GridLearn: Multiagent reinforcement learning for grid-aware building energy management

Increasing amounts of distributed generation in distribution networks can provide both challenges and opportunities for voltage regulation across the network. Intelligent control smart inverters other building energy management systems be leveraged to alleviate these issues. GridLearn is a multiagent reinforcement learning platform that incorporates models power flow achieve grid level goals, by controlling behind-the-meter resources. This study demonstrates how multi-agent preserve owner privacy comfort while pursuing grid-level objectives. Building upon CityLearn framework which considers RL building-level this work expands network setting where goals are additionally considered. As case study, we consider on IEEE-33 bus using controllable loads, storage, inverters. The results show agents nominally reduce instances undervoltages overvoltages 34%.