基于深度神经网络的高压直流换流站能效评估方法

Energy Efficiency Evaluation Method of HVDC Converter Stations Based on Deep Neural Network

由于高压直流换流站设备的非线性特性及负荷波动性,换流站设备的能效难以精确计算和建模,给系统的运行维护及分析研究带来了困难,因此提出一种基于深度神经网络的高压直流换流站能效评估方法。通过参考IEC 61803标准确定影响换流站的能效的主要运行参数,并以此建立换流站能效样本数据集,然后利用深度神经网络算法对换流站能效关系进行建模,得到基于深度神经网络的换流站能效评估模型。最后基于国际大电网会议直流输电基准测试模型的PSCAD/EMTDC电磁暂态仿真对换流站的能效情况进行评估,所得结果验证了基于深度神经网络建立能效评估模型的可行性。

Due to the non⁃linear characteristics and load fluctuations of HVDC converter station equip⁃ment,it is difficult to accurately calculate and model the energy efficiency of a HVDC converter station equipment,which brings difficulties to the operation,maintenance and analysis of the system.Therefore,a kind of energy efficiency evaluation method based on deep neural network for HVDC converter stations is proposed in this paper.The main operating parameters affecting the energy efficiency of a HVDC converter station are determined by referring to IEC 61803 standard and the converter station energy efficiency sample data set is built accordingly.Then,the deep neural network algorithm is used to model the energy efficiency relationship of a HVDC converter station and an energy efficiency evaluation model based on deep neural network for HVDC converterstationsisobtained.Finally,the energy efficiency of the HVDC converterstation is evaluated on the basis of PSCAD/EMTDC electromagnetic transient simulation of the CIGRE benchmark model and the feasibility of the proposed energy efficiency evaluation model based on deep neural network is verified by the obtained result.