Electricity Demand Forecasting with Hybrid Statistical and Machine Learning Algorithms: Case Study of Ukraine

TL;DR

This paper introduces a hybrid statistical and machine learning approach for long-term hourly electricity demand forecasting in Ukraine, demonstrating high accuracy over two years of out-of-sample predictions.

Contribution

It presents a novel hybrid model combining regression, ARIMA, and LSTM techniques specifically designed for long-term hourly electricity demand forecasting.

Findings

Hybrid model achieves 96.83% accuracy in two-year out-of-sample forecasts.

Combining regression and LSTM enhances long-term forecasting accuracy.

Model effectively captures hourly, daily, and yearly consumption patterns.

Abstract

This article presents a novel hybrid approach using statistics and machine learning to forecast the national demand of electricity. As investment and operation of future energy systems require long-term electricity demand forecasts with hourly resolution, our mathematical model fills a gap in energy forecasting. The proposed methodology was constructed using hourly data from Ukraine's electricity consumption ranging from 2013 to 2020. To this end, we analysed the underlying structure of the hourly, daily and yearly time series of electricity consumption. The long-term yearly trend is evaluated using macroeconomic regression analysis. The mid-term model integrates temperature and calendar regressors to describe the underlying structure, and combines ARIMA and LSTM ``black-box'' pattern-based approaches to describe the error term. The short-term model captures the hourly seasonality through calendar regressors and multiple ARMA models for the residual. Results show that the best forecasting model is composed by combining multiple regression models and a LSTM hybrid model for residual prediction. Our hybrid model is very effective at forecasting long-term electricity consumption on an hourly resolution. In two years of out-of-sample forecasts with 17520 timesteps, it is shown to be within 96.83 \% accuracy.