arXiv subjects

Stavros Orfanoudakis

Publications and source records attributed to Stavros Orfanoudakis.

13 recordsLinked to original sources

arXiv2026

Flow Matching Policy Optimization with Mirror Descent and Entropy Constraints

Balancing policy expressiveness with the exploration-exploitation trade-off is a core challenge in online Reinforcement Learning (RL). While Stochastic Differential Equation (SDE)-based diffusion policies can represent complex, multimodal action distributions, they suffer from two critical limitations: their stochastic reverse processes render entropy intractable (necessitating heuristic exploration), and computing policy gradients through long denoising chains is expensive and unstable. In this work, we show that ODE-based flow matching inherently resolves these issues by enabling both simulation-free policy optimization and tractable entropy computation. Building on this, we introduce Flow Matching Policy Optimization with Mirror Descent and Entropy Constraints (FMER). Our framework exploits this insight in three ways. First, we theoretically establish that minimizing an advantage-weighted conditional flow matching loss acts as a simulation-free surrogate for policy mirror descent. This steers the velocity field toward high-value regions while entirely avoiding backpropagation through the ODE solver. Second, we derive an analytic entropy objective that corrects for the density distortion caused by the $\tanh$ transformation (mapping an unbounded latent space to bounded actions), thereby facilitating principled maximum-entropy optimization. Finally, we dynamically tune the mirror descent temperature based on the effective sample size to enforce a robust trust region during training. Empirical evaluations demonstrate that FMER achieves superior performance on the challenging sparse-reward FrankaKitchen environment, while maintaining competitive results across standard dense-reward MuJoCo benchmarks.

cs.LG↗

arXiv2026

Community-to-Vehicle: Integrating Electric Vehicles into Energy Communities -- A Swiss Case Study

The institutional separation between local energy communities and public electric vehicle (EV) charging limits the efficient use of locally generated renewable energy. This paper introduces the concept of community-to-vehicle (C2V) as an institutional design mechanism to bridge this gap by enabling EV charging within the community boundary, where locally generated photovoltaic (PV) surplus is preferentially allocated and offered to external users at a community charging price. Building on the recently introduced local electricity community framework in Switzerland, we design scenarios that capture the transition from full separation to coordinated EV charging and evaluate their impacts on EV users and the community. The results show that C2V significantly improves local PV utilization and enhances economic performance, reducing EV charging costs relative to commercial alternatives while generating additional revenue streams for the community. These findings highlight the potential of C2V as a practical, implementable mechanism for integrating EV charging into local energy communities, providing a clear pathway for adopting coordinated community-EV interaction within existing regulatory frameworks.

eess.SY↗

arXiv2026

SAVGO: Learning State-Action Value Geometry with Cosine Similarity for Continuous Control

While representation and similarity learning have improved the sample efficiency of Reinforcement Learning (RL), they are rarely used to shape policy updates directly in the action space. To bridge this gap, a geometry-aware RL algorithm that explicitly incorporates value-based similarity into the policy update, State-Action Value Geometry Optimization (SAVGO), is proposed. In detail, SAVGO learns a joint state-action embedding space in which pairs with similar action-value estimates exhibit high cosine similarity, while dissimilar pairs are mapped to distinct directions. This learned geometry enables the generation of a similarity kernel over candidate actions sampled at each update, allowing policy improvement to be guided directly toward higher-value regions beyond local gradient-based updates. As a result, representation learning, value estimation, and policy optimization are unified within a single geometry-consistent objective, while preserving the scalability of off-policy actor-critic training. The proposed method is evaluated on standard MuJoCo continuous-control benchmarks, demonstrating improvements over strong baselines on challenging high-dimensional tasks. Ablation studies are done to analyze the contributions of value-geometry learning and similarity-based policy updates.

