Scholarlink

In the modern era, the United Kingdom (UK) is moving towards a future enriched with sustainability and energy efficiency. Thus, accurate electricity consumption predictions are one of the major factors in the UK. This research focuses on electricity consumption in the UK for the next year using historical data and analyzing them through time series analysis. Traditional statistical methods such as Autoregressive Integrated Moving Average (ARIMA), and Seasonal Autoregressive Moving Average (SARIMA) and machine learning algorithms such as XGBoost, Linear Trees and Prophet are used in this research to predict the consumption patterns of electricity in the UK. Moreover, this study will further focus on evaluating the performances and the behavioral patterns of each model in forecasting electricity consumption by developing a comparative analysis that highlights the strengths and weaknesses of each model. The main objective of the following research is to create a model which can forecast the consumption of electricity for the next year in the UK whilst identifying the consumption patterns of electricity in the UK. Hence, this analysis encompasses valuable information for energy providers, consumers and policymakers to enhance energy efficiency and maintain energy sustainability in the UK. Furthermore, by this analysis it was determined that Prophet model is the best model to be used in predicting the electricity consumption for next year in the UK as it has generated significant results compared to other models making the Mean Absolute Percentage Error (MAPE) 0.14% and the Root Mean Squared Error (RMSE) 4409.71.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Predicting Long-Term Electricity Consumption Using Time Series Data: Use Case of the UK Electricity Data

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Samudra Nimesh De Silva,
  • Bhupesh Kumar Mishra,
  • Will Sayers,
  • Zainab Loukil

摘要

In the modern era, the United Kingdom (UK) is moving towards a future enriched with sustainability and energy efficiency. Thus, accurate electricity consumption predictions are one of the major factors in the UK. This research focuses on electricity consumption in the UK for the next year using historical data and analyzing them through time series analysis. Traditional statistical methods such as Autoregressive Integrated Moving Average (ARIMA), and Seasonal Autoregressive Moving Average (SARIMA) and machine learning algorithms such as XGBoost, Linear Trees and Prophet are used in this research to predict the consumption patterns of electricity in the UK. Moreover, this study will further focus on evaluating the performances and the behavioral patterns of each model in forecasting electricity consumption by developing a comparative analysis that highlights the strengths and weaknesses of each model. The main objective of the following research is to create a model which can forecast the consumption of electricity for the next year in the UK whilst identifying the consumption patterns of electricity in the UK. Hence, this analysis encompasses valuable information for energy providers, consumers and policymakers to enhance energy efficiency and maintain energy sustainability in the UK. Furthermore, by this analysis it was determined that Prophet model is the best model to be used in predicting the electricity consumption for next year in the UK as it has generated significant results compared to other models making the Mean Absolute Percentage Error (MAPE) 0.14% and the Root Mean Squared Error (RMSE) 4409.71.