In the distributed optimization of micro-grid, we consider grid connected solar micro-grid system which contains a local consumer, a solar photovoltaic system and a battery. The consumer as an agent continuously interacts with the environment and learns to take optimal actions. Each agent uses a model-free reinforcement learning algorithm, namely Q Learning, to optimize the battery scheduling in dynamic environment of load and available solar power. Multiple agents sense the states of the environment components and make collective decisions about how to respond to randomness in load, intermittent solar power using a Multi-Agent Reinforcement Learning algorithm, called Coordinated Q Learning (CQL). The goals of each agent are to increase the utility of the battery and solar power in order to achieve the long term objective of reducing the power consumption from grid.

No abstract

Considering our depleting resources, efficient energy production and transmission is the need of the hour. This paper focuses on the concept of using Reinforcement Learning (RL) to control the power systems unit commitment and economic dispatch problem. The idea of reinforcement learning strives to present an ever optimal system even when there are load fluctuations. This is done by training the agent (system), thereby enriching its knowledge base which ensures that even without manual intervention all the available resources are used judiciously. Also the agent learns to reach long term objective of minimizing cost by autonomous optimization. A model free reinforcement learning method called, Q learning is used to find the cost at various loadings and is compared with the conventional priority list method and the performance improvement due to Q learning is proved.

No abstract

No abstract