cs.LG↗

arXiv2026

Learning to Route Electric Trucks Under Operational Uncertainty

Electric truck operations require routing decisions that remain feasible under limited battery range, long charging times, travel and energy consumption, and competition for shared charging infrastructure. These features make electric truck routing a coupled logistics and energy problem, limiting the practicality of heuristics-based methods and rendering them computationally infeasible at scale. This paper proposes a learning-based framework for the stochastic electric truck routing under charging constraints and operational uncertainty. The problem, solved by Reinforcement Learning, is formulated as an event-driven semi-Markov decision process with shared charging resources, stochastic travel and energy requirements, and realistic nonlinear fast-charging behavior. To support learning in this setting, a graph-based representation of system state and feasible decisions is introduced, together with a rule-based action mask that restricts policies to operationally admissible actions; thus, improving training efficiency. Building on this formulation, an event-driven simulation environment is developed that supports both Reinforcement Learning and benchmarking against heuristic and mathematical programming baselines. Computational experiments across a range of fleet sizes show that the proposed learning-based algorithm consistently outperforms baselines and attains performance close to optimization benchmarks in many settings, while preserving high success rates under charging congestion and uncertainty.

eess.SY↗

arXiv2026

Topology-Aware Graph Reinforcement Learning for Energy Storage Systems Optimal Dispatch in Distribution Networks

Optimal dispatch of energy storage systems (ESSs) in distribution networks involves jointly improving operating economy and voltage security under time-varying conditions and possible topology changes. To support fast online decision making, we develop a topology-aware Reinforcement Learning architecture based on Twin Delayed Deep Deterministic Policy Gradient (TD3), which integrates graph neural networks (GNNs) as graph feature encoders for ESS dispatch. We conduct a systematic investigation of three GNN variants: graph convolutional networks (GCNs), topology adaptive graph convolutional networks (TAGConv), and graph attention networks (GATs) on the 34-bus and 69-bus systems, and evaluate robustness under multiple topology reconfiguration cases as well as cross-system transfer between networks with different system sizes. Results show that GNN-based controllers consistently reduce the number and magnitude of voltage violations, with clearer benefits on the 69-bus system and under reconfiguration; on the 69-bus system, TD3-GCN and TD3-TAGConv also achieve lower saved cost relative to the NLP benchmark than the NN baseline. We also highlight that transfer gains are case-dependent, and zero-shot transfer between fundamentally different systems results in notable performance degradation and increased voltage magnitude violations. This work is available at: https://github.com/ShuyiGao/GNNs_RL_ESSs and https://github.com/distributionnetworksTUDelft/GNNs_RL_ESSs.

cs.LG↗

arXiv2025

Physics-Informed Reinforcement Learning for Large-Scale EV Smart Charging Considering Distribution Network Voltage Constraints

Electric Vehicles (EVs) offer substantial flexibility for grid services, yet large-scale, uncoordinated charging can threaten voltage stability in distribution networks. Existing Reinforcement Learning (RL) approaches for smart charging often disregard physical grid constraints or have limited performance for complex large-scale tasks, limiting their scalability and real-world applicability. This paper introduces a physics-informed (PI) RL algorithm that integrates a differentiable power flow model and voltage-based reward design into the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm, enabling EVs to deliver real-time voltage support while meeting user demands. The resulting PI-TD3 algorithm achieves faster convergence, improved sample efficiency, and reliable voltage magnitude regulation under uncertain and overloaded conditions. Benchmarks on the IEEE 34-bus and 123-bus networks show that the proposed PI-TD3 outperforms both model-free RL and optimization-based baselines in grid constraint management, user satisfaction, and economic metrics, even as the system scales to hundreds of EVs. These advances enable robust, scalable, and practical EV charging strategies that enhance grid resilience and support distribution networks operation.

eess.SY↗

arXiv2025

GNN-DT: Graph Neural Network Enhanced Decision Transformer for Efficient Optimization in Dynamic Environments

