Scholarlink

Forecasting energy consumption is very important in modern energy management, essential for grid stability, cost optimization, and resource planning. Machine learning is widely used but, the selection of the correct forecasting model remains challenge. This paper presents a comparison of three deep learning models for energy forecasting: Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Temporal Convolutional Network (TCN). Each model is then trained and tested on a real-world energy consumption dataset with time-based features. The performance is then measured using Mean Absolute Error (MAE) and Mean Squared Error (MSE). The highest performing model is also used to generate a 30-day forecast, showing its practical applicability for future energy planning.

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

A Comparative Analysis of Deep Learning Architectures for Short-Term Energy Consumption Forecasting Using Time-Based Weather Data

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • S. Kirthica,
  • Tarun Kumar Elangovan,
  • Nandith Rajesh,
  • T. K. Nikaash

摘要

Forecasting energy consumption is very important in modern energy management, essential for grid stability, cost optimization, and resource planning. Machine learning is widely used but, the selection of the correct forecasting model remains challenge. This paper presents a comparison of three deep learning models for energy forecasting: Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Temporal Convolutional Network (TCN). Each model is then trained and tested on a real-world energy consumption dataset with time-based features. The performance is then measured using Mean Absolute Error (MAE) and Mean Squared Error (MSE). The highest performing model is also used to generate a 30-day forecast, showing its practical applicability for future energy planning.