基于大数据的智能电网状态远程监测方法

智能电网作为一种智能化电力传输载体,在电力供应环节发挥了重要作用,因此保证其正常运行具有重要的现实意义。当前智能电网状态远程监测多与智能算法相结合,通过智能算法完成状态评估,常见的智能算法有神经网络、决策树以及支持向量机等,但这三种算法应用下,空间复杂度与时间复杂度较大。针对上述问题,提出一种基于大数据的自适应免疫粒子群算法智能电网状态远程监测方法。方法首先利用量测工具对智能电网状态信息量进行采集,然后对采集到的信息量进行处理,包括数据清洗、数据去噪、数据消减、数据标准化,最后利用自适应免疫粒子群算法实现智能电网健康状况评估。结果表明:与神经网络、决策树以及支持向量机三种算法相比,自适应免疫粒子群算法运行下,产生的空间复杂度与时间复杂度最小,分别为247.7 byte和154 s。

Remote monitoring method of smart grid state based on big data

As an intelligent power transmission carrier,smart grid plays an important role in power supply,so it has important practical significance to ensure its normal operation.At present,the remote monitoring of smart grid status mostly combines with intelligent algorithm,which completes state assessment through intelligent algorithm.Common intelligent algorithms include neural network,decision tree and support vector machine,etc.However,under the application of these three algorithms,the space complexity and time complexity are relatively large.To solve the above problems,an adaptive immune particle swarm optimization(IAPSO)based on large data is proposed for smart grid state remote monitoring.Firstly,the state information of smart grid is collected by measuring tools,and then the collected information is processed,including data cleaning,data denoising,data reduction,data standardization.Finally,the adaptive immune particle swarm optimization(AIPSO)algorithm is used to evaluate the health status of smart grid.The results show that,compared with the three algorithms of neural network,decision tree and support vector machine,the space complexity and time complexity of this algorithm are the smallest,which are 247.7 byte and 154 seconds respectively.