Scholarlink

<p>By integrating battery energy storage systems (BESS) into the Microgrid (MG), it is possible to optimize the grid's dependable functioning under a range of load scenarios and support high-quality renewable energy (RE) fluctuations. To address the challenges mentioned above, this paper introduces a hybrid technique for optimizing the management of energy storage for battery options in the MG, which will improve the utilization of energy and ensure a stable supply of power by managing RE fluctuations. The suggested method integrates the golden jackal optimization (GJO) and robust variational physics informed neural network (RVPINN); therefore it is called the GJO–RVPINN technique. The aim is to improve economic performance of MGs integrated with BESS by reducing operating cost. By optimizing the BESS's operating settings, the GJO guarantees effective Energy Management and storage. The RVPINN is employed to predict RE generation and load demand, enabling optimized energy dispatch for improved grid stability. By then, the suggested method is implemented on MATLAB platform and evaluated with various existing techniques such as Particle Swarm Optimization (PSO), Multi Objective Natural Aggregation Algorithm, improved PSO, robust optimization algorithm, and Hybrid Interval-Robust Optimization. The suggested GJO–RVPINN method achieves an operational cost of $174.75 and an efficiency of 95% for optimal battery storage management in MGs.</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

Golden jackal optimizer and robust variational physics informed neural network for optimal battery storage management in microgrids

  • 期刊论文

  • 发表日期：

    2025年8月22日

查看全文
  • M. Sudha,
  • R. V. Preetha,
  • Praveena Mandapati,
  • P. Venkata Prasad

摘要

By integrating battery energy storage systems (BESS) into the Microgrid (MG), it is possible to optimize the grid's dependable functioning under a range of load scenarios and support high-quality renewable energy (RE) fluctuations. To address the challenges mentioned above, this paper introduces a hybrid technique for optimizing the management of energy storage for battery options in the MG, which will improve the utilization of energy and ensure a stable supply of power by managing RE fluctuations. The suggested method integrates the golden jackal optimization (GJO) and robust variational physics informed neural network (RVPINN); therefore it is called the GJO–RVPINN technique. The aim is to improve economic performance of MGs integrated with BESS by reducing operating cost. By optimizing the BESS's operating settings, the GJO guarantees effective Energy Management and storage. The RVPINN is employed to predict RE generation and load demand, enabling optimized energy dispatch for improved grid stability. By then, the suggested method is implemented on MATLAB platform and evaluated with various existing techniques such as Particle Swarm Optimization (PSO), Multi Objective Natural Aggregation Algorithm, improved PSO, robust optimization algorithm, and Hybrid Interval-Robust Optimization. The suggested GJO–RVPINN method achieves an operational cost of $174.75 and an efficiency of 95% for optimal battery storage management in MGs.