCOM 2021 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)}, publisher={IEEE Communications Society}, author={Hasnain, Asif and Karl, Holger} }","mla":"Hasnain, Asif, and Holger Karl. “Learning Coflow Admissions.” IEEE INFOCOM 2021 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS), IEEE Communications Society, doi:10.1109/INFOCOMWKSHPS51825.2021.9484599."},"year":"2021","main_file_link":[{"url":"https://ieeexplore.ieee.org/document/9484599"}],"ddc":["000"],"user_id":"63288","abstract":[{"text":"Data-parallel applications are developed using different data programming models, e.g., MapReduce, partition/aggregate. These models represent diverse resource requirements of application in a datacenter network, which can be represented by the coflow abstraction. The conventional method of creating hand-crafted coflow heuristics for admission or scheduling for different workloads is practically infeasible. In this paper, we propose a deep reinforcement learning (DRL)-based coflow admission scheme -- LCS -- that can learn an admission policy for a higher-level performance objective, i.e., maximize successful coflow admissions, without manual feature engineering. LCS is trained on a production trace, which has online coflow arrivals. The evaluation results show that LCS is able to learn a reasonable admission policy that admits more coflows than state-of-the-art Varys heuristic while meeting their deadlines.","lang":"eng"}],"status":"public","date_created":"2021-01-16T18:24:19Z","author":[{"last_name":"Hasnain","id":"63288","first_name":"Asif","full_name":"Hasnain, Asif"},{"last_name":"Karl","id":"126","first_name":"Holger","full_name":"Karl, Holger"}],"publisher":"IEEE Communications Society","keyword":["Coflow scheduling","Reinforcement learning","Deadlines"],"publication":"IEEE INFOCOM 2021 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","doi":"10.1109/INFOCOMWKSHPS51825.2021.9484599","date_updated":"2022-01-06T06:54:42Z","language":[{"iso":"eng"}],"title":"Learning Coflow Admissions","related_material":{"link":[{"relation":"confirmation","url":"https://ieeexplore.ieee.org/document/9484599"}]},"publication_status":"accepted","project":[{"name":"SFB 901 - Subproject C4","_id":"16"},{"name":"SFB 901 - Project Area C","_id":"4"},{"_id":"1","name":"SFB 901"}],"department":[{"_id":"75"}]},{"date_updated":"2022-01-06T06:55:00Z","_id":"21479","year":"2021","citation":{"ama":"Afifi H, Ramaswamy A, Karl H. A Reinforcement Learning QoI/QoS-Aware Approach in Acoustic Sensor Networks. In: 2021 IEEE 18th Annual Consumer Communications \\& Networking Conference (CCNC) (CCNC 2021). ; 2021.","apa":"Afifi, H., Ramaswamy, A., & Karl, H. (2021). A Reinforcement Learning QoI/QoS-Aware Approach in Acoustic Sensor Networks. In 2021 IEEE 18th Annual Consumer Communications \\& Networking Conference (CCNC) (CCNC 2021).","chicago":"Afifi, Haitham, Arunselvan Ramaswamy, and Holger Karl. “A Reinforcement Learning QoI/QoS-Aware Approach in Acoustic Sensor Networks.” In 2021 IEEE 18th Annual Consumer Communications \\& Networking Conference (CCNC) (CCNC 2021), 2021.","bibtex":"@inproceedings{Afifi_Ramaswamy_Karl_2021, title={A Reinforcement Learning QoI/QoS-Aware Approach in Acoustic Sensor Networks}, booktitle={2021 IEEE 18th Annual Consumer Communications \\& Networking Conference (CCNC) (CCNC 2021)}, author={Afifi, Haitham and Ramaswamy, Arunselvan and Karl, Holger}, year={2021} }","mla":"Afifi, Haitham, et al. “A Reinforcement Learning QoI/QoS-Aware Approach in Acoustic Sensor Networks.” 2021 IEEE 18th Annual Consumer Communications \\& Networking Conference (CCNC) (CCNC 2021), 2021.","short":"H. Afifi, A. Ramaswamy, H. Karl, in: 2021 IEEE 18th Annual Consumer Communications \\& Networking Conference (CCNC) (CCNC 2021), 2021.","ieee":"H. Afifi, A. Ramaswamy, and H. Karl, “A Reinforcement Learning QoI/QoS-Aware Approach in Acoustic Sensor Networks,” in 2021 IEEE 18th Annual Consumer Communications \\& Networking Conference (CCNC) (CCNC 2021), 2021."