@article{65495, abstract = {{This paper presents a holistic framework for the transition from diesel to electric bus networks, crucial for meeting EU regulations targeting 100% zero-emission urban buses by 2035. We employ a two-phase solution framework: in phase 1, we solve the Charging Location and Electric Vehicle Scheduling Problem to generate vehicle schedules that are feasible for electric operation; in phase 2, these schedules serve as input to a multi-period transition planning model that minimizes the total cost of ownership while determining fleet replacement and charging infrastructure deployment. Our experiments show that schedules obtained from solving the integrated charging location and vehicle scheduling problem significantly outperform traditional methods, resulting in lower total cost of ownership. Additionally, transition plans reduce local emissions by up to 85% compared to a diesel-only scenario. We find that vehicle rotations with long distances and sufficient idle time are prioritized for electrification, enabling earlier emission reductions and cost savings. This highlights the importance of adopting vehicle scheduling tailored for electric buses, rather than relying on legacy diesel schedules.}}, author = {{Stumpe, Miriam and Rößler-von Saß, David and Natalia, Kliewer and Schryen, Guido}}, journal = {{Transportation Research Interdisciplinary Perspectives}}, keywords = {{electric bus, multi-period planning, electric vehicle scheduling, charging infrastructure, fleet replacement}}, title = {{{Impact of Vehicle Scheduling and Strategic Transition Planning on Zero-Emission Bus Systems}}}, year = {{2026}}, } @article{65857, abstract = {{This paper presents a holistic framework for the transition from diesel to electric bus networks, crucial for meeting EU regulations targeting 100% zero-emission urban buses by 2035. We employ a two-phase solution framework: in phase 1, we solve the Charging Location and Electric Vehicle Scheduling Problem to generate vehicle schedules that are feasible for electric operation; in phase 2, these schedules serve as input to a multi-period transition planning model that minimizes the total cost of ownership while determining fleet replacement and charging infrastructure deployment. Our experiments show that schedules obtained from solving the integrated charging location and vehicle scheduling problem significantly outperform traditional methods, resulting in lower total cost of ownership. Additionally, transition plans reduce local emissions by up to 85% compared to a diesel-only scenario. We find that vehicle rotations with long distances and sufficient idle time are prioritized for electrification, enabling earlier emission reductions and cost savings. This highlights the importance of adopting vehicle scheduling tailored for electric buses, rather than relying on legacy diesel schedules.}}, author = {{Stumpe, Miriam and Rößler-von Saß, David and Kliewer, Natalia and Schryen, Guido}}, issn = {{2590-1982}}, journal = {{Transportation Research Interdisciplinary Perspectives}}, keywords = {{Electric bus, Multi-period planning, Electric vehicle scheduling, Charging infrastructure, Fleet replacement}}, publisher = {{Elsevier BV}}, title = {{{Impact of vehicle scheduling and strategic transition planning on zero-emission bus systems}}}, doi = {{10.1016/j.trip.2026.102008}}, volume = {{38}}, year = {{2026}}, } @inproceedings{20125, abstract = {{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.}}, author = {{Hasnain, Asif and Karl, Holger}}, booktitle = {{2021 IEEE 18th Annual Consumer Communications & Networking Conference (CCNC)}}, keywords = {{Flow scheduling, Deadlines, Reinforcement learning}}, location = {{Las Vegas, USA}}, publisher = {{IEEE Computer Society}}, title = {{{Learning Flow Scheduling}}}, doi = {{https://doi.org/10.1109/CCNC49032.2021.9369514}}, year = {{2021}}, } @inproceedings{21005, abstract = {{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.}}, author = {{Hasnain, Asif and Karl, Holger}}, booktitle = {{IEEE INFOCOM 2021 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)}}, keywords = {{Coflow scheduling, Reinforcement learning, Deadlines}}, location = {{Vancouver BC Canada}}, publisher = {{IEEE Communications Society}}, title = {{{Learning Coflow Admissions}}}, doi = {{10.1109/INFOCOMWKSHPS51825.2021.9484599}}, year = {{2021}}, } @inproceedings{17082, abstract = {{Data-parallel applications run on cluster of servers in a datacenter and their communication triggers correlated resource demand on multiple links that can be abstracted as coflow. They often desire predictable network performance, which can be passed to network via coflow abstraction for application-aware network scheduling. In this paper, we propose a heuristic and an optimization algorithm for predictable network performance such that they guarantee coflows completion within their deadlines. The algorithms also ensure high network utilization, i.e., it's work-conserving, and avoids starvation of coflows. We evaluate both algorithms via trace-driven simulation and show that they admit 1.1x more coflows than the Varys scheme while meeting their deadlines.