Reinforcement Learning (RL) methods used for solving real-world optimization problems often involve dynamic state-action spaces, larger scale, and sparse rewards, leading to significant challenges in convergence, scalability, and efficient exploration of the solution space. This study introduces GNN-DT, a novel Decision Transformer (DT) architecture that integrates Graph Neural Network (GNN) embedders with a novel residual connection between input and output tokens crucial for handling dynamic environments. By learning from previously collected trajectories, GNN-DT tackles the sparse rewards limitations of online RL algorithms and delivers high-quality solutions in real-time. We evaluate GNN-DT on the complex electric vehicle (EV) charging optimization problem and prove that its performance is superior and requires significantly fewer training trajectories, thus improving sample efficiency compared to existing DT and offline RL baselines. Furthermore, GNN-DT exhibits robust generalization to unseen environments and larger action spaces, addressing a critical gap in prior offline and online RL approaches.

cs.LG↗

arXiv2025

Adaptive Informed Deep Neural Networks for Power Flow Analysis

This study introduces PINN4PF, an end-to-end deep learning architecture for power flow (PF) analysis that effectively captures the nonlinear dynamics of large-scale modern power systems. The proposed neural network (NN) architecture consists of two important advancements in the training pipeline: (A) a double-head feed-forward NN that aligns with PF analysis, including an activation function that adjusts to the net active and reactive power injections patterns, and (B) a physics-based loss function that partially incorporates power system topology information through a novel hidden function. The effectiveness of the proposed architecture is illustrated through 4-bus, 15-bus, 290-bus, and 2224-bus test systems and is evaluated against two baselines: a linear regression model (LR) and a black-box NN (MLP). The comparison is based on (i) generalization ability, (ii) robustness, (iii) impact of training dataset size on generalization ability, (iv) accuracy in approximating derived PF quantities (specifically line current, line active power, and line reactive power), and (v) scalability. Results demonstrate that PINN4PF outperforms both baselines across all test systems by up to two orders of magnitude not only in terms of direct criteria, e.g., generalization ability, but also in terms of approximating derived physical quantities.

eess.SY↗

arXiv2025

Optimizing Electric Vehicles Charging using Large Language Models and Graph Neural Networks

Maintaining grid stability amid widespread electric vehicle (EV) adoption is vital for sustainable transportation. Traditional optimization methods and Reinforcement Learning (RL) approaches often struggle with the high dimensionality and dynamic nature of real-time EV charging, leading to sub-optimal solutions. To address these challenges, this study demonstrates that combining Large Language Models (LLMs), for sequence modeling, with Graph Neural Networks (GNNs), for relational information extraction, not only outperforms conventional EV smart charging methods, but also paves the way for entirely new research directions and innovative solutions.

eess.SY↗

arXiv2024

A Simulation Tool for V2G Enabled Demand Response Based on Model Predictive Control

Integrating electric vehicles (EVs) into the power grid can revolutionize energy management strategies, offering both challenges and opportunities for creating a more sustainable and resilient grid. In this context, model predictive control (MPC) emerges as a powerful tool for addressing the complexities of Grid-to-vehicle (G2V) and vehicle-to-grid (V2G) enabled demand response management. By leveraging advanced optimization techniques, MPC algorithms can anticipate future grid conditions and dynamically adjust EV charging and discharging schedules to balance supply and demand while minimizing operational costs and maximizing flexibility. However, no standard tools exist to evaluate novel energy management strategies based on MPC approaches. Our research focuses on harnessing the potential of MPC in G2V and V2G applications, by providing a simulation tool that allows to maximize EV flexibility and support demand response initiatives while mitigating the impact on EV battery health. In this paper, we propose an open-source MPC controller for G2V and V2G-enabled demand response management. The proposed approach is capable of tackling the uncertainties inherent in demand response operations. Through extensive simulation and analysis, we demonstrate the efficacy of our approach in maximizing the benefits of G2V and V2G while assessing the impact on the longevity and reliability of EV batteries. Specifically, our controller enables Charge Point Operators (CPOs) to optimize EV charging and discharging schedules in real-time, taking into account fluctuating energy prices, grid constraints, and EV user preferences.

