Reinforcement learning-driven optimization of incentive-based demand response in distribution network with optimal placement of DG

Demand response (DR) is a key strategy for strengthening the economic efficiency, planning and operational stability of microgrids. This paper proposes an incentive-based DR program implemented through agent-based reinforcement learning, designed to optimize the profit of both the distribution system operator and load operator, while maintaining customer comfort. Concurrently, an analytical technique ascertains the optimal size of distribution generators (DG) and their respective location by minimizing a multi-index objective comprising active loss voltage deviation, reactive power losses and MVA burden. To address the uncertainty inherent in renewable-based DGs, the beta probability distribution function (PDF) is applied for solar power and the Weibull probability function is applied for wind power uncertainty. The performance of the proposed methodology is tested on a modified IEEE 33-bus distribution system, which consists of DGs and load operators. Results demonstrate that integrating DR with optimally placed DGs leads to a 8.96% reduction in power demand, 11.74% reduction in power loss, and 8.86% reduction in total cost. Additionally, the total profit for the distribution system operator increases to $ 379.1310/day. The daily incentives earned for load reduction varied across agents. L1 received $4.8990 for cutting 181.9520 kW, while L2 earned $7.3743 for a 274.0533 kW reduction. L3 was awarded $15.6795 after decreasing usage by 492.3093 kW, and L4 gained $26.1324 for 820.5156 kW. The highest incentive, $71.8010, was awarded to L5 for curtailing 2025.6234 kW, and L6 received $39.9005 for a 1012.8211 kW reduction, based on their priority level. An analysis of the strategy’s efficacy in optimizing microgrid operational performance and financial sustainability.