Scholarlink

<p>This research work presents a novel approach utilizing a machine learning framework, known as the Improved Evolutionary Algorithm-Self Organized Maps (IEA-SOM), for solving the Optimal Reactive Power Dispatch (ORPD) problem in electrical power systems. This novel algorithm is applied to solve the non-linear single-objective deterministic and stochastic ORPD problem in the IEEE 30-bus test system. In addition, it is applied to solve the deterministic ORPD problem in the IEEE 118-bus system to evaluate its suitability for large-scale systems. In the stochastic ORPD problem, a mathematical model for solar PV power is utilized, which involves various meteorological parameters such as real-time solar irradiance, wind velocity, and photovoltaic panel temperature. A comparative statistical analysis has been conducted to demonstrate the efficacy of the proposed algorithm in relation to recently developed optimizers for solving the deterministic and stochastic ORPD problem. The simulation outcomes demonstrate that the proposed method outperforms recently introduced Evolutionary Algorithm-Self Organized Map (EASOM), Driving Training-Based Optimization (DTBO), and COOT Algorithm, which were employed to address the same problem.</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

An Advanced Machine Learning Framework for Efficient Reactive Power Dispatch in Solar PV Integrated System

  • 期刊论文

  • 发表日期：

    2026年2月26日

查看全文
  • G. K. Jaiswal,
  • U. Nangia,
  • N. K. Jain

摘要

This research work presents a novel approach utilizing a machine learning framework, known as the Improved Evolutionary Algorithm-Self Organized Maps (IEA-SOM), for solving the Optimal Reactive Power Dispatch (ORPD) problem in electrical power systems. This novel algorithm is applied to solve the non-linear single-objective deterministic and stochastic ORPD problem in the IEEE 30-bus test system. In addition, it is applied to solve the deterministic ORPD problem in the IEEE 118-bus system to evaluate its suitability for large-scale systems. In the stochastic ORPD problem, a mathematical model for solar PV power is utilized, which involves various meteorological parameters such as real-time solar irradiance, wind velocity, and photovoltaic panel temperature. A comparative statistical analysis has been conducted to demonstrate the efficacy of the proposed algorithm in relation to recently developed optimizers for solving the deterministic and stochastic ORPD problem. The simulation outcomes demonstrate that the proposed method outperforms recently introduced Evolutionary Algorithm-Self Organized Map (EASOM), Driving Training-Based Optimization (DTBO), and COOT Algorithm, which were employed to address the same problem.