}}, author = {{Hasnain, Asif and Karl, Holger}}, booktitle = {{2020 20th IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing (CCGRID)}}, keywords = {{Coflow, Scheduling, Deadlines, Data centers}}, location = {{Melbourne, Australia}}, publisher = {{IEEE Computer Society}}, title = {{{Coflow Scheduling with Performance Guarantees for Data Center Applications}}}, doi = {{https://doi.org/10.1109/CCGrid49817.2020.00010}}, year = {{2020}}, } @article{5674, abstract = {{In disaster operations management, a challenging task for rescue organizations occurs when they have to assign and schedule their rescue units to emerging incidents under time pressure in order to reduce the overall resulting harm. Of particular importance in practical scenarios is the need to consider collaboration of rescue units. This task has hardly been addressed in the literature. We contribute to both modeling and solving this problem by (1) conceptualizing the situation as a type of scheduling problem, (2) modeling it as a binary linear minimization problem, (3) suggesting a branch-and-price algorithm, which can serve as both an exact and heuristic solution procedure, and (4) conducting computational experiments - including a sensitivity analysis of the effects of exogenous model parameters on execution times and objective value improvements over a heuristic suggested in the literature - for different practical disaster scenarios. The results of our computational experiments show that most problem instances of practically feasible size can be solved to optimality within ten minutes. Furthermore, even when our algorithm is terminated once the first feasible solution has been found, this solution is in almost all cases competitive to the optimal solution and substantially better than the solution obtained by the best known algorithm from the literature. This performance of our branch-and-price algorithm enables rescue organizations to apply our procedure in practice, even when the time for decision making is limited to a few minutes. By addressing a very general type of scheduling problem, our approach applies to various scheduling situations.}}, author = {{Rauchecker, Gerhard and Schryen, Guido}}, journal = {{European Journal of Operational Research}}, keywords = {{OR in disaster relief, disaster operations management, scheduling, branch-and-price}}, number = {{1}}, pages = {{352 -- 363}}, publisher = {{Elsevier}}, title = {{{An Exact Branch-and-Price Algorithm for Scheduling Rescue Units during Disaster Response}}}, volume = {{272}}, year = {{2019}}, } @article{6512, abstract = {{Scheduling problems are essential for decision making in many academic disciplines, including operations management, computer science, and information systems. Since many scheduling problems are NP-hard in the strong sense, there is only limited research on exact algorithms and how their efficiency scales when implemented on parallel computing architectures. We address this gap by (1) adapting an exact branch-and-price algorithm to a parallel machine scheduling problem on unrelated machines with sequence- and machine-dependent setup times, (2) parallelizing the adapted algorithm by implementing a distributed-memory parallelization with a master/worker approach, and (3) conducting extensive computational experiments using up to 960 MPI processes on a modern high performance computing cluster. With our experiments, we show that the efficiency of our parallelization approach can lead to superlinear speedup but can vary substantially between instances. We further show that the wall time of serial execution can be substantially reduced through our parallelization, in some cases from 94 hours to less than six minutes when our algorithm is executed on 960 processes.}}, author = {{Rauchecker, Gerhard and Schryen, Guido}}, journal = {{Computers & Operations Research}}, keywords = {{parallel machine scheduling with setup times, parallel branch-and-price algorithm, high performance computing, master/worker parallelization}}, number = {{104}}, pages = {{338--357}}, publisher = {{Elsevier}}, title = {{{Using High Performance Computing for Unrelated Parallel Machine Scheduling with Sequence-Dependent Setup Times: Development and Computational Evaluation of a Parallel Branch-and-Price Algorithm}}}, year = {{2019}}, } @inproceedings{13443, abstract = {{This work considers the problem of control and resource allocation in networked systems. To this end, we present DIRA a Deep reinforcement learning based Iterative Resource Allocation algorithm, which is scalable and control-aware. Our algorithm is tailored towards large-scale problems where control and scheduling need to act jointly to optimize performance. DIRA can be used to schedule general time-domain optimization based controllers. In the present work, we focus on control designs based on suitably adapted linear quadratic regulators. We apply our algorithm to networked systems with correlated fading communication channels. Our simulations show that DIRA scales well to large scheduling problems.