},"type":"conference","language":[{"iso":"eng"}],"title":"A Reinforcement Learning QoI/QoS-Aware Approach in Acoustic Sensor Networks","user_id":"65718","abstract":[{"lang":"eng","text":"Two of the most important metrics when developing Wireless Sensor Networks (WSNs) applications are the Quality of Information (QoI) and Quality of Service (QoS). The former is used to specify the quality of the collected data by the sensors (e.g., measurements error or signal's intensity), while the latter defines the network's performance and availability (e.g., packet losses and latency). In this paper, we consider an example of wireless acoustic sensor networks, where we select a subset of microphones for two different objectives. First, we maximize the recording quality under QoS constraints. Second, we apply a trade-off between QoI and QoS. We formulate the problem as a constrained Markov Decision Problem (MDP) and solve it using reinforcement learning (RL). We compare the RL solution to a baseline model and show that in case of QoS-guarantee objective, the RL solution has an optimality gap up to 1\\%. Meanwhile, the RL solution is better than the baseline with improvements up to 23\\%, when using the trade-off objective."}],"date_created":"2021-03-12T16:03:53Z","project":[{"_id":"27","name":"Akustische Sensornetzwerke - Teilprojekt \"Verteilte akustische Signalverarbeitung über funkbasierte Sensornetzwerke"}],"status":"public","publication":"2021 IEEE 18th Annual Consumer Communications \\& Networking Conference (CCNC) (CCNC 2021)","keyword":["reinforcement learning","wireless sensor networks","resource allocation","acoustic sensor networks"],"author":[{"first_name":"Haitham","full_name":"Afifi, Haitham","last_name":"Afifi","id":"65718"},{"full_name":"Ramaswamy, Arunselvan","orcid":"https://orcid.org/ 0000-0001-7547-8111","first_name":"Arunselvan","id":"66937","last_name":"Ramaswamy"},{"first_name":"Holger","full_name":"Karl, Holger","last_name":"Karl","id":"126"}]},{"date_created":"2021-03-18T17:15:47Z","has_accepted_license":"1","status":"public","file_date_updated":"2021-03-18T17:12:56Z","publication":"IEEE International Conference on Distributed Computing Systems (ICDCS)","keyword":["network management","service management","coordination","reinforcement learning","distributed"],"publisher":"IEEE","author":[{"orcid":"0000-0001-8210-4011","full_name":"Schneider, Stefan Balthasar","first_name":"Stefan Balthasar","id":"35343","last_name":"Schneider"},{"last_name":"Qarawlus","full_name":"Qarawlus, Haydar","first_name":"Haydar"},{"last_name":"Karl","id":"126","first_name":"Holger","full_name":"Karl, Holger"}],"file":[{"date_created":"2021-03-18T17:12:56Z","file_name":"public_author_version.pdf","access_level":"open_access","title":"Distributed Online Service Coordination Using Deep Reinforcement Learning","file_id":"21544","creator":"stschn","file_size":606321,"relation":"main_file","content_type":"application/pdf","date_updated":"2021-03-18T17:12:56Z"}],"ddc":["000"],"user_id":"35343","abstract":[{"lang":"eng","text":"Services often consist of multiple chained components such as microservices in a service mesh, or machine learning functions in a pipeline. Providing these services requires online coordination including scaling the service, placing instance of all components in the network, scheduling traffic to these instances, and routing traffic through the network. Optimized service coordination is still a hard problem due to many influencing factors such as rapidly arriving user demands and limited node and link capacity. Existing approaches to solve the problem are often built on rigid models and assumptions, tailored to specific scenarios. If the scenario changes and the assumptions no longer hold, they easily break and require manual adjustments by experts. Novel self-learning approaches using deep reinforcement learning (DRL) are promising but still have limitations as they only address simplified versions of the problem and are typically centralized and thus do not scale to practical large-scale networks.