Suat Gumussoy
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Suat Gumussoy has a total of 54 co-authors. Here are the top co-authors by number of shared publications:
- Wim Michiels
Department of Computer Science, KU Leuven, Heverlee, Belgium
19 shared publications - Hitay Özbay
Department of Electrical and Electronics Engineering, Bilkent University, Ankara 06800, Turkey
9 shared publications Wim Michiels
8 shared publications- Umit Yusuf Ogras
University of Wisconsin - Madison, Madison, WI, USA
5 shared publications Umit Y. Ogras
3 shared publicationsAhmet Arda Ozdemir
2 shared publications
Latest Publications
- 26 May 2025
- Published by Elsevier in IFAC Journal of Systems and Control
- Vol. 32
A bottom-up approach for searching for sparse controllers with a budget
- 26 May 2025
- Published by Elsevier in IFAC Journal of Systems and Control
- Vol. 32
A bottom-up approach for searching for sparse controllers with a budget
- 26 February 2025
- Published by Springer Nature in Forschung im Ingenieurwesen
- Vol. 89 (1) , 1-11
Conceptual closed-loop design of automotive cooling systems leveraging Reinforcement Learning
- 26 February 2025
- Published by Springer Nature in Forschung im Ingenieurwesen
- Vol. 89 (1) , 1-11
Conceptual closed-loop design of automotive cooling systems leveraging Reinforcement Learning
- 2 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Control of Network Systems
- Vol. 12 (1) , 18-27
Certifying Stability and Performance of Uncertain Differential–Algebraic Systems: A Dissipativity Framework
This paper presents a novel framework for characterizing dissipativity of uncertain systems whose dynamics evolve according to differential-algebraic equations. Sufficient conditions for dissipativity (specializing to, e.g., stability or $L_{2}$ gain bounds) are provided in the case that uncertainties are characterized by integral quadratic constraints. For polynomial or linear dynamics, these conditions can be efficiently verified through sum-of-squares or semidefinite programming. Performance analysis of the IEEE 39-bus power network with a set of potential line failures modeled as an uncertainty set provides an illustrative example that highlights the computational tractability of this approach; conservatism introduced in this example is shown to be quite minimal.
- 2 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Control of Network Systems
- Vol. 12 (1) , 18-27
Certifying Stability and Performance of Uncertain Differential–Algebraic Systems: A Dissipativity Framework
This paper presents a novel framework for characterizing dissipativity of uncertain systems whose dynamics evolve according to differential-algebraic equations. Sufficient conditions for dissipativity (specializing to, e.g., stability or $L_{2}$ gain bounds) are provided in the case that uncertainties are characterized by integral quadratic constraints. For polynomial or linear dynamics, these conditions can be efficiently verified through sum-of-squares or semidefinite programming. Performance analysis of the IEEE 39-bus power network with a set of potential line failures modeled as an uncertainty set provides an illustrative example that highlights the computational tractability of this approach; conservatism introduced in this example is shown to be quite minimal.
- Open Access
Learning Emergence of Interaction Patterns across Independent RL Agents in Multi-Agent Environments
Many real-world problems, such as controlling swarms of drones and urban traffic, naturally lend themselves to modeling as multi-agent reinforcement learning (RL) problems. However, existing multi-agent RL methods often suffer from scalability challenges, primarily due to the introduction of communication among agents. Consequently, a key challenge lies in adapting the success of deep learning in single-agent RL to the multi-agent setting. In response to this challenge, we propose an approach that fundamentally reimagines multi-agent environments. Unlike conventional methods that model each agent individually with separate networks, our approach, the Bottom Up Network (BUN), adopts a unique perspective. BUN treats the collective of multi-agents as a unified entity while employing a specialized weight initialization strategy that promotes independent learning. Furthermore, we dynamically establish connections among agents using gradient information, enabling coordination when necessary while maintaining these connections as limited and sparse to effectively manage the computational budget. Our extensive empirical evaluations across a variety of cooperative multi-agent scenarios, including tasks such as cooperative navigation and traffic control, consistently demonstrate BUN's superiority over baseline methods with substantially reduced computational costs.