}}, author = {{Redder, Adrian and Ramaswamy, Arunselvan and Quevedo, Daniel}}, booktitle = {{Proceedings of the 8th IFAC Workshop on Distributed Estimation and Control in Networked Systems}}, keywords = {{Networked control systems, deep reinforcement learning, large-scale systems, resource scheduling, stochastic control}}, location = {{Chicago, USA}}, title = {{{Deep reinforcement learning for scheduling in large-scale networked control systems}}}, year = {{2019}}, } @inproceedings{22, abstract = {{This paper describes a data structure and a heuristic to plan and map arbitrary resources in complex combinations while applying time dependent constraints. The approach is used in the planning based workload manager OpenCCS at the Paderborn Center for Parallel Computing (PC\(^2\)) to operate heterogeneous clusters with up to 10000 cores. We also show performance results derived from four years of operation.}}, author = {{Keller, Axel}}, booktitle = {{Proc. Workshop on Job Scheduling Strategies for Parallel Processing (JSSPP)}}, editor = {{Klusáček, D. and Cirne, W. and Desai, N.}}, isbn = {{978-3-319-77398-8}}, keywords = {{Scheduling Planning Mapping Workload management}}, location = {{Orlando, FL, USA}}, pages = {{132--151}}, publisher = {{Springer}}, title = {{{A Data Structure for Planning Based Workload Management of Heterogeneous HPC Systems}}}, doi = {{10.1007/978-3-319-77398-8_8}}, volume = {{10773}}, year = {{2018}}, } @inproceedings{5675, abstract = {{When responding to natural disasters, professional relief units are often supported by many volunteers which are not affiliated to humanitarian organizations. The effective coordination of these volunteers is crucial to leverage their capabilities and to avoid conflicts with professional relief units. In this paper, we empirically identify key requirements that professional relief units pose on this coordination. Based on these requirements, we suggest a decision model. We computationally solve a real-world instance of the model and empirically validate the computed solution in interviews with practitioners. Our results show that the suggested model allows for solving volunteer coordination tasks of realistic size near-optimally within short time, with the determined solution being well accepted by practitioners. We also describe in this article how the suggested decision support model is integrated in the volunteer coordination system which we develop in joint cooperation with a disaster management authority and a software development company.}}, author = {{Rauchecker, Gerhard and Schryen, Guido}}, booktitle = {{Proceedings of the 15th International Conference on Information Systems for Crisis Response and Management}}, keywords = {{Coordination of spontaneous volunteers, volunteer coordination system, decision support, scheduling optimization model, linear programming}}, location = {{Rochester, NY, USA}}, title = {{{Decision Support for the Optimal Coordination of Spontaneous Volunteers in Disaster Relief}}}, year = {{2018}}, } @inproceedings{48856, abstract = {{There exist many optimal or heuristic priority rules for machine scheduling problems, which can easily be integrated into single-objective evolutionary algorithms via mutation operators. However, in the multi-objective case, simultaneously applying different priorities for different objectives may cause severe disruptions in the genome and may lead to inferior solutions. In this paper, we combine an existing mutation operator concept with new insights from detailed observation of the structure of solutions for multi-objective machine scheduling problems. This allows the comprehensive integration of priority rules to produce better Pareto-front approximations. We evaluate the extended operator concept compared to standard swap mutation and the stand-alone components of our hybrid scheme, which performs best in all evaluated cases.}}, author = {{Bossek, Jakob and Grimme, Christian}}, booktitle = {{2017 IEEE Symposium Series on Computational Intelligence (SSCI)}}, keywords = {{Evolutionary computation, Processor scheduling, Schedules, Scheduling, Sociology, Standards, Statistics}}, pages = {{1–8}}, title = {{{An Extended Mutation-Based Priority-Rule Integration Concept for Multi-Objective Machine Scheduling}}}, doi = {{10.1109/SSCI.2017.8285224}}, year = {{2017}}, } @article{17657, abstract = {{Inter-datacenter transfers of non-interactive but timely large flows over a private (managed) network is an important problem faced by many cloud service providers. The considered flows are non-interactive because they do not explicitly target the end users. However, most of them must be performed on a timely basis and are associated with a deadline. We propose to schedule these flows by a centralized controller, which determines when to transmit each flow and which path to use. Two scheduling models are presented in this paper. In the first, the controller also determines the rate of each flow, while in the second bandwidth is assigned by the network according to the TCP rules. We develop scheduling algorithms for both models and compare their complexity and performance.