\r\n\r\nTo address these issues, we propose a distributed self-learning service coordination approach using DRL. After centralized training, we deploy a distributed DRL agent at each node in the network, making fast coordination decisions locally in parallel with the other nodes. Each agent only observes its direct neighbors and does not need global knowledge. Hence, our approach scales independently from the size of the network. In our extensive evaluation using real-world network topologies and traffic traces, we show that our proposed approach outperforms a state-of-the-art conventional heuristic as well as a centralized DRL approach (60% higher throughput on average) while requiring less time per online decision (1 ms)."}],"year":"2021","citation":{"ama":"Schneider SB, Qarawlus H, Karl H. Distributed Online Service Coordination Using Deep Reinforcement Learning. In: IEEE International Conference on Distributed Computing Systems (ICDCS). IEEE; 2021.","apa":"Schneider, S. B., Qarawlus, H., & Karl, H. (2021). Distributed Online Service Coordination Using Deep Reinforcement Learning. In IEEE International Conference on Distributed Computing Systems (ICDCS). Washington, DC, USA: IEEE.","chicago":"Schneider, Stefan Balthasar, Haydar Qarawlus, and Holger Karl. “Distributed Online Service Coordination Using Deep Reinforcement Learning.” In IEEE International Conference on Distributed Computing Systems (ICDCS). IEEE, 2021.","mla":"Schneider, Stefan Balthasar, et al. “Distributed Online Service Coordination Using Deep Reinforcement Learning.” IEEE International Conference on Distributed Computing Systems (ICDCS), IEEE, 2021.","bibtex":"@inproceedings{Schneider_Qarawlus_Karl_2021, title={Distributed Online Service Coordination Using Deep Reinforcement Learning}, booktitle={IEEE International Conference on Distributed Computing Systems (ICDCS)}, publisher={IEEE}, author={Schneider, Stefan Balthasar and Qarawlus, Haydar and Karl, Holger}, year={2021} }","short":"S.B. Schneider, H. Qarawlus, H. Karl, in: IEEE International Conference on Distributed Computing Systems (ICDCS), IEEE, 2021.","ieee":"S. B. Schneider, H. Qarawlus, and H. Karl, “Distributed Online Service Coordination Using Deep Reinforcement Learning,” in IEEE International Conference on Distributed Computing Systems (ICDCS), Washington, DC, USA, 2021."},"type":"conference","conference":{"name":"IEEE International Conference on Distributed Computing Systems (ICDCS)","location":"Washington, DC, USA"},"_id":"21543","project":[{"name":"SFB 901","_id":"1"},{"name":"SFB 901 - Project Area C","_id":"4"},{"_id":"16","name":"SFB 901 - Subproject C4"}],"department":[{"_id":"75"}],"title":"Distributed Online Service Coordination Using Deep Reinforcement Learning","related_material":{"link":[{"relation":"software","url":"https://github.com/ RealVNF/distributed-drl-coordination"}]},"language":[{"iso":"eng"}],"oa":"1","date_updated":"2022-01-06T06:55:04Z"},{"title":"Self-Learning Multi-Objective Service Coordination Using Deep Reinforcement Learning","department":[{"_id":"75"}],"project":[{"_id":"1","name":"SFB 901"},{"_id":"4","name":"SFB 901 - Project Area C"},{"_id":"16","name":"SFB 901 - Subproject C4"}],"date_updated":"2022-01-06T06:55:15Z","oa":"1","doi":"10.1109/TNSM.2021.3076503","language":[{"iso":"eng"}],"abstract":[{"lang":"eng","text":"Modern services consist of interconnected components,e.g., microservices in a service mesh or machine learning functions in a pipeline. These services can scale and run across multiple network nodes on demand. To process incoming traffic, service components have to be instantiated and traffic assigned to these instances, taking capacities, changing demands, and Quality of Service (QoS) requirements into account. This challenge is usually solved with custom approaches designed by experts. While this typically works well for the considered scenario, the models often rely on unrealistic assumptions or on knowledge that is not available in practice (e.g., a priori knowledge).