​1 简介为了解决短期负荷预测精度低,准确性差等问题,采用一种使用灰狼优化算法(GWO)优化长短期记忆网络(LSTM)的短期负荷预测模型.针对模型的参数较难选择的问题,利用GWO对LSTM模型参数寻优.通过实例验证了预测模型的有效性,结果表明GWO-LSTM比LSTM模型具有更好的效果.1.1 灰狼优化算法1.2 LSTM模型1.3 基于鲸鱼算法优化LSTM流程2 部分代码%% Get cuckoos by ramdom walkfunction nestget_cuckoos(nest,best,Lb,Ub)% Levy flightsnsize(nest,1);% Levy exponent and coefficient% For details, see equation (2.21), Page 16 (chapter 2) of the book% X. S. Yang, Nature-Inspired Metaheuristic Algorithms, 2nd Edition, Luniver Press, (2010).beta3/2;sigma(gamma(1beta)sin(pibeta/2)/(gamma((1beta)/2)beta2^((beta-1)/2)))^(1/beta);for j1:n,snest(j,:);% This is a simple way of implementing Levy flights% For standard random walks, use step1;%% Levy flights by Mantegnas algorithmurandn(size(s))*sigma;vrandn(size(s));stepu./abs(v).^(1/beta);% In the next equation, the difference factor (s-best) means that% when the solution is the best solution, it remains unchanged.stepsize0.001step.(s-best);% Here the factor 0.01 comes from the fact that L/100 should the typical% step size of walks/flights where L is the typical lenghtscale;% otherwise, Levy flights may become too aggresive/efficient,% which makes new solutions (even) jump out side of the design domain% (and thus wasting evaluations).% Now the actual random walks or flightsssstepsize.*randn(size(s));% Apply simple bounds/limitsnest(j,:)simplebounds(s,Lb,Ub);end% Application of simple constraintsfunction ssimplebounds(s,lb,ub)Flag4ubsub;Flag4lbslb;ss.(~(Flag4ubFlag4lb))ub.Flag4ublb.*Flag4lb;% Apply the lower bound% ns_tmps;% Ins_tmpLb;% ns_tmp(I)Lb(I);%% % Apply the upper bounds% Jns_tmpUb;% ns_tmp(J)Ub(J);% % Update this new move% sns_tmp;3 仿真结果4 参考文献[1]曹开田, 高莘尧, 姜梦彦. 一种基于鲸鱼算法优化LSTM的频谱感知方法:.[2]刘昊东, 邹必昌. 基于鲸鱼算法优化长短期记忆网络的短期负荷预测[J]. 电子世界(3):2.