Estimating Demand Flexibility Using Siamese LSTM Neural Networks

TL;DR

This paper introduces a novel Siamese LSTM neural network approach to accurately estimate demand flexibility and time-varying elasticity in power systems, capturing complex response features often missed by traditional methods.

Contribution

It proposes a model-free, two-stage estimation framework using Siamese LSTM networks to improve demand flexibility estimation accuracy and capture abnormal response features.

Findings

Higher estimation accuracy than existing methods

Effective in capturing delayed and vanishing elasticities

Improves understanding of demand response dynamics

Abstract

There is an opportunity in modern power systems to explore the demand flexibility by incentivizing consumers with dynamic prices. In this paper, we quantify demand flexibility using an efficient tool called time-varying elasticity, whose value may change depending on the prices and decision dynamics. This tool is particularly useful for evaluating the demand response potential and system reliability. Recent empirical evidences have highlighted some abnormal features when studying demand flexibility, such as delayed responses and vanishing elasticities after price spikes. Existing methods fail to capture these complicated features because they heavily rely on some predefined (often over-simplified) regression expressions. Instead, this paper proposes a model-free methodology to automatically and accurately derive the optimal estimation pattern. We further develop a two-stage estimation process with Siamese long short-term memory (LSTM) networks. Here, a LSTM network encodes the price response, while the other network estimates the time-varying elasticities. In the case study, the proposed framework and models are validated to achieve higher overall estimation accuracy and better description for various abnormal features when compared with the state-of-the-art methods.