\r\n\r\nWe propose DeepCoord, a novel deep reinforcement learning approach that learns how to best coordinate services and is geared towards realistic assumptions. It interacts with the network and relies on available, possibly delayed monitoring information. Rather than defining a complex model or an algorithm on how to achieve an objective, our model-free approach adapts to various objectives and traffic patterns. An agent is trained offline without expert knowledge and then applied online with minimal overhead. Compared to a state-of-the-art heuristic, DeepCoord significantly improves flow throughput (up to 76%) and overall network utility (more than 2x) on realworld network topologies and traffic traces. It also supports optimizing multiple, possibly competing objectives, learns to respect QoS requirements, generalizes to scenarios with unseen, stochastic traffic, and scales to large real-world networks. For reproducibility and reuse, our code is publicly available."}],"article_type":"original","user_id":"35343","ddc":["000"],"file":[{"access_level":"open_access","date_created":"2021-04-27T08:01:26Z","file_name":"ris-accepted-version.pdf","description":"Author version of the accepted paper","relation":"main_file","date_updated":"2021-04-27T08:01:26Z","content_type":"application/pdf","creator":"stschn","file_id":"21809","file_size":4172270}],"publication":"Transactions on Network and Service Management","keyword":["network management","service management","coordination","reinforcement learning","self-learning","self-adaptation","multi-objective"],"file_date_updated":"2021-04-27T08:01:26Z","author":[{"id":"35343","last_name":"Schneider","full_name":"Schneider, Stefan Balthasar","orcid":"0000-0001-8210-4011","first_name":"Stefan Balthasar"},{"last_name":"Khalili","full_name":"Khalili, Ramin","first_name":"Ramin"},{"first_name":"Adnan","full_name":"Manzoor, Adnan","last_name":"Manzoor"},{"last_name":"Qarawlus","first_name":"Haydar","full_name":"Qarawlus, Haydar"},{"last_name":"Schellenberg","full_name":"Schellenberg, Rafael","first_name":"Rafael"},{"first_name":"Holger","full_name":"Karl, Holger","last_name":"Karl","id":"126"},{"last_name":"Hecker","full_name":"Hecker, Artur","first_name":"Artur"}],"publisher":"IEEE","date_created":"2021-04-27T08:04:16Z","has_accepted_license":"1","status":"public","_id":"21808","year":"2021","citation":{"ieee":"S. B. Schneider et al., “Self-Learning Multi-Objective Service Coordination Using Deep Reinforcement Learning,” Transactions on Network and Service Management, 2021.","short":"S.B. Schneider, R. Khalili, A. Manzoor, H. Qarawlus, R. Schellenberg, H. Karl, A. Hecker, Transactions on Network and Service Management (2021).","mla":"Schneider, Stefan Balthasar, et al. “Self-Learning Multi-Objective Service Coordination Using Deep Reinforcement Learning.” Transactions on Network and Service Management, IEEE, 2021, doi:10.1109/TNSM.2021.3076503.","bibtex":"@article{Schneider_Khalili_Manzoor_Qarawlus_Schellenberg_Karl_Hecker_2021, title={Self-Learning Multi-Objective Service Coordination Using Deep Reinforcement Learning}, DOI={10.1109/TNSM.2021.3076503}, journal={Transactions on Network and Service Management}, publisher={IEEE}, author={Schneider, Stefan Balthasar and Khalili, Ramin and Manzoor, Adnan and Qarawlus, Haydar and Schellenberg, Rafael and Karl, Holger and Hecker, Artur}, year={2021} }","chicago":"Schneider, Stefan Balthasar, Ramin Khalili, Adnan Manzoor, Haydar Qarawlus, Rafael Schellenberg, Holger Karl, and Artur Hecker. “Self-Learning Multi-Objective Service Coordination Using Deep Reinforcement Learning.” Transactions on Network and Service Management, 2021. https://doi.org/10.1109/TNSM.2021.3076503.","ama":"Schneider SB, Khalili R, Manzoor A, et al. Self-Learning Multi-Objective Service Coordination Using Deep Reinforcement Learning. Transactions on Network and Service Management. 