Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Electrical Load Forecasting Model Using Hybrid LSTM Neural Networks with Online Correction

Nan Lu, Quan Ouyang, Yang Li, Changfu Zou

TL;DR

A gradient regularization-based offline training algorithm and an output layer parameter fine-tuning-based online model correction method are developed to enhance the model's capabilities to defend against disturbance and adapt to the latest load data distribution, thus improving the forecasting accuracy.

Abstract

Accurate electrical load forecasting is of great importance for the efficient operation and control of modern power systems. In this work, a hybrid long short-term memory (LSTM)-based model with online correction is developed for day-ahead electrical load forecasting. Firstly, four types of features are extracted from the original electrical load dataset, including the historical time series, time index features, historical statistical features, and similarity features. Then, a hybrid LSTM-based electrical load forecasting model is designed, where an LSTM neural network block and a fully-connected neural network block are integrated that can model both temporal features (historical time series) and non-temporal features (the rest features). A gradient regularization-based offline training algorithm and an output layer parameter fine-tuning-based online model correction method are developed to enhance the model's capabilities to defend against disturbance and adapt to the latest load data distribution, thus improving the forecasting accuracy. At last, extensive experiments are carried out to validate the effectiveness of the proposed electrical load forecasting strategy with superior accuracy compared with commonly used forecasting models.

Electrical Load Forecasting Model Using Hybrid LSTM Neural Networks with Online Correction

TL;DR

A gradient regularization-based offline training algorithm and an output layer parameter fine-tuning-based online model correction method are developed to enhance the model's capabilities to defend against disturbance and adapt to the latest load data distribution, thus improving the forecasting accuracy.

Abstract

Accurate electrical load forecasting is of great importance for the efficient operation and control of modern power systems. In this work, a hybrid long short-term memory (LSTM)-based model with online correction is developed for day-ahead electrical load forecasting. Firstly, four types of features are extracted from the original electrical load dataset, including the historical time series, time index features, historical statistical features, and similarity features. Then, a hybrid LSTM-based electrical load forecasting model is designed, where an LSTM neural network block and a fully-connected neural network block are integrated that can model both temporal features (historical time series) and non-temporal features (the rest features). A gradient regularization-based offline training algorithm and an output layer parameter fine-tuning-based online model correction method are developed to enhance the model's capabilities to defend against disturbance and adapt to the latest load data distribution, thus improving the forecasting accuracy. At last, extensive experiments are carried out to validate the effectiveness of the proposed electrical load forecasting strategy with superior accuracy compared with commonly used forecasting models.
Paper Structure (24 sections, 8 equations, 8 figures, 4 tables)

This paper contains 24 sections, 8 equations, 8 figures, 4 tables.

Table of Contents

  1. INTRODUCTION
  2. PROBLEM STATEMENT
  3. Dataset Analysis
  4. Feature Selection
  5. Historical time series
  6. Time index features
  7. Historical statistical features
  8. Similarity features
  9. THE FORECASTING MODEL
  10. LSTM Neural Network for Temporal Features Modeling
  11. FCNN for Non-Temporal Features Modeling
  12. Block Concatenation and Output
  13. MODEL TRAINING AND ONLINE CORRECTION
  14. Offline Model Training based on Gradient Regularization
  15. Online Model Correction by Fine-Tuning Output Layer Parameters
  16. ...and 9 more sections

Figures (8)

  • Figure 1: Electrical load dataset from 2019-01-01 to 2020-12-31 in (a) Belgium, (b) Denmark, and (c) Norway.
  • Figure 2: Correlation of three statistical features between the previous week and target day.
  • Figure 3: Hybrid LSTM-based electrical load forecasting model scheme.
  • Figure 4: Structure of the LSTM neural network block in the developed model.
  • Figure 5: The forecasting results of the day-ahead electrical load by the developed model from 2021-01-01 to 2021-12-31 in (a) Belgium, (b) Denmark, and (c) Norway.
  • ...and 3 more figures