【创新未发表】基于凌日优化算法TSOA优化ELM实现负荷预测算法研究Matlab代码

Matlab算法改进和仿真定制工程师

343人浏览 · 2026-06-21 21:36:05

Matlab算法改进和仿真定制工程师 · 2026-06-21 21:36:05 发布

✅作者简介：热爱科研的Matlab仿真开发者，擅长毕业设计辅导、数学建模、数据处理、程序设计科研仿真。

🍎完整代码获取定制创新论文复现点击：Matlab科研工作室

👇 关注我领取海量matlab电子书和数学建模资料

🍊个人信条：做科研，博学之、审问之、慎思之、明辨之、笃行之，是为：博学慎思，明辨笃行。

🔥 内容介绍

一、引言

负荷预测在电力系统的规划、运行和管理中起着关键作用。准确的负荷预测有助于优化发电计划、合理分配电力资源以及提高电网运行的稳定性和经济性。传统的负荷预测方法在处理复杂的负荷变化模式时存在局限性，而基于机器学习的方法展现出了强大的潜力。极限学习机（ELM）作为一种快速且有效的单隐层前馈神经网络，但其随机生成的输入权重和偏置可能导致预测性能的不稳定。本文提出利用凌日优化算法（TSOA）对 ELM 进行优化，旨在提高负荷预测的精度和可靠性。

二、相关理论基础

凌日优化算法（TSOA）
- 灵感来源
  ：凌日优化算法是一种受天文现象凌日启发而提出的新型元启发式优化算法。在天文学中，凌日是指一个天体在另一个天体与观测者之间通过的现象。TSOA 模拟了行星在围绕恒星运行过程中，受恒星引力和其他行星引力影响下的运动轨迹。
- 算法流程
  ：在 TSOA 中，每个优化问题的解被看作是一个 “行星”，其位置代表了问题的一个潜在解。算法通过模拟行星的运动来搜索最优解。行星的运动受到引力的影响，引力的大小与行星之间的距离以及目标函数值相关。距离较近且目标函数值较好的行星对其他行星产生更强的引力。行星根据引力的作用更新自己的位置，在搜索空间中不断移动，逐渐向最优解靠近。同时，算法引入了一定的随机扰动，以避免算法陷入局部最优解，增强全局搜索能力。例如，在每次迭代中，行星的位置更新公式结合了引力作用和随机因素，使得算法能够在探索新的搜索区域和利用已发现的较好解之间取得平衡。

三、基于 TSOA 优化 ELM 的负荷预测算法

⛳️ 运行结果

📣 部分代码

function [Best_Planet , best,Bestss] = TransitSearch (ns,maxcycle,Vmin,Vmax,nvar,CostFunction)

SN=10;

%% Initialization

Empty.Location = [];

Empty.Cost = inf;

Galaxy_Center = repmat (Empty, 1, 1);

region = repmat (Empty, ns*SN, 1);

selested_regions = repmat (Empty, ns, 1);

Stars = repmat (Empty, ns, 1);

Stars_sorted = zeros(ns,1);

Ranks = 1:1:ns;

Stars_Ranks = zeros(ns,1);

Luminosity = zeros(ns,1);

Star_RanksNormal = zeros(ns,1);

Distance = zeros(ns,1);

Transit0 = zeros(ns,1);

SN_P = repmat (Empty, SN, 1);

Bests=region;

if length(Vmin) >1

Vmin=Vmin;

Vmax=Vmax;

else

Vmin=Vmin*ones(1,nvar);

Vmax=Vmax*ones(1,nvar);

end

%% Galaxy Phase

% Initial Location of The Center of the Galaxy

Galaxy_Center.Location = unifrnd(Vmin,Vmax,1,nvar);

% Galaxy_Center.Location=initialization(ns,nvar,Vmax,Vmin);

Galaxy_Center.Cost = CostFunction(Galaxy_Center.Location);

% Galactic Habitate Zone of the Galaxy

for l = 1:ns*SN

zone = randi(2);

if zone ==1

difference = rand().*(Galaxy_Center.Location)-(unifrnd(Vmin,Vmax,1,nvar));

else

difference = rand().*(Galaxy_Center.Location)+(unifrnd(Vmin,Vmax,1,nvar));

end

Noise = ((rand(1,nvar)).^3).*(unifrnd(Vmin,Vmax,1,nvar));

region(l).Location = Galaxy_Center.Location + difference - Noise;

region(l).Location = max(region(l).Location, Vmin);

region(l).Location = min(region(l).Location, Vmax);

region(l).Cost = CostFunction(region(l).Location);

end

% Selection of Stars from the Galactic Habitate Zone of the Galaxy

[Sort,index]=sort([region.Cost]);

for i = 1:ns

selested_regions(i) = region(i);

for k = 1:SN

zone = randi(2);

if zone ==1

difference = rand().*(selested_regions(i).Location)-rand().*(unifrnd(Vmin,Vmax,1,nvar));

else

difference = rand().*(selested_regions(i).Location)+rand().*(unifrnd(Vmin,Vmax,1,nvar));

end

Noise = ((rand(1,nvar)).^3).*(unifrnd(Vmin,Vmax,1,nvar));

new.Location = selested_regions(i).Location + difference - Noise;

new.Location = max(new.Location, Vmin);

new.Location = min(new.Location, Vmax);

new.Cost = CostFunction(new.Location);

if new.Cost < Stars(i).Cost

Stars(i) = new;

end

% Initial Location of the Best Planets (Start Point: Its Star)

Best_Planets = Stars;

% Specification of the Best Planet

[Sort,index]=sort([Best_Planets(1).Cost]);

Best_Planet = Best_Planets(index(1,1));