2021. doi:10.1109/TNSM.2021.3076503","apa":"Schneider, S. B., Khalili, R., Manzoor, A., Qarawlus, H., Schellenberg, R., Karl, H., & Hecker, A. (2021). Self-Learning Multi-Objective Service Coordination Using Deep Reinforcement Learning. Transactions on Network and Service Management. https://doi.org/10.1109/TNSM.2021.3076503"},"type":"journal_article"},{"citation":{"bibtex":"@book{Schneider_Karl_Khalili_Hecker_2021, title={DeepCoMP: Coordinated Multipoint Using Multi-Agent Deep Reinforcement Learning}, author={Schneider, Stefan Balthasar and Karl, Holger and Khalili, Ramin and Hecker, Artur}, year={2021} }","mla":"Schneider, Stefan Balthasar, et al. DeepCoMP: Coordinated Multipoint Using Multi-Agent Deep Reinforcement Learning. 2021.","chicago":"Schneider, Stefan Balthasar, Holger Karl, Ramin Khalili, and Artur Hecker. DeepCoMP: Coordinated Multipoint Using Multi-Agent Deep Reinforcement Learning, 2021.","apa":"Schneider, S. B., Karl, H., Khalili, R., & Hecker, A. (2021). DeepCoMP: Coordinated Multipoint Using Multi-Agent Deep Reinforcement Learning.","ama":"Schneider SB, Karl H, Khalili R, Hecker A. DeepCoMP: Coordinated Multipoint Using Multi-Agent Deep Reinforcement Learning.; 2021.","ieee":"S. B. Schneider, H. Karl, R. Khalili, and A. Hecker, DeepCoMP: Coordinated Multipoint Using Multi-Agent Deep Reinforcement Learning. 2021.","short":"S.B. Schneider, H. Karl, R. Khalili, A. Hecker, DeepCoMP: Coordinated Multipoint Using Multi-Agent Deep Reinforcement Learning, 2021."},"year":"2021","type":"working_paper","language":[{"iso":"eng"}],"oa":"1","date_updated":"2022-11-18T09:59:27Z","_id":"33854","date_created":"2022-10-20T16:44:19Z","project":[{"_id":"4","name":"SFB 901 - C: SFB 901 - Project Area C"},{"name":"SFB 901 - C4: SFB 901 - Subproject C4","_id":"16"},{"_id":"1","name":"SFB 901: SFB 901"}],"status":"public","has_accepted_license":"1","keyword":["mobility management","coordinated multipoint","CoMP","cell selection","resource management","reinforcement learning","multi agent","MARL","self-learning","self-adaptation","QoE"],"department":[{"_id":"75"}],"file_date_updated":"2022-10-20T16:41:10Z","author":[{"first_name":"Stefan Balthasar","orcid":"0000-0001-8210-4011","full_name":"Schneider, Stefan Balthasar","last_name":"Schneider","id":"35343"},{"first_name":"Holger","full_name":"Karl, Holger","last_name":"Karl","id":"126"},{"first_name":"Ramin","full_name":"Khalili, Ramin","last_name":"Khalili"},{"first_name":"Artur","full_name":"Hecker, Artur","last_name":"Hecker"}],"file":[{"file_size":2521656,"file_id":"33855","creator":"stschn","content_type":"application/pdf","date_updated":"2022-10-20T16:41:10Z","relation":"main_file","file_name":"preprint.pdf","date_created":"2022-10-20T16:41:10Z","access_level":"open_access"}],"ddc":["004"],"title":"DeepCoMP: Coordinated Multipoint Using Multi-Agent Deep Reinforcement Learning","user_id":"477","abstract":[{"text":"Macrodiversity is a key technique to increase the capacity of mobile networks. It can be realized using coordinated multipoint (CoMP), simultaneously connecting users to multiple overlapping cells. Selecting which users to serve by how many and which cells is NP-hard but needs to happen continuously in real time as users move and channel state changes. Existing approaches often require strict assumptions about or perfect knowledge of the underlying radio system, its resource allocation scheme, or user movements, none of which is readily available in practice.\r\n\r\nInstead, we propose three novel self-learning and self-adapting approaches using model-free deep reinforcement learning (DRL): DeepCoMP, DD-CoMP, and D3-CoMP. DeepCoMP leverages central observations and control of all users to select cells almost optimally. DD-CoMP and D3-CoMP use multi-agent DRL, which allows distributed, robust, and highly scalable coordination. All three approaches learn from experience and self-adapt to varying scenarios, reaching 2x higher Quality of Experience than other approaches. They have very few built-in assumptions and do not need prior system knowledge, making them more robust to change and better