Scholarlink

<p>The advancement of smart grids (SGs) has driven interest in load forecasting (LF) to improve the reliability, stability, and efficiency of energy distribution. LF supports SGs in making informed decisions on power operations, upgrades, and pricing, which are essential for delivering electrical power fairly and efficiently. However, traditional LF methods struggle to capture the complex interactions between energy consumption and external factors. This paper proposes a hybrid artificial neural network-firefly optimization model to address these challenges, incorporating power losses and reliability into the forecasting process to enhance accuracy. The data show a 421% rise in real power loss, a 424% increase in reactive power loss, and a 128% growth in expected energy not supplied (EENS) over 11&#xa0;years, underlining the importance of considering power losses in solar energy system designs. Using data from Tamil Nadu’s energy grid (TANGEDCO) since 2013, this model provides utility companies with predictive insights for strategic grid improvements. This study highlights the benefits of solar integration, supporting sustainable energy practices and informing long-term infrastructure planning.</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 smart grid reliability with advanced load forecasting using deep learning

  • 期刊论文

  • 发表日期：

    2025年1月2日

查看全文
  • J. Jasmine,
  • M. Germin Nisha,
  • Rajesh Prasad

摘要

The advancement of smart grids (SGs) has driven interest in load forecasting (LF) to improve the reliability, stability, and efficiency of energy distribution. LF supports SGs in making informed decisions on power operations, upgrades, and pricing, which are essential for delivering electrical power fairly and efficiently. However, traditional LF methods struggle to capture the complex interactions between energy consumption and external factors. This paper proposes a hybrid artificial neural network-firefly optimization model to address these challenges, incorporating power losses and reliability into the forecasting process to enhance accuracy. The data show a 421% rise in real power loss, a 424% increase in reactive power loss, and a 128% growth in expected energy not supplied (EENS) over 11 years, underlining the importance of considering power losses in solar energy system designs. Using data from Tamil Nadu’s energy grid (TANGEDCO) since 2013, this model provides utility companies with predictive insights for strategic grid improvements. This study highlights the benefits of solar integration, supporting sustainable energy practices and informing long-term infrastructure planning.