基于K-Means++和Elman神经网络的低压台区线损计算方法
Line Loss Calculation Method for Low-voltage Substations Based on K-Means++and Elman Neural Networks
张林山 1廖耀华 1王恩 1李波 1朱梦梦 1王毅2
作者信息
- 1. 云南电网有限责任公司电力科学研究院,昆明 650217;云南省绿色能源与数字电力量测及控保重点实验室,昆明 650217
- 2. 重庆邮电大学通信与信息工程学院,重庆 400065
- 折叠
摘要
为了解决低压台区线损计算在理论上因线路复杂、用户众多以及数据获取困难等带来计算难度与精度不足的问题,提出了 一种结合改进K-Means++算法与Elman神经网络的创新计算方法.深入分析了低压台区线损的决定因素,并依据相关性分析构建了线损的关键特征指标集.采纳主成分分析方法实施数据降维,简化数据结构.通过改进的K-Means++算法对数据集进行有效聚类,优化模型训练过程.同时,整合粒子群优化算法进一步提升Elman神经网络的性能.通过对实际数据进行仿真验证,结果证实所提出的方法在训练效率和计算精度方面表现优异.
Abstract
To address theoretical challenges and accuracy limitations in estimating line losses for low-voltage substations,arising from complex transmission lines,multiple users,and data acquisition difficulties,we devised an innovative calculation approach in this study.Our method merges an enhanced K-means++algorithm with an Elman neural network.We initially conducted an in-depth analysis of factors influencing line losses in low-voltage substations and identified key indicators through correlation analysis.Employing principal component analysis(PCA),we reduced data dimensionality and complexity.Utilizing an enhanced K-means++algorithm,we efficiently clustered the dataset and optimized model training.Integration of particle swarm optimization algorithms further boosted the Elman neural networks'performance.Simulation verification using actual data affirmed the method's superior performance in training efficiency and computational accuracy.
关键词
线损/相关系数/改进K-Means++算法/Elman神经网络Key words
line loss/correlation coefficient/improved K-Means++algorithm/Elman neural network引用本文复制引用
基金项目
中国南方电网有限责任公司科技项目(YNKJXM20220166)
出版年
2024
NETL
NSTL
万方数据