Open AccessLearning Emergence of Interaction Patterns across Independent RL Agents in Multi-Agent Environments
Many real-world problems, such as controlling swarms of drones and urban traffic, naturally lend themselves to modeling as multi-agent reinforcement learning (RL) problems. However, existing multi-agent RL methods often suffer from scalability challenges, primarily due to the introduction of communication among agents. Consequently, a key challenge lies in adapting the success of deep learning in single-agent RL to the multi-agent setting. In response to this challenge, we propose an approach that fundamentally reimagines multi-agent environments. Unlike conventional methods that model each agent individually with separate networks, our approach, the Bottom Up Network (BUN), adopts a unique perspective. BUN treats the collective of multi-agents as a unified entity while employing a specialized weight initialization strategy that promotes independent learning. Furthermore, we dynamically establish connections among agents using gradient information, enabling coordination when necessary while maintaining these connections as limited and sparse to effectively manage the computational budget. Our extensive empirical evaluations across a variety of cooperative multi-agent scenarios, including tasks such as cooperative navigation and traffic control, consistently demonstrate BUN's superiority over baseline methods with substantially reduced computational costs.
- 26 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Systems
- Vol. 40 (1) , 585-596
Grouping of $N-1$ Contingencies for Controller Synthesis: A Study for Power Line FailuresThe problem of maintaining power system stability and performance after the failure of any single line in a power system (an “ $N-1$ contingency”) is investigated. Due to the large number of possible $N-1$ contingencies for a power network, it is impractical to optimize controller parameters for each possible contingency a priori. A method to partition a set of contingencies into groups of contingencies that are similar to each other from a control perspective is presented. Design of a single controller for each group, rather than for each contingency, provides a computationally tractable method for maintaining stability and performance after element failures. The choice of number of groups tunes a trade-off between computation time and controller performance for a given set of contingencies. Results are simulated on the IEEE 39-bus and 68-bus systems, illustrating that, with controllers designed for a relatively small number of groups, power system stability may be significantly improved after an $N-1$ contingency compared to continued use of the nominal controller. Furthermore, performance is comparable to that of controllers designed for each contingency individually.
- 26 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Systems
- Vol. 40 (1) , 585-596
Grouping of $N-1$ Contingencies for Controller Synthesis: A Study for Power Line FailuresThe problem of maintaining power system stability and performance after the failure of any single line in a power system (an “ $N-1$ contingency”) is investigated. Due to the large number of possible $N-1$ contingencies for a power network, it is impractical to optimize controller parameters for each possible contingency a priori. A method to partition a set of contingencies into groups of contingencies that are similar to each other from a control perspective is presented. Design of a single controller for each group, rather than for each contingency, provides a computationally tractable method for maintaining stability and performance after element failures. The choice of number of groups tunes a trade-off between computation time and controller performance for a given set of contingencies. Results are simulated on the IEEE 39-bus and 68-bus systems, illustrating that, with controllers designed for a relatively small number of groups, power system stability may be significantly improved after an $N-1$ contingency compared to continued use of the nominal controller. Furthermore, performance is comparable to that of controllers designed for each contingency individually.
- Open Access
- 9 September 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Embedded Computing Systems
- Vol. 22 (5s) , 1-22
DTRL: Decision Tree-based Multi-Objective Reinforcement Learning for Runtime Task Scheduling in Domain-Specific System-on-Chips
Domain-specific systems-on-chip (DSSoCs) combine general-purpose processors and specialized hardware accelerators to improve performance and energy efficiency for a specific domain. The optimal allocation of tasks to processing elements (PEs) with minimal runtime overheads is crucial to achieving this potential. However, this problem remains challenging as prior approaches suffer from non-optimal scheduling decisions or significant runtime overheads. Moreover, existing techniques focus on a single optimization objective, such as maximizing performance. This work proposes DTRL, a decision-tree-based multi-objective reinforcement learning technique for runtime task scheduling in DSSoCs. DTRL trains a single global differentiable decision tree (DDT) policy that covers the entire objective space quantified by a preference vector. Our extensive experimental evaluations using our novel reinforcement learning environment demonstrate that DTRL captures the trade-off between execution time and power consumption, thereby generating a Pareto set of solutions using a single policy. Furthermore, comparison with state-of-the-art heuristic–, optimization–, and machine learning-based schedulers shows that DTRL achieves up to 9× higher performance and up to 3.08× reduction in energy consumption. The trained DDT policy achieves 120 ns inference latency on Xilinx Zynq ZCU102 FPGA at 1.2 GHz, resulting in negligible runtime overheads. Evaluation on the same hardware shows that DTRL achieves up to 16% higher performance than a state-of-the-art heuristic scheduler.
