[{"citation":{"apa":"Hasnain, A., &#38; Karl, H. (n.d.). Learning Flow Scheduling. In <i>2021 IEEE 18th Annual Consumer Communications &#38; Networking Conference (CCNC)</i>. Las Vegas, USA: IEEE Computer Society. <a href=\"https://doi.org/10.1109/CCNC49032.2021.9369514\">https://doi.org/10.1109/CCNC49032.2021.9369514</a>","bibtex":"@inproceedings{Hasnain_Karl, title={Learning Flow Scheduling}, DOI={<a href=\"https://doi.org/10.1109/CCNC49032.2021.9369514\">https://doi.org/10.1109/CCNC49032.2021.9369514</a>}, booktitle={2021 IEEE 18th Annual Consumer Communications &#38; Networking Conference (CCNC)}, publisher={IEEE Computer Society}, author={Hasnain, Asif and Karl, Holger} }","mla":"Hasnain, Asif, and Holger Karl. “Learning Flow Scheduling.” <i>2021 IEEE 18th Annual Consumer Communications &#38; Networking Conference (CCNC)</i>, IEEE Computer Society, doi:<a href=\"https://doi.org/10.1109/CCNC49032.2021.9369514\">https://doi.org/10.1109/CCNC49032.2021.9369514</a>.","short":"A. Hasnain, H. Karl, in: 2021 IEEE 18th Annual Consumer Communications &#38; Networking Conference (CCNC), IEEE Computer Society, n.d.","chicago":"Hasnain, Asif, and Holger Karl. “Learning Flow Scheduling.” In <i>2021 IEEE 18th Annual Consumer Communications &#38; Networking Conference (CCNC)</i>. IEEE Computer Society, n.d. <a href=\"https://doi.org/10.1109/CCNC49032.2021.9369514\">https://doi.org/10.1109/CCNC49032.2021.9369514</a>.","ieee":"A. Hasnain and H. Karl, “Learning Flow Scheduling,” in <i>2021 IEEE 18th Annual Consumer Communications &#38; Networking Conference (CCNC)</i>, Las Vegas, USA.","ama":"Hasnain A, Karl H. Learning Flow Scheduling. In: <i>2021 IEEE 18th Annual Consumer Communications &#38; Networking Conference (CCNC)</i>. IEEE Computer Society. doi:<a href=\"https://doi.org/10.1109/CCNC49032.2021.9369514\">https://doi.org/10.1109/CCNC49032.2021.9369514</a>"},"year":"2021","publication_status":"accepted","conference":{"start_date":"2021-01-09","name":"2021 IEEE 18th Annual Consumer Communications & Networking Conference (CCNC)","location":"Las Vegas, USA","end_date":"2021-01-12"},"doi":"https://doi.org/10.1109/CCNC49032.2021.9369514","main_file_link":[{"url":"https://ieeexplore.ieee.org/document/9369514"}],"title":"Learning Flow Scheduling","date_created":"2020-10-19T14:27:17Z","author":[{"first_name":"Asif","last_name":"Hasnain","id":"63288","full_name":"Hasnain, Asif"},{"last_name":"Karl","id":"126","full_name":"Karl, Holger","first_name":"Holger"}],"publisher":"IEEE Computer Society","date_updated":"2022-01-06T06:54:20Z","status":"public","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"}],"publication":"2021 IEEE 18th Annual Consumer Communications & Networking Conference (CCNC)","type":"conference","language":[{"iso":"eng"}],"keyword":["Flow scheduling","Deadlines","Reinforcement learning"],"ddc":["000"],"department":[{"_id":"75"}],"user_id":"63288","_id":"20125","project":[{"name":"SFB 901 - Project Area C","_id":"4"},{"_id":"16","name":"SFB 901 - Subproject C4"},{"_id":"1","name":"SFB 901"}]},{"doi":"10.1109/TNET.2012.2227792","title":"On the Admission of Dependent Flows in Powerful Sensor Networks","volume":21,"author":[{"full_name":"Cohen, R.","last_name":"Cohen","first_name":"R."