A Flow-Based Model for Conditional and Probabilistic Electricity Consumption Profile Generation and Prediction

TL;DR

This paper presents FCPFlow, a flow-based generative model for probabilistic and conditional residential load profile generation and prediction, improving scalability and modeling of complex correlations in electricity consumption data.

Contribution

Introduction of FCPFlow, a novel flow-based model with invertible layers for enhanced RLP generation and forecasting under various conditions.

Findings

FCPFlow outperforms traditional statistical models in scalability.

FCPFlow better captures complex correlations in RLPs.

FCPFlow is effective for conditional and probabilistic load forecasting.

Abstract

Residential Load Profile (RLP) generation and prediction are critical for the operation and planning of distribution networks, especially as diverse low-carbon technologies (e.g., photovoltaic and electric vehicles) are increasingly adopted. This paper introduces a novel flow-based generative model, termed Full Convolutional Profile Flow (FCPFlow), which is uniquely designed for both conditional and unconditional RLP generation, and for probabilistic load forecasting. By introducing two new layers--the invertible linear layer and the invertible normalization layer--the proposed FCPFlow architecture shows three main advantages compared to traditional statistical and contemporary deep generative models: 1) it is well-suited for RLP generation under continuous conditions, such as varying weather and annual electricity consumption, 2) it demonstrates superior scalability in different datasets compared to traditional statistical models, and 3) it also demonstrates better modeling capabilities in capturing the complex correlation of RLPs compared with deep generative models.