- 9 September 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Embedded Computing Systems
- Vol. 22 (5s) , 1-22
Open AccessDTRL: Decision Tree-based Multi-Objective Reinforcement Learning for Runtime Task Scheduling in Domain-Specific System-on-Chips
Domain-specific systems-on-chip (DSSoCs) combine general-purpose processors and specialized hardware accelerators to improve performance and energy efficiency for a specific domain. The optimal allocation of tasks to processing elements (PEs) with minimal runtime overheads is crucial to achieving this potential. However, this problem remains challenging as prior approaches suffer from non-optimal scheduling decisions or significant runtime overheads. Moreover, existing techniques focus on a single optimization objective, such as maximizing performance. This work proposes DTRL, a decision-tree-based multi-objective reinforcement learning technique for runtime task scheduling in DSSoCs. DTRL trains a single global differentiable decision tree (DDT) policy that covers the entire objective space quantified by a preference vector. Our extensive experimental evaluations using our novel reinforcement learning environment demonstrate that DTRL captures the trade-off between execution time and power consumption, thereby generating a Pareto set of solutions using a single policy. Furthermore, comparison with state-of-the-art heuristic–, optimization–, and machine learning-based schedulers shows that DTRL achieves up to 9× higher performance and up to 3.08× reduction in energy consumption. The trained DDT policy achieves 120 ns inference latency on Xilinx Zynq ZCU102 FPGA at 1.2 GHz, resulting in negligible runtime overheads. Evaluation on the same hardware shows that DTRL achieves up to 16% higher performance than a state-of-the-art heuristic scheduler.
- Open Access
PD-MORL: Preference-Driven Multi-Objective Reinforcement Learning Algorithm
Multi-objective reinforcement learning (MORL) approaches have emerged to tackle many real-world problems with multiple conflicting objectives by maximizing a joint objective function weighted by a preference vector. These approaches find fixed customized policies corresponding to preference vectors specified during training. However, the design constraints and objectives typically change dynamically in real-life scenarios. Furthermore, storing a policy for each potential preference is not scalable. Hence, obtaining a set of Pareto front solutions for the entire preference space in a given domain with a single training is critical. To this end, we propose a novel MORL algorithm that trains a single universal network to cover the entire preference space scalable to continuous robotic tasks. The proposed approach, Preference-Driven MORL (PD-MORL), utilizes the preferences as guidance to update the network parameters. It also employs a novel parallelization approach to increase sample efficiency. We show that PD-MORL achieves up to 25% larger hypervolume for challenging continuous control tasks and uses an order of magnitude fewer trainable parameters compared to prior approaches.
Open AccessPD-MORL: Preference-Driven Multi-Objective Reinforcement Learning Algorithm
Multi-objective reinforcement learning (MORL) approaches have emerged to tackle many real-world problems with multiple conflicting objectives by maximizing a joint objective function weighted by a preference vector. These approaches find fixed customized policies corresponding to preference vectors specified during training. However, the design constraints and objectives typically change dynamically in real-life scenarios. Furthermore, storing a policy for each potential preference is not scalable. Hence, obtaining a set of Pareto front solutions for the entire preference space in a given domain with a single training is critical. To this end, we propose a novel MORL algorithm that trains a single universal network to cover the entire preference space scalable to continuous robotic tasks. The proposed approach, Preference-Driven MORL (PD-MORL), utilizes the preferences as guidance to update the network parameters. It also employs a novel parallelization approach to increase sample efficiency. We show that PD-MORL achieves up to 25% larger hypervolume for challenging continuous control tasks and uses an order of magnitude fewer trainable parameters compared to prior approaches.
