analiza aiqbench
This research proposes a deep reinforcement learning framework that explicitly quantifies uncertainty in distribution networks to distinguish between inherent operational risks and out-of-distribution anomalies like cyber-physical attacks. By decomposing total uncertainty into aleatoric and epistemic components, the method enables robust fallback controls during deployment while maintaining optimal operation under stochastic conditions. The approach advances safety-critical AI applications by integrating Bayesian methods with distributional reinforcement learning for enhanced system reliability.
Risk and Anomaly Identification for Distribution Network Optimal Operation Based on Reinforcement Learning and Uncertainty Quantification
arXiv:2609.03308v1 Announce Type: new Abstract: Reliable operation of modern distribution networks requires timely identification of operational risks and anomalous events under pervasive uncertainty. In practice, operators must identify risks that are inherent in stochastic yet in-distribution conditions, and anomalies that correspond to out-of-distribution behaviors such as unusual load patterns, extreme weather or cyber-physical attacks. This paper addresses this joint risk and anomaly identification problem for optimal distribution network operation and proposes a deep reinforcement learning framework that is explicitly uncertainty aware. We integrate distributional and Bayesian deep reinforcement learning to realize a second- order uncertainty quantification scheme that decomposes total uncertainty into aleatoric and epistemic components, which are respectively used to characterize inherent risk and out-of- distribution anomalies. The resulting epistemic estimates drive both exploration during training and out-of-distribution detec- tion with fallback control during deployment, whereas aleatoric estimates are used to characterize intrinsic operational risk. Simulation results demonstrate the performance of our DRL agent and the effectiveness of the uncertainty quantification.
Abstract:Reliable operation of modern distribution networks requires timely identification of operational risks and anomalous events under pervasive uncertainty. In practice, operators must identify risks that are inherent in stochastic yet in-distribution conditions, and anomalies that correspond to out-of-distribution behaviors such as unusual load patterns, extreme weather or cyber-physical attacks. This paper addresses this joint risk and anomaly identification problem for optimal distribution network operation and proposes a deep reinforcement learning framework that is explicitly uncertainty aware. We integrate distributional and Bayesian deep reinforcement learning to realize a second- order uncertainty quantification scheme that decomposes total uncertainty into aleatoric and epistemic components, which are respectively used to characterize inherent risk and out-of- distribution anomalies. The resulting epistemic estimates drive both exploration during training and out-of-distribution detec- tion with fallback control during deployment, whereas aleatoric estimates are used to characterize intrinsic operational risk. Simulation results demonstrate the performance of our DRL agent and the effectiveness of the uncertainty quantification.
Machine Learning (cs.LG); Multiagent Systems (cs.MA); Systems and Control (eess.SY)
arXiv:2609.03308 [cs.LG]
(or arXiv:2609.03308v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.03308 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 258 cuvinte
Subiecte conexe
Vertical Advantage: Transforming Industries with Lakebase and Agentic AI
Databricks · 27 aug. 2026
Article: Governing AI in the Cloud: A Practical Guide for Architects
InfoQ · 15 iun. 2026
Key Organizations Developing Strategies in Quantum Finance, Risk Modeling, Portfolio Optimization, Cryptography, Q-Day
Inside Quantum Technology · 30 iul. 2026
A Red Line and Oversight Framework for Government AI Contracts
AI Alignment Forum · 18 iul. 2026