applicable in practice than existing approaches.","lang":"eng"}]},{"project":[{"name":"SFB 901: SFB 901","_id":"1"},{"_id":"4","name":"SFB 901 - C: SFB 901 - Project Area C"},{"name":"SFB 901 - C4: SFB 901 - Subproject C4","_id":"16"}],"date_created":"2023-01-10T15:08:50Z","status":"public","has_accepted_license":"1","keyword":["nfv","coordination","machine learning","reinforcement learning","phd","digest"],"file_date_updated":"2023-01-10T15:07:03Z","department":[{"_id":"75"}],"author":[{"first_name":"Stefan Balthasar","orcid":"0000-0001-8210-4011","full_name":"Schneider, Stefan Balthasar","last_name":"Schneider","id":"35343"}],"file":[{"date_created":"2023-01-10T15:07:03Z","file_name":"main.pdf","access_level":"open_access","creator":"stschn","file_id":"35890","file_size":133340,"relation":"main_file","content_type":"application/pdf","date_updated":"2023-01-10T15:07:03Z"}],"title":"Conventional and Machine Learning Approaches for Network and Service Coordination","ddc":["004"],"user_id":"35343","abstract":[{"lang":"eng","text":"Network and service coordination is important to provide modern services consisting of multiple interconnected components, e.g., in 5G, network function virtualization (NFV), or cloud and edge computing. In this paper, I outline my dissertation research, which proposes six approaches to automate such network and service coordination. All approaches dynamically react to the current demand and optimize coordination for high service quality and low costs. The approaches range from centralized to distributed methods and from conventional heuristic algorithms and mixed-integer linear programs to machine learning approaches using supervised and reinforcement learning. I briefly discuss their main ideas and advantages over other state-of-the-art approaches and compare strengths and weaknesses."}],"type":"working_paper","citation":{"mla":"Schneider, Stefan Balthasar. Conventional and Machine Learning Approaches for Network and Service Coordination. 2021.","bibtex":"@book{Schneider_2021, title={Conventional and Machine Learning Approaches for Network and Service Coordination}, author={Schneider, Stefan Balthasar}, year={2021} }","ama":"Schneider SB. Conventional and Machine Learning Approaches for Network and Service Coordination.; 2021.","apa":"Schneider, S. B. (2021). Conventional and Machine Learning Approaches for Network and Service Coordination.","chicago":"Schneider, Stefan Balthasar. Conventional and Machine Learning Approaches for Network and Service Coordination, 2021.","ieee":"S. B. Schneider, Conventional and Machine Learning Approaches for Network and Service Coordination. 2021.","short":"S.B. Schneider, Conventional and Machine Learning Approaches for Network and Service Coordination, 2021."},"year":"2021","language":[{"iso":"eng"}],"oa":"1","date_updated":"2023-01-10T15:09:05Z","_id":"35889"},{"year":"2020","type":"conference","citation":{"chicago":"Schneider, Stefan Balthasar, Adnan Manzoor, Haydar Qarawlus, Rafael Schellenberg, Holger Karl, Ramin Khalili, and Artur Hecker. “Self-Driving Network and Service Coordination Using Deep Reinforcement Learning.” In IEEE International Conference on Network and Service Management (CNSM). IEEE, 2020.","ama":"Schneider SB, Manzoor A, Qarawlus H, et al. Self-Driving Network and Service Coordination Using Deep Reinforcement Learning. In: IEEE International Conference on Network and Service Management (CNSM). IEEE; 2020.","apa":"Schneider, S. B., Manzoor, A., Qarawlus, H., Schellenberg, R., Karl, H., Khalili, R., & Hecker, A. (2020). Self-Driving Network and Service Coordination Using Deep Reinforcement Learning. In IEEE International Conference on Network and Service Management (CNSM). IEEE.","mla":"Schneider, Stefan Balthasar, et al. “Self-Driving Network and Service Coordination Using Deep Reinforcement Learning.” IEEE International Conference on Network and Service Management (CNSM), IEEE, 2020.","bibtex":"@inproceedings{Schneider_Manzoor_Qarawlus_Schellenberg_Karl_Khalili_Hecker_2020, title={Self-Driving