A Time-Varying Incentive Optimization for Interactive Demand Response Based on Two-Step Clustering

With the increasing marketization of electricity, residential users are gradually participating in various businesses power utility companies, and there more interactive adjustments between load, source, grid. However, participation large-scale has also brought challenges to grid companies carrying out demand-side dispatching work. The user load response is uneven, users’ behavioral characteristics highly differentiated. It necessary consider differences electricity consumption demand design peak–valley time-sharing incentives, adopt a flexible incentive form. In this context, paper first establishes comprehensive clustering method integrating k-means self-organizing networks (SONs) for two-step BP neural network reverse adjustment correction. Then, time-varying optimization based on introduced. Furthermore, different results customers, incentives formulated. proposed validated through case studies, where indicate that our can effectively improve reduce costs compared existing methods.