}}, author = {{Cohen, R. and Polevoy, Gleb}}, issn = {{2168-7161}}, journal = {{Cloud Computing, IEEE Transactions on}}, keywords = {{Approximation algorithms, Approximation methods, Bandwidth, Cloud computing, Routing, Schedules, Scheduling}}, number = {{99}}, pages = {{1--1}}, title = {{{Inter-Datacenter Scheduling of Large Data Flows}}}, doi = {{10.1109/TCC.2015.2487964}}, volume = {{PP}}, year = {{2015}}, } @inproceedings{5678, abstract = {{Many academic disciplines - including information systems, computer science, and operations management - face scheduling problems as important decision making tasks. Since many scheduling problems are NP-hard in the strong sense, there is a need for developing solution heuristics. For scheduling problems with setup times on unrelated parallel machines, there is limited research on solution methods and to the best of our knowledge, parallel computer architectures have not yet been taken advantage of. We address this gap by proposing and implementing a new solution heuristic and by testing different parallelization strategies. In our computational experiments, we show that our heuristic calculates near-optimal solutions even for large instances and that computing time can be reduced substantially by our parallelization approach.}}, author = {{Rauchecker, Gerhard and Schryen, Guido}}, booktitle = {{Australasian Conference on Information Systems}}, keywords = {{scheduling, decision support, heuristic, high performance computing, parallel algorithms}}, pages = {{1--13}}, title = {{{High-Performance Computing for Scheduling Decision Support: A Parallel Depth-First Search Heuristic}}}, year = {{2015}}, } @inproceedings{10779, author = {{Guettatfi, Zakarya and Kermia, Omar and Khouas, Abdelhakim}}, booktitle = {{25th International Conference on Field Programmable Logic and Applications (FPL)}}, issn = {{1946-147X}}, keywords = {{embedded systems, field programmable gate arrays, operating systems (computers), scheduling, μC/OS-II, FPGAs, OS foundation, SafeRTOS, Xenomai, chip utilization ration, complex time constraints, embedded systems, hard real-time hardware task allocation, hard real-time hardware task scheduling, hardware-software real-time operating systems, partially reconfigurable field-programmable gate arrays, resource constraints, safety-critical RTOS, Field programmable gate arrays, Hardware, Job shop scheduling, Real-time systems, Shape, Software}}, publisher = {{Imperial College}}, title = {{{Over effective hard real-time hardware tasks scheduling and allocation}}}, doi = {{10.1109/FPL.2015.7293994}}, year = {{2015}}, } @article{17663, abstract = {{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.}}, author = {{Cohen, R. and Nudelman, I. and Polevoy, Gleb}}, issn = {{1063-6692}}, journal = {{Networking, IEEE/ACM Transactions on}}, keywords = {{Approximation algorithms, Approximation methods, Bandwidth, Logic gates, Radar, Vectors, Wireless sensor networks, Dependent flow scheduling, sensor networks}}, number = {{5}}, pages = {{1461--1471}}, title = {{{On the Admission of Dependent Flows in Powerful Sensor Networks}}}, doi = {{10.1109/TNET.2012.2227792}}, volume = {{21}}, year = {{2013}}, } @inproceedings{37009, abstract = {{Today, mobile and embedded real time systems have to cope with the migration and allocation of multiple software tasks running on top of a real time operating system (RTOS) residing on one or several processors. For scaling of each task set and processor configuration, instruction set simulation and worst case timing analysis are typically applied. This paper presents a complementary approach for the verification of RTOS properties based on an abstract RTOS-Model in SystemC. We apply IEEE P1850 PSL for which we present an approach and first experiences for the assertion-based verification of RTOS properties.}}, author = {{Oliveira, Marcio F. S. and Zabel, Henning and Müller, Wolfgang}}, booktitle = {{Proceedings of DATE’10}}, keywords = {{Operating systems, Real time systems, Timing, Hardware, Analytical models, Embedded software, Software systems, Processor scheduling, Software performance, Performance analysis}}, location = {{Dresden}}, publisher = {{IEEE}}, title = {{{Assertion-Based Verification of RTOS Properties}}}, doi = {{10.1109/DATE.2010.5457130}}, year = {{2010}}, } @inbook{33813, abstract = {{Today, mobile and embedded real-time systems have to cope with the migration and allocation of multiple software tasks running on top of a real-time operating system (RTOS) residing on one or several system processors. Each RTOS has to be configured towards the individual needs of the application and environment. For this, different scheduling strategies and task priorities have to be evaluated in order to keep execution and response times for a given task set. Abstract RTOS simulation is applied to analyze different parameters in early design phases. This chapter presents a SystemC RTOS library for abstract yet accurate RTOS sim- ulation, supporting modeling of preemption in the presence of prioritized and nested interrupts. After introducing basic principles of abstract RTOS simula- tion, we present our SystemC library in detail. Thereafter, we discuss related approaches and close with applications in electronic automotive systems design and some evaluations.