eess.SY↗

arXiv2024

EV2Gym: A Flexible V2G Simulator for EV Smart Charging Research and Benchmarking

As electric vehicle (EV) numbers rise, concerns about the capacity of current charging and power grid infrastructure grow, necessitating the development of smart charging solutions. While many smart charging simulators have been developed in recent years, only a few support the development of Reinforcement Learning (RL) algorithms in the form of a Gym environment, and those that do usually lack depth in modeling Vehicle-to-Grid (V2G) scenarios. To address the aforementioned issues, this paper introduces the EV2Gym, a realistic simulator platform for the development and assessment of small and large-scale smart charging algorithms within a standardized platform. The proposed simulator is populated with comprehensive EV, charging station, power transformer, and EV behavior models validated using real data. EV2Gym has a highly customizable interface empowering users to choose from pre-designed case studies or craft their own customized scenarios to suit their specific requirements. Moreover, it incorporates a diverse array of RL, mathematical programming, and heuristic algorithms to speed up the development and benchmarking of new solutions. By offering a unified and standardized platform, EV2Gym aims to provide researchers and practitioners with a robust environment for advancing and assessing smart charging algorithms.

cs.SE↗

arXiv2024

PowerFlowNet: Power Flow Approximation Using Message Passing Graph Neural Networks

Accurate and efficient power flow (PF) analysis is crucial in modern electrical networks' operation and planning. Therefore, there is a need for scalable algorithms that can provide accurate and fast solutions for both small and large scale power networks. As the power network can be interpreted as a graph, Graph Neural Networks (GNNs) have emerged as a promising approach for improving the accuracy and speed of PF approximations by exploiting information sharing via the underlying graph structure. In this study, we introduce PowerFlowNet, a novel GNN architecture for PF approximation that showcases similar performance with the traditional Newton-Raphson method but achieves it 4 times faster in the simple IEEE 14-bus system and 145 times faster in the realistic case of the French high voltage network (6470rte). Meanwhile, it significantly outperforms other traditional approximation methods, such as the DC relaxation method, in terms of performance and execution time; therefore, making PowerFlowNet a highly promising solution for real-world PF analysis. Furthermore, we verify the efficacy of our approach by conducting an in-depth experimental evaluation, thoroughly examining the performance, scalability, interpretability, and architectural dependability of PowerFlowNet. The evaluation provides insights into the behavior and potential applications of GNNs in power system analysis.

cs.LG↗

arXiv2023

A Novel Multiagent Flexibility Aggregation Framework

The increasing number of Distributed Energy Resources (DERs) in the emerging Smart Grid, has created an imminent need for intelligent multiagent frameworks able to utilize these assets efficiently. In this paper, we propose a novel DER aggregation framework, encompassing a multiagent architecture and various types of mechanisms for the effective management and efficient integration of DERs in the Grid. One critical component of our architecture is the Local Flexibility Estimators (LFEs) agents, which are key for offloading the Aggregator from serious or resource-intensive responsibilities -- such as addressing privacy concerns and predicting the accuracy of DER statements regarding their offered demand response services. The proposed framework allows the formation of efficient LFE cooperatives. To this end, we developed and deployed a variety of cooperative member selection mechanisms, including (a) scoring rules, and (b) (deep) reinforcement learning. We use data from the well-known PowerTAC simulator to systematically evaluate our framework. Our experiments verify its effectiveness for incorporating heterogeneous DERs into the Grid in an efficient manner. In particular, when using the well-known probabilistic prediction accuracy-incentivizing CRPS scoring rule as a selection mechanism, our framework results in increased average payments for participants, when compared with traditional commercial aggregators.

cs.AI↗