基于改进粒子群算法的换流站多协议无线数据分析及预测

Research on multi-protocol wireless data analysis and prediction of converter station based on improved particle swarm algorithm

目前直流输电正在朝着高电压大容量的技术方向发展,其在长距离输电、跨区域联网及调度灵活等方面的优势日趋显现,但由于换流站关键设备故障造成的直流系统非正常停运对电力系统造成的影响也越来越大。因此,加强对直流关键设备的感知程度,对关键设备的故障进行预判并提前进行处理,对减少直流系统非正常停运并提高供电可靠性具有重大意义。以宁夏国家电网换流站多协议无线数据为例,提出了基于灰狼算法的改进粒子群算法。实验表明,该粒子群-灰狼算法能够更精确地对换流站的各种监测数据进行预测,减小预测误差,为今后换流站的运行和维护提供了依据。

At present,DC transmission is developing toward high voltage and large capacity technology.Its advantages in longdistance transmission,cross-region networking and flexible dispatch are becoming more and more obvious,but at the same time,abnormal outage of DC system caused by critical equipment failure of converter station has a greater impact on power system.Therefore,it is of great significance to enhance the perception of critical DC equipment,to predict and handle the faults of critical DC equipment in advance,to reduce abnormal outage of DC system and to improve power supply reliability.Taking the multi-protocol wireless data of Ningxia State Grid converter station as an example,an improved particle swarm algorithm based on the gray wolf algorithm is proposed.The experimental results show that the particle swarm-wolf algorithm can more accurately predict the monitoring data of the converter station,reduce the prediction error,and provide a basis for the operation and maintenance of the converter station in the future.