MARLA-SG: Multi-Agent Reinforcement Learning Algorithm for Efficient Demand Response in Smart Grid

The population is sharply growing in the last decade, resulting in non-potential power requests in dense urban areas, especially with the traditional power grid where the system is not compatible with the infrequent changes. Smart grids have shown strong potential to effectively mitigate and smooth power consumption curves to avoid shortages by adjusting and forecasting the cost function in real-time in response to consumption fluctuations to achieve the desired objectives. The main challenge for the smart grid designers is to reduce the cost and Peak to Average Ratio (PAR) while maintaining the desired satisfaction level. This article presents the development and evaluation of a Multi-Agent Reinforcement Learning Algorithm for efficient demand response in Smart Grid (MARLA-SG). Also, it shows a simple and flexible way of choosing state elements to reduce the possible number of states, regardless of the device type, range of operation, and maximum allowable delay. It also produces a simple way to represent the reward function regardless of the used cost function. SARSA (State-Action-Reward-State-Action) and Q-learning schemes are used and attained PAR reduction of 9.6%, 12.16%, and an average cost reduction of 10.2%, 7.8%, respectively.