Learning to run a Power Network Challenge: a Retrospective Analysis

Abstract

Power networks, responsible for transporting electricity across large geographical regions, are complex infrastructures on which modern life critically depend. Variations in demand and production profiles, with increasing renewable energy integration, as well as the high voltage network technology, constitute a real challenge for human operators when optimizing electricity transportation while avoiding blackouts. Motivated to investigate the potential of Artificial Intelligence methods in enabling adaptability in power network operation, we have designed a L2RPN challenge to encourage the development of reinforcement learning solutions to key problems present in the next-generation power networks. The NeurIPS 2020 competition was well received by the international community attracting over 300 participants worldwide.The main contribution of this challenge is our proposed comprehensive 'Grid2Op' framework, and associated benchmark, which plays realistic sequential network operations scenarios. The Grid2Op framework, which is open-source and easily re-usable, allows users to define new environments with its companion GridAlive ecosystem. Grid2Op relies on existing non-linear physical power network simulators and let users create a series of perturbations and challenges that are representative of two important problems: a) the uncertainty resulting from the increased use of unpredictable renewable energy sources, and b) the robustness required with contingent line disconnections.In this paper, we give the highlights of the NeurIPS 2020 competition. We present the benchmark suite and analyse the winning solutions, including one super-human performance demonstration. We propose our organizational insights for a successful competition and conclude on open research avenues. Given the challenge success, we expect our work will foster research to create more sustainable solutions for power network operations.

Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challenges

“…In [156], a framework called Gym-ANM is developed to establish RL environments for active network management tasks in distribution systems. Besides, the Gird2Op framework 10 is an open-source environment for training RL agents to operate power networks, which is the testbed for the Learning to Run a Power Network (L2RPN) challenge [157]. Other recently developed RL environments include RLGC [145] for power system control, gymgrid [158] and OMG [159] for microgrid simulation and control, and PowerGym [160] for voltage control in distribution systems, etc.…”

Massively Digitized Power Grid: Opportunities and Challenges of Use-Inspired AI

“…Third, the value of creating comprehensive and trustworthy benchmark power datasets has been overlooked by the power system community. There have been few opensource datasets [220], [221] and online contests dedicated to topics such as forced oscillation localization [222] and power system operation [223], [224]. However, far more will be needed to build a standard library of opensource benchmark datasets along with critical tasks in a clear mathematical formulation that can be used to train, calibrate, test, and benchmark data-driven models.…”

A Graph Policy Network Approach for Volt-Var Control in Power Distribution Systems

“…With recent breakthroughs in RL, power systems researchers have attempted to use RL for power systems operations. One of such examples is learning to operate a transmission systems operation in L2RPN competition [Marot et al, 2021]. Though transmission systems are fundamentally different from distribution systems in both network topology (looped vs. radial) and typical problem types (dynamic systems vs. quasi-static systems), RL has shown promising results [Yoon et al, 2020] in transmission systems.…”