Constrained Thompson Sampling for Real-Time Electricity Pricing with Grid Reliability Constraints

TL;DR

This paper introduces Con-TS-RTP, a constrained Thompson sampling algorithm for real-time electricity pricing that learns customer load responses while ensuring grid reliability, balancing demand management and operational constraints.

Contribution

It presents a novel constrained Thompson sampling heuristic tailored for real-time electricity load shaping with reliability constraints, addressing operational safety during learning.

Findings

Regret bounds are established for the proposed algorithm.

The method maintains distribution system reliability during learning.

It effectively balances load shaping objectives with grid safety.

Abstract

We consider the problem of an aggregator attempting to learn customers' load flexibility models while implementing a load shaping program by means of broadcasting daily dispatch signals. We adopt a multi-armed bandit formulation to account for the stochastic and unknown nature of customers' responses to dispatch signals. We propose a constrained Thompson sampling heuristic, Con-TS-RTP, that accounts for various possible aggregator objectives (e.g., to reduce demand at peak hours, integrate more intermittent renewable generation, track a desired daily load profile, etc) and takes into account the operational constraints of a distribution system to avoid potential grid failures as a result of uncertainty in the customers' response. We provide a discussion on the regret bounds for our algorithm as well as a discussion on the operational reliability of the distribution system's constraints being upheld throughout the learning process.