CommonPower: A Framework for Safe Data-Driven Smart Grid Control
Not on the map. Why?
Abstract (arXiv)
The growing complexity of power system management has led to an increased interest in reinforcement learning (RL). To validate their effectiveness, RL algorithms have to be evaluated across multiple case studies. Case study design is an arduous task requiring the consideration of many aspects, among them the influence of available forecasts and the level of decentralization in the control structure. Furthermore, vanilla RL controllers cannot themselves ensure the satisfaction of system constraints, which makes devising a safeguarding mechanism a necessary task for every case study before deploying the system. To address these shortcomings, we introduce the Python tool CommonPower, the first general framework for the modeling and simulation of power system management tailored towards machine learning. Its modular architecture enables users to focus on specific elements without having to implement a simulation environment. Another unique contribution of CommonPower is the automatic synthesis of model predictive controllers and safeguards. Beyond offering a unified interface for single-agent RL, multi-agent RL, and optimal control, CommonPower includes a training pipeline for machine-learning-based forecasters as well as a flexible mechanism for incorporating feedback of safeguards into the learning updates of RL controllers.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 41 of its 95 references that are in the map. First posted on arXiv 5 Jun 2024.
Builds on
41 of 95 references.
References · 41
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2017Proximal Policy Optimization Algorithmscited by 14,441
- 2021The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Gamescited by 903
- 2018Tune: A Research Platform for Distributed Model Selection and Trainingcited by 395
- 2021Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learningcited by 337
- 2020Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?cited by 281
- 2021DC3: A learning method for optimization with hard constraintscited by 181
- 2022A Review of Safe Reinforcement Learning: Methods, Theory and Applicationscited by 169
- 2018A predictive safety filter for learning-based control of constrained nonlinear dynamical systemscited by 91
- 2017pandapower - an Open Source Python Tool for Convenient Modeling, Analysis and Optimization of Electric Power Systemscited by 79
- 2021Learning to run a Power Network Challenge: a Retrospective Analysiscited by 52
- 2018Review of Smart Meter Data Analytics: Applications, Methodologies, and Challengescited by 47
29 more
- 2020Enforcing robust control guarantees within neural network policiescited by 40
- 2021Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challengescited by 40
- 2021Enforcing Policy Feasibility Constraints through Differentiable Projection for Energy Optimizationcited by 31
- 2022Provably Safe Reinforcement Learning: Conceptual Analysis, Survey, and Benchmarkingcited by 31
- 2020Safe Reinforcement Learning via Projection on a Safe Set: How to Achieve Optimality?cited by 29
- 2020CityLearn: Standardizing Research in Multi-Agent Reinforcement Learning for Demand Response and Urban Energy Managementcited by 27
- 2019Adaptive Power System Emergency Control using Deep Reinforcement Learningcited by 26
- 2020Multi-Agent Deep Reinforcement Learning for HVAC Control in Commercial Buildingscited by 24
- 2020Reinforcement Learning for Electricity Network Operationcited by 20
- 2022Online Shielding for Reinforcement Learningcited by 19
- 2021Gym-ANM: Reinforcement Learning Environments for Active Network Management Tasks in Electricity Distribution Systemscited by 18
- 2014Convex Relaxation of Optimal Power Flow, Part I: Formulations and Equivalencecited by 17
- 2021Computationally Efficient Safe Reinforcement Learning for Power Systemscited by 17
- 2021PowerGridworld: A Framework for Multi-Agent Reinforcement Learning in Power Systemscited by 15
- 2024CityLearn v2: Energy-flexible, resilient, occupant-centric, and carbon-aware management of grid-interactive communitiescited by 14
- 2020PowerNet: Multi-agent Deep Reinforcement Learning for Scalable Powergrid Controlcited by 13
- 2020Deep Reinforcement Learning Based Volt-VAR Optimization in Smart Distribution Systemscited by 12
- 2021GridLearn: Multiagent Reinforcement Learning for Grid-Aware Building Energy Managementcited by 12
- 2020pymgrid: An Open-Source Python Microgrid Simulator for Applied Artificial Intelligence Researchcited by 10
- 2021PowerGym: A Reinforcement Learning Environment for Volt-Var Control in Power Distribution Systemscited by 10
- 2022Correct-by-Construction Runtime Enforcement in AI -- A Surveycited by 10
- 2021Gym-ANM: Open-source software to leverage reinforcement learning for power system management in research and educationcited by 6
- 2021Guarantees for Real Robotic Systems: Unifying Formal Controller Synthesis and Reachset-Conformant Identificationcited by 5
- 2022Contingency-constrained economic dispatch with safe reinforcement learningcited by 5
- 2020Safe Reinforcement Learning for Emergency LoadShedding of Power Systemscited by 4
- 2018Convex Restriction of Power Flow Feasibility Setscited by 3
- 2021SAVER: Safe Learning-Based Controller for Real-Time Voltage Regulationcited by 3
- 2022Andes_gym: A Versatile Environment for Deep Reinforcement Learning in Power Systemscited by 3
- 2020Deep Multi-Agent Reinforcement Learning for Cost Efficient Distributed Load Frequency Controlcited by 2
Built on by
Citing papers per year: 2024: 1; 2025: 0; 2026: 2.
3 papers.