基于改进遗传算法的多源数据继电保护定值优化策略

Relay protection settings optimization strategy for multi⁃source data based on improved genetic algorithm

针对传统继电保护策略存在准确度差且效率低的问题,文中基于多源数据提出了一种性能更优的继电保护策略。对于多源数据一致性差、分析困难的特点,采用经验模态分解对数据进行预处理,以获得不同梯度的时域以及频域数据。同时为了增强传统遗传算法的分类性能,还引入了极限学习机对输入数据进行分类,并使用遗传算法对极限学习机的参数加以优化。所设计的模型可以对配电网发生的故障进行判定,并引导继电保护设施做出正确响应。实验结果表明,相较于对比算法,该算法具有更高的准确性及更优的效率,且优化后继电保护装置的判断综合准确率可达89%。

Aiming at the shortcomings of poor accuracy and low efficiency of traditional relay protection strategies,this paper proposes a better relay protection strategy based on multi⁃source data.For the characteristics of poor consistency and difficult analysis of multi⁃source data,empirical mode decomp⁃osition is used to preprocess the data to obtain time⁃domain and frequency⁃domain data with different gradients.At the same time,in order to enhance the classification performance of traditional genetic algorithm,limit learning machine is introduced to classify the input data,and genetic algorithm is used to optimize the parameters of limit learning machine.The designed model can judge the faults of distribution network and guide the relay protection facilities to make correct response.The experimental results show that compared with the comparison algorithm,the algorithm in this paper has higher accuracy and better efficiency,and the comprehensive accuracy of the optimized relay protection device is 89%.