Reimagining Demand-Side Management with Mean Field Learning

TL;DR

This paper introduces MD-MFC, a novel mean field control algorithm for demand-side management that effectively tracks consumption signals without regularization, using a Bregman divergence-based mirror descent scheme, demonstrated on realistic data.

Contribution

The paper presents MD-MFC, a new algorithm for demand-side management that offers theoretical guarantees and simplifies load control through a novel optimization approach.

Findings

MD-MFC effectively tracks demand signals without regularization.

The algorithm provides theoretical guarantees for convex, Lipschitz objectives.

Experiments demonstrate practical applicability on realistic data.

Abstract

Integrating renewable energy into the power grid while balancing supply and demand is a complex issue, given its intermittent nature. Demand side management (DSM) offers solutions to this challenge. We propose a new method for DSM, in particular the problem of controlling a large population of electrical devices to follow a desired consumption signal. We model it as a finite horizon Markovian mean field control problem. We develop a new algorithm, MD-MFC, which provides theoretical guarantees for convex and Lipschitz objective functions. What distinguishes MD-MFC from the existing load control literature is its effectiveness in directly solving the target tracking problem without resorting to regularization techniques on the main problem. A non-standard Bregman divergence on a mirror descent scheme allows dynamic programming to be used to obtain simple closed-form solutions. In addition, we show that general mean-field game algorithms can be applied to this problem, which expands the possibilities for addressing load control problems. We illustrate our claims with experiments on a realistic data set.