A Scenario-adaptive Online Learning Algorithm for Demand Response

This paper introduces a scenario-adaptive online learning algorithm for aggregating demand side resources. The problem of dispatching demands is formulated under a contextual combinatorial multi-armed bandit framework with the objective to minimize the mismatch between actual aggregated demand adjustment and the reduction target from system operator. Comparing with previous online learning framework for demand aggregation, this paper considers temporal and spatial factors and creates a scenario-adaptive mechanism to model the behavior of demands. The simulation results show the proposed method achieves less mismatch and more reliable aggregation performance than conventional methods.