Hybrid Approach for Electricity Price Forecasting using AlexNet and LSTM

TL;DR

This paper introduces a hybrid model combining AlexNet and LSTM for electricity price forecasting, significantly improving accuracy over traditional and standalone machine learning models by leveraging external variables and advanced feature extraction.

Contribution

The novel integration of AlexNet with LSTM for electricity price prediction enhances accuracy by effectively extracting features and modeling sequential data, outperforming existing models.

Findings

Hybrid model achieves 97.08% accuracy.

Outperforms RNN and ANN models.

Utilizes external variables like demand and weather.

Abstract

The recent development of advanced machine learning methods for hybrid models has greatly addressed the need for the correct prediction of electrical prices. This method combines AlexNet and LSTM algorithms, which are used to introduce a new model with higher accuracy in price forecasting. Despite RNN and ANN being effective, they often fail to deal with forex time sequence data. The traditional methods do not accurately forecast the prices. These traditional methods only focus on demand and price which leads to insufficient analysis of data. To address this issue, using the hybrid approach, which focuses on external variables that also effect the predicted prices. Nevertheless, due to AlexNet's excellent feature extraction and LSTM's learning sequential patterns, the prediction accuracy is vastly increased. The model is built on the past data, which has been supplied with the most significant elements like demand, temperature, sunlight, and rain. For example, the model applies methods, such as minimum-maximum scaling and a time window, to predict the electricity prices of the future. The results show that this hybrid model is good than the standalone ones in terms of accuracy. Although we got our accuracy rating of 97.08, it shows higher accompaniments than remaining models RNN and ANN with accuracies of 96.64 and 96.63 respectively.