},{"first_name":"I.","full_name":"Nudelman, I.","last_name":"Nudelman"},{"first_name":"Gleb","last_name":"Polevoy","id":"83983","full_name":"Polevoy, Gleb"}],"date_created":"2020-08-06T15:22:05Z","date_updated":"2022-01-06T06:53:16Z","page":"1461-1471","intvolume":"        21","citation":{"apa":"Cohen, R., Nudelman, I., &#38; Polevoy, G. (2013). On the Admission of Dependent Flows in Powerful Sensor Networks. <i>Networking, IEEE/ACM Transactions On</i>, <i>21</i>(5), 1461–1471. <a href=\"https://doi.org/10.1109/TNET.2012.2227792\">https://doi.org/10.1109/TNET.2012.2227792</a>","bibtex":"@article{Cohen_Nudelman_Polevoy_2013, title={On the Admission of Dependent Flows in Powerful Sensor Networks}, volume={21}, DOI={<a href=\"https://doi.org/10.1109/TNET.2012.2227792\">10.1109/TNET.2012.2227792</a>}, number={5}, journal={Networking, IEEE/ACM Transactions on}, author={Cohen, R. and Nudelman, I. and Polevoy, Gleb}, year={2013}, pages={1461–1471} }","mla":"Cohen, R., et al. “On the Admission of Dependent Flows in Powerful Sensor Networks.” <i>Networking, IEEE/ACM Transactions On</i>, vol. 21, no. 5, 2013, pp. 1461–71, doi:<a href=\"https://doi.org/10.1109/TNET.2012.2227792\">10.1109/TNET.2012.2227792</a>.","short":"R. Cohen, I. Nudelman, G. Polevoy, Networking, IEEE/ACM Transactions On 21 (2013) 1461–1471.","ama":"Cohen R, Nudelman I, Polevoy G. On the Admission of Dependent Flows in Powerful Sensor Networks. <i>Networking, IEEE/ACM Transactions on</i>. 2013;21(5):1461-1471. doi:<a href=\"https://doi.org/10.1109/TNET.2012.2227792\">10.1109/TNET.2012.2227792</a>","chicago":"Cohen, R., I. Nudelman, and Gleb Polevoy. “On the Admission of Dependent Flows in Powerful Sensor Networks.” <i>Networking, IEEE/ACM Transactions On</i> 21, no. 5 (2013): 1461–71. <a href=\"https://doi.org/10.1109/TNET.2012.2227792\">https://doi.org/10.1109/TNET.2012.2227792</a>.","ieee":"R. Cohen, I. Nudelman, and G. Polevoy, “On the Admission of Dependent Flows in Powerful Sensor Networks,” <i>Networking, IEEE/ACM Transactions on</i>, vol. 21, no. 5, pp. 1461–1471, 2013."},"year":"2013","issue":"5","publication_identifier":{"issn":["1063-6692"]},"extern":"1","language":[{"iso":"eng"}],"keyword":["Approximation algorithms","Approximation methods","Bandwidth","Logic gates","Radar","Vectors","Wireless sensor networks","Dependent flow scheduling","sensor networks"],"department":[{"_id":"63"},{"_id":"541"}],"user_id":"83983","_id":"17663","status":"public","abstract":[{"lang":"eng","text":"In this paper, we define and study a new problem, referred to as the Dependent Unsplittable Flow Problem (D-UFP). We present and discuss this problem in the context of large-scale powerful (radar/camera) sensor networks, but we believe it has important applications on the admission of large flows in other networks as well. In order to optimize the selection of flows transmitted to the gateway, D-UFP takes into account possible dependencies between flows. We show that D-UFP is more difficult than NP-hard problems for which no good approximation is known. Then, we address two special cases of this problem: the case where all the sensors have a shared channel and the case where the sensors form a mesh and route to the gateway over a spanning tree."}],"publication":"Networking, IEEE/ACM Transactions on","type":"journal_article"}]