Enforcing Policy Feasibility Constraints through Differentiable Projection for Energy Optimization

원문 초록

While reinforcement learning (RL) is gaining popularity in energy systems control, its real-world applications are limited due to the fact that the actions from learned policies may not satisfy functional requirements or be feasible for the underlying physical system. In this work, we propose PROjected Feasibility (PROF), a method to enforce convex operational constraints within neural policies. Specifically, we incorporate a differentiable projection layer within a neural network-based policy to enforce that all learned actions are feasible. We then update the policy end-to-end by propagating gradients through this differentiable projection layer, making the policy cognizant of the operational constraints. We demonstrate our method on two applications: energy-efficient building operation and inverter control. In the building operation setting, we show that PROF maintains thermal comfort requirements while improving energy efficiency by 4% over state-of-the-art methods. In the inverter control setting, PROF perfectly satisfies voltage constraints on the IEEE 37-bus feeder system, as it learns to curtail as little renewable energy as possible within its safety set.