Network and Service Coordination Using Deep Reinforcement Learning}, booktitle={IEEE International Conference on Network and Service Management (CNSM)}, publisher={IEEE}, author={Schneider, Stefan Balthasar and Manzoor, Adnan and Qarawlus, Haydar and Schellenberg, Rafael and Karl, Holger and Khalili, Ramin and Hecker, Artur}, year={2020} }","short":"S.B. Schneider, A. Manzoor, H. Qarawlus, R. Schellenberg, H. Karl, R. Khalili, A. Hecker, in: IEEE International Conference on Network and Service Management (CNSM), IEEE, 2020.","ieee":"S. B. Schneider et al., “Self-Driving Network and Service Coordination Using Deep Reinforcement Learning,” in IEEE International Conference on Network and Service Management (CNSM), 2020."},"_id":"19609","file":[{"date_created":"2020-09-22T06:29:16Z","file_name":"ris_with_copyright.pdf","access_level":"open_access","file_id":"19610","creator":"stschn","file_size":642999,"relation":"main_file","content_type":"application/pdf","date_updated":"2020-09-22T06:36:00Z"}],"publication":"IEEE International Conference on Network and Service Management (CNSM)","file_date_updated":"2020-09-22T06:36:00Z","keyword":["self-driving networks","self-learning","network coordination","service coordination","reinforcement learning","deep learning","nfv"],"publisher":"IEEE","author":[{"first_name":"Stefan Balthasar","full_name":"Schneider, Stefan Balthasar","orcid":"0000-0001-8210-4011","last_name":"Schneider","id":"35343"},{"full_name":"Manzoor, Adnan","first_name":"Adnan","last_name":"Manzoor"},{"last_name":"Qarawlus","full_name":"Qarawlus, Haydar","first_name":"Haydar"},{"first_name":"Rafael","full_name":"Schellenberg, Rafael","last_name":"Schellenberg"},{"last_name":"Karl","id":"126","first_name":"Holger","full_name":"Karl, Holger"},{"full_name":"Khalili, Ramin","first_name":"Ramin","last_name":"Khalili"},{"last_name":"Hecker","full_name":"Hecker, Artur","first_name":"Artur"}],"date_created":"2020-09-22T06:28:22Z","has_accepted_license":"1","status":"public","abstract":[{"lang":"eng","text":"Modern services comprise interconnected components,\r\ne.g., microservices in a service mesh, that can scale and\r\nrun on multiple nodes across the network on demand. To process\r\nincoming traffic, service components have to be instantiated and\r\ntraffic assigned to these instances, taking capacities and changing\r\ndemands into account. This challenge is usually solved with\r\ncustom approaches designed by experts. While this typically\r\nworks well for the considered scenario, the models often rely\r\non unrealistic assumptions or on knowledge that is not available\r\nin practice (e.g., a priori knowledge).\r\n\r\nWe propose a novel deep reinforcement learning approach that\r\nlearns how to best coordinate services and is geared towards\r\nrealistic assumptions. It interacts with the network and relies on\r\navailable, possibly delayed monitoring information. Rather than\r\ndefining a complex model or an algorithm how to achieve an\r\nobjective, our model-free approach adapts to various objectives\r\nand traffic patterns. An agent is trained offline without expert\r\nknowledge and then applied online with minimal overhead. Compared\r\nto a state-of-the-art heuristic, it significantly improves flow\r\nthroughput and overall network utility on real-world network\r\ntopologies and traffic traces. It also learns to optimize different\r\nobjectives, generalizes to scenarios with unseen, stochastic traffic\r\npatterns, and scales to large real-world networks."