}}, author = {{Zabel, Henning and Müller, Wolfgang and Gerstlauer, Andreas}}, booktitle = {{Hardware Dependent Software - Principles and Practice}}, editor = {{Ecker, Wolfgang and Müller, Wolfgang and Dömer, Rainer}}, isbn = {{978-1-4020-9435-4}}, keywords = {{RTOS Modelling, RTOS Simulation, SystemC, Task Scheduling, Interrupt Analysis}}, pages = {{233--260}}, publisher = {{Springer Verlag}}, title = {{{Accurate RTOS Modelling and Analysis with SystemC}}}, doi = {{10.1007/978-1-4020-9436-1_9}}, year = {{2009}}, } @inproceedings{37066, abstract = {{Today, mobile and embedded real-time systems have to cope with the migration and allocation of multiple software tasks running on top of a real-time operating system (RTOS) residing on one or multiple system processors. Abstract RTOS simulations and timing analysis applies for fast and early estimation to configure it towards the individual needs of the application and environment. In this context, a high accuracy of the simulation compared to an instruction set simulation (ISS) is of key importance. In this paper, we investigate the accuracy of abstract RTOS simulation and compare it to ISS and the behavior of the physical system. We show that we can reach an increased accuracy of the simulation when we inject noise into the time model. Our results indicate that it is sufficient to inject uniformly distributed random time values to the RTOS real-time clock.}}, author = {{Zabel, Henning and Müller, Wolfgang}}, booktitle = {{Proceedings of DATE'09}}, isbn = {{978-1-4244-3781-8}}, keywords = {{Timing, Analytical models, Clocks, Performance analysis, Scheduling, Operating systems, Delay, Real time systems, Application software, Context modeling}}, title = {{{Increased Accuracy through Noise Injection in Abstract RTOS Simulation}}}, doi = {{10.1109/DATE.2009.5090925}}, year = {{2009}}, } @article{10646, author = {{Danne, Klaus and Mühlenbernd, Roland and Platzner, Marco}}, issn = {{1751-8601}}, journal = {{IET Computers Digital Techniques}}, keywords = {{reconfigurable architectures, resource allocation, device reconfiguration time, dynamic hardware reconfiguration, dynamically reconfigurable hardware, light-weight runtime system, merge server distribute load, periodic real-time tasks, runtime system overheads, schedulability analysis, scheduling technique, server-based execution, synthesis tool flow}}, number = {{4}}, pages = {{295--302}}, title = {{{Server-based execution of periodic tasks on dynamically reconfigurable hardware}}}, doi = {{10.1049/iet-cdt:20060186}}, volume = {{1}}, year = {{2007}}, } @inproceedings{39526, abstract = {{The main goal of the article is to evaluate the suitability of visual programming languages, i.e., Pictorial Janus (K. Kahn and V. Saraswat, 1990), for the modeling of complex systems and their control strategies. These systems can be seen as networks of communicating objects. Objects select strategies for suitable actions based on incoming messages. Our field of investigation is in computer integrated manufacturing considering the example of a car manufacturing cell. This color sorting assembly buffer (CSAB) schedules jobs in queues. The jobs represent car bodies scheduled in feeder lines for the enameling. Feeder lines collect raw bodies to blocks. Blocks are bodies which are to be enameled by the same color. This organization decreases the cost of expensive change-over-times when changing colors at the enamelling. Blocks of bodies are dislocated from the queue and enameled successively. Contradictory system goals, such as minimizing color changes and preserving the sequence of incoming jobs, have to be regarded by appropriate control strategies. Due to the complexity of this (NP complete) problem and to real time requirements for online control there are no optimal strategies on hand. Consequently, suitable heuristics have to be developed. Often they are designed applying a trial-and-error method. A modeling framework has to support the rapid prototyping of these systems as well as an expressive end user oriented representation. Both are essential requirements since end users need other visualization techniques than experienced designers due to their different knowledge and interests.}}, author = {{Geiger, Christian and Hunstock, R. and Lehrenfeld, Georg and Müller, Wolfgang and Quintanilla, J. and Tahedl, C. and Weber, A.}}, booktitle = {{Proceedings of the 1996 IEEE Symposium on Visual Languages}}, isbn = {{0-8186-7508-X}}, keywords = {{Computer integrated manufacturing, Job shop scheduling, Processor scheduling, Computer languages, Control system synthesis, Computer aided manufacturing, Sorting, Assembly, Costs, Control systems}}, title = {{{Visual Modeling and 3D-Representation with a Complete Visual Programming Language --- A Case Study in Manufacturing}}}, doi = {{10.1109/VL.1996.545302}}, year = {{1996}}, }