Scholarlink

<p>The sustained expansion of the world’s population has led to a remarkable escalation in renewable energy consumption as global economies adopt green energy systems; therefore, high-fidelity renewable energy consumption forecasting emerges as a crucial factor for efficient energy management and sustainable economic development. This study proposes a hybrid framework for forecasting renewable energy consumption. Machine learning (ML) predictive model integrated statistical models such as simple exponential smoothing (SES), the holt-winters (HW), and the autoregressive integrated moving average (ARIMA) model to form the hybrid framework. The explainable artificial intelligence (XAI) interprets the best predictive model’s feature contributions. The developed forecasting models were evaluated on a hold-out test set and validated across a 24-month future forecast period, along with comparative plots and metrics. The proposed system demonstrates 2.68% mean absolute percentage error (MAPE), which ensures the model’s operational effectiveness. This research emphasizes the efficiency of integrating a simple ML model with a statistical time series method for forecasting renewable energy consumption with a unique set of features, which provides a groundwork for broader advancement of energy management in the future.</p>

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

Enhanced Renewable Energy Consumption Forecasting Leveraging Machine Learning and Statistical Models with XAI Interpretability

  • 期刊论文

  • 发表日期：

    2026年5月7日

查看全文
  • Wazia Haque Onti,
  • Safiul Haque Chowdhury,
  • Muhammad Minoar Hossain,
  • Mohammad Mamun

摘要

The sustained expansion of the world’s population has led to a remarkable escalation in renewable energy consumption as global economies adopt green energy systems; therefore, high-fidelity renewable energy consumption forecasting emerges as a crucial factor for efficient energy management and sustainable economic development. This study proposes a hybrid framework for forecasting renewable energy consumption. Machine learning (ML) predictive model integrated statistical models such as simple exponential smoothing (SES), the holt-winters (HW), and the autoregressive integrated moving average (ARIMA) model to form the hybrid framework. The explainable artificial intelligence (XAI) interprets the best predictive model’s feature contributions. The developed forecasting models were evaluated on a hold-out test set and validated across a 24-month future forecast period, along with comparative plots and metrics. The proposed system demonstrates 2.68% mean absolute percentage error (MAPE), which ensures the model’s operational effectiveness. This research emphasizes the efficiency of integrating a simple ML model with a statistical time series method for forecasting renewable energy consumption with a unique set of features, which provides a groundwork for broader advancement of energy management in the future.