Scholarlink

<p>Due to the need to reduce greenhouse gas emissions and prevent climate change, renewable energy sources like solar and wind power are becoming increasingly important in the energy landscape. However, the intermittent nature of renewable energy generation poses challenges for its integration into existing power grids. In the paper, we propose a Salp swarm-optimized twin support vector machine (SSO-TSVM) to predict smart grid stability and gather a vast amount of data to evaluate the performance of the proposed method. SSO-TSVM is an advanced machine algorithms that predicts electricity system stability by utilizing SSO efficiency characteristics and TSVM’s classification capabilities. This improves reliability and durability, particularly when it comes to regulating swings in renewable energy. Next, we preprocess the collected dataset by using Z-score normalization. And Map reduction technique is used to minimize the volume of data that needs to be analyzed for parallel computing. The relevant features are extracted by using principal component analysis (PCA). Experiment for the proposed algorithm can be simulated by using Python 3.11 software. The experimental results of the proposed method are analyzed in terms of f1-score (96%) and accuracy (92%), precision (94%), recall (92%). It can be demonstrated that the proposed SSO-TSVM achieves the greatest performance in predicting smart grid stability compared to existing approaches.</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

Leveraging data analytics and ML for enhanced renewable energy resource management

  • 期刊论文

  • 发表日期：

    2025年1月8日

查看全文
  • Ankur Pan Saikia,
  • Kunal Dey,
  • Amandeep Gill,
  • Amit Gantra

摘要

Due to the need to reduce greenhouse gas emissions and prevent climate change, renewable energy sources like solar and wind power are becoming increasingly important in the energy landscape. However, the intermittent nature of renewable energy generation poses challenges for its integration into existing power grids. In the paper, we propose a Salp swarm-optimized twin support vector machine (SSO-TSVM) to predict smart grid stability and gather a vast amount of data to evaluate the performance of the proposed method. SSO-TSVM is an advanced machine algorithms that predicts electricity system stability by utilizing SSO efficiency characteristics and TSVM’s classification capabilities. This improves reliability and durability, particularly when it comes to regulating swings in renewable energy. Next, we preprocess the collected dataset by using Z-score normalization. And Map reduction technique is used to minimize the volume of data that needs to be analyzed for parallel computing. The relevant features are extracted by using principal component analysis (PCA). Experiment for the proposed algorithm can be simulated by using Python 3.11 software. The experimental results of the proposed method are analyzed in terms of f1-score (96%) and accuracy (92%), precision (94%), recall (92%). It can be demonstrated that the proposed SSO-TSVM achieves the greatest performance in predicting smart grid stability compared to existing approaches.