An Online Stochastic Learning Strategy for Demand Response in Smart Microgrid

Demand response (DR) plays an essential role in smart grids to reconfigure the load profile to match the energy supply for reliable and economic operation. This article presents an online adaptive DR strategy based on stochastic learning and optimization for smart microgrids with renewable energy to maximize the operation profit. To enable prompt interaction with the stochastic dynamics of usage demands, renewable generations and real-time pricing, a novel event-driven continuous-time Markov control processes model is introduced to formulate the DR optimization. Based on performance sensitivity analysis, a stochastic learning algorithm that combines potentials estimate and policy iteration is developed to find the optimal DR policy online. The presented strategy is environment-adaptive and computation-efficient, which is competent for real-time control and optimization in unknown environments. Simulations have been conducted to evaluate the performance of the presented strategy, and the results demonstrate the effectiveness.