- Open Access
- 31 January 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Computing for Healthcare
- Vol. 4 (1) , 1-21
Transfer Learning for Human Activity Recognition Using Representational Analysis of Neural Networks
Human activity recognition (HAR) has increased in recent years due to its applications in mobile health monitoring, activity recognition, and patient rehabilitation. The typical approach is training a HAR classifier offline with known users and then using the same classifier for new users. However, the accuracy for new users can be low with this approach if their activity patterns are different than those in the training data. At the same time, training from scratch for new users is not feasible for mobile applications due to the high computational cost and training time. To address this issue, we propose a HAR transfer learning framework with two components. First, a representational analysis reveals common features that can transfer across users and user-specific features that need to be customized. Using this insight, we transfer the reusable portion of the offline classifier to new users and fine-tune only the rest. Our experiments with five datasets show up to 43% accuracy improvement and 66% training time reduction when compared to the baseline without using transfer learning. Furthermore, measurements on the hardware platform reveal that the power and energy consumption decreased by 43% and 68%, respectively, while achieving the same or higher accuracy as training from scratch. Our code is released for reproducibility. 1
- 31 January 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Computing for Healthcare
- Vol. 4 (1) , 1-21
Open AccessTransfer Learning for Human Activity Recognition Using Representational Analysis of Neural Networks
Human activity recognition (HAR) has increased in recent years due to its applications in mobile health monitoring, activity recognition, and patient rehabilitation. The typical approach is training a HAR classifier offline with known users and then using the same classifier for new users. However, the accuracy for new users can be low with this approach if their activity patterns are different than those in the training data. At the same time, training from scratch for new users is not feasible for mobile applications due to the high computational cost and training time. To address this issue, we propose a HAR transfer learning framework with two components. First, a representational analysis reveals common features that can transfer across users and user-specific features that need to be customized. Using this insight, we transfer the reusable portion of the offline classifier to new users and fine-tune only the rest. Our experiments with five datasets show up to 43% accuracy improvement and 66% training time reduction when compared to the baseline without using transfer learning. Furthermore, measurements on the hardware platform reveal that the power and energy consumption decreased by 43% and 68%, respectively, while achieving the same or higher accuracy as training from scratch. Our code is released for reproducibility. 1
- Open Access
Tuning an H-Infinity Controller with a Given Order and a Structure for Interconnected Systems with Delays
An eigenvalue based framework is developed for the H-infinity norm analysis and its norm minimization of coupled systems with time-delays, which are naturally described by delay differential algebraic equations (DDAEs). For these equations H-infinity norms are analyzed and their sensitivity with respect to small delay perturbations is studied. Subsequently, numerical methods for the H-infinity norm computation and for designing controllers minimizing the H-infinity norm with a prescribed structure or order, based on a direct optimization approach, are briefly addressed. The effectiveness of the approach is illustrated with a software demo. The chapter concludes by pointing out the similarities with the computation and optimization of characteristic roots of DDAEs.
Open AccessTuning an H-Infinity Controller with a Given Order and a Structure for Interconnected Systems with Delays
An eigenvalue based framework is developed for the H-infinity norm analysis and its norm minimization of coupled systems with time-delays, which are naturally described by delay differential algebraic equations (DDAEs). For these equations H-infinity norms are analyzed and their sensitivity with respect to small delay perturbations is studied. Subsequently, numerical methods for the H-infinity norm computation and for designing controllers minimizing the H-infinity norm with a prescribed structure or order, based on a direct optimization approach, are briefly addressed. The effectiveness of the approach is illustrated with a software demo. The chapter concludes by pointing out the similarities with the computation and optimization of characteristic roots of DDAEs.
- Open Access
Eigenvalue based algorithms and software for the design of fixed-order stabilizing controllers for interconnected systems with time-delays
An eigenvalue based framework is developed for the stability analysis and stabilization of coupled systems with time-delays, which are naturally described by delay differential algebraic equations. The spectral properties of these equations are analyzed and their stability properties are studied, taking into account the effect of small delay perturbations. Subsequently, numerical methods for stability assessment and for designing stabilizing controllers with a prescribed structure or order, based on a direct optimization approach, are briefly addressed. The effectiveness of the approach is illustrated with a software demo. The paper concludes by pointing out the similarities with the computation and optimization of H-infinity norms.
Open AccessEigenvalue based algorithms and software for the design of fixed-order stabilizing controllers for interconnected systems with time-delays
An eigenvalue based framework is developed for the stability analysis and stabilization of coupled systems with time-delays, which are naturally described by delay differential algebraic equations. The spectral properties of these equations are analyzed and their stability properties are studied, taking into account the effect of small delay perturbations. Subsequently, numerical methods for stability assessment and for designing stabilizing controllers with a prescribed structure or order, based on a direct optimization approach, are briefly addressed. The effectiveness of the approach is illustrated with a software demo. The paper concludes by pointing out the similarities with the computation and optimization of H-infinity norms.