Variational Autoencoder-Based Approach to Latent Feature Analysis on Efficient Representation of Power Load Monitoring Data

TL;DR

This paper introduces VAE-LF, a variational autoencoder-based model that effectively represents and completes high-dimensional, incomplete power load data, improving forecasting accuracy in smart grid applications.

Contribution

The paper presents a novel VAE-based model for efficient low-dimensional representation and data completion of high-dimensional power load data, outperforming benchmarks.

Findings

VAE-LF achieves lower RMSE and MAE than benchmark models.

VAE-LF performs especially well on low sparsity ratio data.

The method enhances electric load management in smart grids.

Abstract

With the development of smart grids, High-Dimensional and Incomplete (HDI) Power Load Monitoring (PLM) data challenges the performance of Power Load Forecasting (PLF) models. In this paper, we propose a potential characterization model VAE-LF based on Variational Autoencoder (VAE) for efficiently representing and complementing PLM missing data. VAE-LF learns a low-dimensional latent representation of the data using an Encoder-Decoder structure by splitting the HDI PLM data into vectors and feeding them sequentially into the VAE-LF model, and generates the complementary data. Experiments on the UK-DALE dataset show that VAE-LF outperforms other benchmark models in both 5% and 10% sparsity test cases, with significantly lower RMSE and MAE, and especially outperforms on low sparsity ratio data. The method provides an efficient data-completion solution for electric load management in smart grids.