Scholarlink

<p>The increasing proliferation of Internet of Things (IoT) devices in energy infrastructure has accelerated the demand for high-resolution forecasting models capable of accurately predicting energy consumption from time series data. In this context, this study addresses the challenge of short-interval energy forecasting by leveraging Bidirectional Long Short-Term Memory networks (BiLSTM) enhanced through advanced hyperparameter tuning. We introduce a novel metaheuristic, the iHow Optimization Algorithm (iHowOA), inspired by human cognitive learning processes, to optimize BiLSTM architecture for improved generalization and accuracy. Our framework is evaluated on a real-world IoT-based HVAC blower energy consumption dataset, recorded at 10–15-minute intervals. Initial baseline modeling using BiLSTM yielded a mean squared error (MSE) of 0.008487059, while the iHowOA-optimized BiLSTM model achieved a substantially lower MSE of <InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(9.42 \times 10^{-7}\)</EquationSource> </InlineEquation>, reflecting a near order-of-magnitude improvement. These results demonstrate the strength of coupling human-inspired metaheuristics with deep sequence models for energy forecasting tasks. The proposed approach offers a scalable and adaptive solution for intelligent energy systems, enabling real-time prediction, optimization, and integration within smart building management frameworks.</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

Enhancing energy forecasting accuracy through human-inspired optimization: a novel iHowOA-BiLSTM framework for IoT applications

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年3月26日

查看全文
  • Amal H. Alharbi,
  • Doaa Sami Khafaga,
  • El-Sayed M. El-Kenawy,
  • Marwa M. Eid,
  • Ebrahim A. Mattar,
  • Mervat El-Seddek

摘要

The increasing proliferation of Internet of Things (IoT) devices in energy infrastructure has accelerated the demand for high-resolution forecasting models capable of accurately predicting energy consumption from time series data. In this context, this study addresses the challenge of short-interval energy forecasting by leveraging Bidirectional Long Short-Term Memory networks (BiLSTM) enhanced through advanced hyperparameter tuning. We introduce a novel metaheuristic, the iHow Optimization Algorithm (iHowOA), inspired by human cognitive learning processes, to optimize BiLSTM architecture for improved generalization and accuracy. Our framework is evaluated on a real-world IoT-based HVAC blower energy consumption dataset, recorded at 10–15-minute intervals. Initial baseline modeling using BiLSTM yielded a mean squared error (MSE) of 0.008487059, while the iHowOA-optimized BiLSTM model achieved a substantially lower MSE of \(9.42 \times 10^{-7}\) , reflecting a near order-of-magnitude improvement. These results demonstrate the strength of coupling human-inspired metaheuristics with deep sequence models for energy forecasting tasks. The proposed approach offers a scalable and adaptive solution for intelligent energy systems, enabling real-time prediction, optimization, and integration within smart building management frameworks.