Learning Prosumer Behavior in Energy Communities: Integrating Bilevel Programming and Online Learning

TL;DR

This paper introduces a combined bilevel programming and online learning framework using Thompson sampling to dynamically set energy prices and learn prosumer behaviors in energy communities, reducing reliance on pre-existing data.

Contribution

It presents a novel integration of bilevel programming with online learning for real-time prosumer behavior inference in energy markets.

Findings

Rapid learning of prosumer characteristics within five days

Achieved full convergence in 100 days

Low regret in dynamic pricing and behavior inference

Abstract

Dynamic pricing through bilevel programming is widely used for demand response but often assumes perfect knowledge of prosumer behavior, which is unrealistic in practical applications. This paper presents a novel framework that integrates bilevel programming with online learning, specifically Thompson sampling, to overcome this limitation. The approach dynamically sets optimal prices while simultaneously learning prosumer behaviors through observed responses, eliminating the need for extensive pre-existing datasets. Applied to an energy community providing capacity limitation services to a distribution system operator, the framework allows the community manager to infer individual prosumer characteristics, including usage patterns for photovoltaic systems, electric vehicles, home batteries, and heat pumps. Numerical simulations with 25 prosumers, each represented by 10 potential signatures, demonstrate rapid learning with low regret, with most prosumer characteristics learned within five days and full convergence achieved in 100 days.