}],"user_id":"35343","ddc":["006"],"language":[{"iso":"eng"}],"date_updated":"2022-01-06T06:54:08Z","oa":"1","department":[{"_id":"75"}],"project":[{"_id":"1","name":"SFB 901"},{"_id":"4","name":"SFB 901 - Project Area C"},{"name":"SFB 901 - Subproject C4","_id":"16"}],"title":"Self-Driving Network and Service Coordination Using Deep Reinforcement Learning"},{"main_file_link":[{"open_access":"1","url":"https://arxiv.org/abs/1905.05992"}],"year":"2019","citation":{"ieee":"A. Redder, A. Ramaswamy, and D. Quevedo, “Deep reinforcement learning for scheduling in large-scale networked control systems,” in Proceedings of the 8th IFAC Workshop on Distributed Estimation and Control in Networked Systems, Chicago, USA, 2019.","short":"A. Redder, A. Ramaswamy, D. Quevedo, in: Proceedings of the 8th IFAC Workshop on Distributed Estimation and Control in Networked Systems, 2019.","bibtex":"@inproceedings{Redder_Ramaswamy_Quevedo_2019, title={Deep reinforcement learning for scheduling in large-scale networked control systems}, booktitle={Proceedings of the 8th IFAC Workshop on Distributed Estimation and Control in Networked Systems}, author={Redder, Adrian and Ramaswamy, Arunselvan and Quevedo, Daniel}, year={2019} }","mla":"Redder, Adrian, et al. “Deep Reinforcement Learning for Scheduling in Large-Scale Networked Control Systems.” Proceedings of the 8th IFAC Workshop on Distributed Estimation and Control in Networked Systems, 2019.","chicago":"Redder, Adrian, Arunselvan Ramaswamy, and Daniel Quevedo. “Deep Reinforcement Learning for Scheduling in Large-Scale Networked Control Systems.” In Proceedings of the 8th IFAC Workshop on Distributed Estimation and Control in Networked Systems, 2019.","apa":"Redder, A., Ramaswamy, A., & Quevedo, D. (2019). Deep reinforcement learning for scheduling in large-scale networked control systems. In Proceedings of the 8th IFAC Workshop on Distributed Estimation and Control in Networked Systems. Chicago, USA.","ama":"Redder A, Ramaswamy A, Quevedo D. Deep reinforcement learning for scheduling in large-scale networked control systems. In: Proceedings of the 8th IFAC Workshop on Distributed Estimation and Control in Networked Systems. ; 2019."},"type":"conference","_id":"13443","conference":{"end_date":"2019-09-17","name":"8th IFAC Workshop on Distributed Estimation and Control in Networked Systems - NECSYS 2019","start_date":"2019-09-16","location":"Chicago, USA"},"author":[{"last_name":"Redder","id":"52265","first_name":"Adrian","full_name":"Redder, Adrian","orcid":"https://orcid.org/0000-0001-7391-4688"},{"id":"66937","last_name":"Ramaswamy","full_name":"Ramaswamy, Arunselvan","orcid":"https://orcid.org/ 0000-0001-7547-8111","first_name":"Arunselvan"},{"first_name":"Daniel","full_name":"Quevedo, Daniel","last_name":"Quevedo"}],"file_date_updated":"2019-09-23T16:21:16Z","publication":"Proceedings of the 8th IFAC Workshop on Distributed Estimation and Control in Networked Systems","keyword":["Networked control systems","deep reinforcement learning","large-scale systems","resource scheduling","stochastic control"],"file":[{"content_type":"application/pdf","date_updated":"2019-09-23T16:21:16Z","relation":"main_file","file_size":371429,"creator":"aredder","file_id":"13444","access_level":"local","date_created":"2019-09-23T15:48:33Z","file_name":"ifacconf.pdf"}],"has_accepted_license":"1","status":"public","date_created":"2019-09-23T16:00:58Z","abstract":[{"lang":"eng","text":"This work considers the problem of control and resource allocation in networked\r\nsystems. To this end, we present DIRA a Deep reinforcement learning based Iterative Resource\r\nAllocation algorithm, which is scalable and control-aware. Our algorithm is tailored towards\r\nlarge-scale problems where control and scheduling need to act jointly to optimize performance.\r\nDIRA can be used to schedule general time-domain optimization based controllers. In the present\r\nwork, we focus on control designs based on suitably adapted linear quadratic regulators. We\r\napply our algorithm to networked systems with correlated fading communication channels. Our\r\nsimulations show that DIRA scales well to large scheduling problems."}],"ddc":["620"],"user_id":"52265","language":[{"iso":"eng"}],"date_updated":"2022-01-06T06:51:36Z","oa":"1","publication_status":"published","project":[{"_id":"52","name":"Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"title":"Deep reinforcement learning for scheduling in large-scale networked control systems"}]