% Telescope Location

Telescope.Location = unifrnd(Vmin,Vmax,1,nvar);

% Determination of the Luminosity of the Stars

for i = 1:ns

Stars_sorted(i,1) = Stars(i).Cost;

end

Stars_sorted = sort (Stars_sorted);

for i = 1:ns

for ii = 1:ns

if Stars(i).Cost == Stars_sorted(ii,1)

Stars_Ranks(i,1) = Ranks(1,ii);

Star_RanksNormal(i,1) = (Stars_Ranks(i,1))./ns;

end

Distance(i,1) = sum((Stars(i).Location-Telescope.Location).^2).^0.5;

Luminosity(i,1) = Star_RanksNormal(i,1)/((Distance(i,1))^2);

end

Luminosity_new = Luminosity;

Stars2 = Stars;

%% Loops of the TS Algorithm

for it = 1:maxcycle

%% Transit Phase

Transit = Transit0;

Luminosity = Luminosity_new;

for i = 1:ns

difference = (2*rand()-1).*(Stars(i).Location);

Noise = ((rand(1,nvar)).^3).*(unifrnd(Vmin,Vmax,1,nvar));

Stars2(i).Location = Stars(i).Location + difference - Noise;

Stars2(i).Location = max(Stars2(i).Location, Vmin);

Stars2(i).Location = min(Stars2(i).Location, Vmax);

Stars2(i).Cost = CostFunction(Stars2(i).Location);

end

for i = 1:ns

Stars_sorted(i,1) = Stars2(i).Cost;

end

Stars_sorted = sort (Stars_sorted);

for i = 1:ns

for ii = 1:ns

if Stars2(i).Cost == Stars_sorted(ii,1)

Stars_Ranks(i,1) = Ranks(1,ii);

Star_RanksNormal(i,1) = (Stars_Ranks(i,1))./ns;

end

Distance(i,1) = sum((Stars2(i).Location-Telescope.Location).^2).^0.5;

Luminosity_new(i,1) = Star_RanksNormal(i,1)/((Distance(i,1))^2);

if Luminosity_new(i,1) < Luminosity(i,1)

Transit (i,1) = 1; % Has transit been observed? 0 = No; 1 = Yes

end

Stars = Stars2;

%% Location Phase (Exploration)

for i = 1:ns

if Transit (i,1) == 1

% Determination of the Location of the Planet

Luminosity_Ratio = Luminosity_new(i,1)/Luminosity(i,1);

Planet.Location = (rand().*Telescope.Location + Luminosity_Ratio.*Stars(i).Location)./2;

for k = 1:SN

zone = randi(3);

if zone ==1

new.Location = Planet.Location - (2*rand()-1).*(unifrnd(Vmin,Vmax,1,nvar));

elseif zone ==2

new.Location = Planet.Location + (2*rand()-1).*(unifrnd(Vmin,Vmax,1,nvar));

else

new.Location = Planet.Location + (2.*rand(1,nvar)-1).*(unifrnd(Vmin,Vmax,1,nvar));

end

new.Location = max(new.Location, Vmin);

new.Location = min(new.Location, Vmax);

% new.Cost = CostFunction(new.Location);

SN_P(k) = new;

end

SUM = 0;

for k = 1:SN

SUM = SUM+SN_P(k).Location;

end

new.Location = SUM./SN;

new.Cost = CostFunction(new.Location);

if new.Cost < Best_Planets(i).Cost

Best_Planets(i) = new;

end

else % No Transit observed: Neighbouring planets

Neighbor.Location = (rand().*Stars(i).Location + rand().*(unifrnd(Vmin,Vmax,1,nvar)))./2;

for k = 1:SN

zone = randi(3);

if zone ==1

Neighbor.Location = Neighbor.Location - (2*rand()-1).*(unifrnd(Vmin,Vmax,1,nvar));

elseif zone ==2

Neighbor.Location = Neighbor.Location + (2*rand()-1).*(unifrnd(Vmin,Vmax,1,nvar));

else

Neighbor.Location = Neighbor.Location + (2.*rand(1,nvar)-1).*(unifrnd(Vmin,Vmax,1,nvar));

end

Neighbor.Location = max(Neighbor.Location, Vmin);

Neighbor.Location = min(Neighbor.Location, Vmax);

Neighbor.Cost = CostFunction (Neighbor.Location);

SN_P(k) = Neighbor;

end

SUM = 0;

for k = 1:SN

SUM = SUM+SN_P(k).Location;

end

Neighbor.Location = SUM./SN;

Neighbor.Cost = CostFunction (Neighbor.Location);

if Neighbor.Cost < Best_Planets(i).Cost

Best_Planets(i) = Neighbor;

end

%% Signal Amplification of the Best Planets (Exploitation)

for i = 1:ns

for k = 1:SN

RAND = randi(2 );

if RAND ==1

Power = randi(SN*ns);

Coefficient = 2*rand();

Noise = ((rand(1,nvar)).^Power).*(unifrnd(Vmin,Vmax,1,nvar));

else

Power = randi(SN*ns);

Coefficient = 2*rand();

Noise = -((rand(1,nvar)).^Power).*(unifrnd(Vmin,Vmax,1,nvar));

end

% new.Location = (rand().*Best_Planets(i).Location) - Coefficient.*Noise;

chance = randi(2);

if chance ==1

new.Location = Best_Planets(i).Location - Coefficient.*Noise;

else

new.Location = (rand().*Best_Planets(i).Location) - Coefficient.*Noise;

end

new.Location = max(new.Location, Vmin);

new.Location = min(new.Location, Vmax);

new.Cost = CostFunction(new.Location);

% new.Cost = Penalty(new,ConstraintFunction,CostFunction);

if new.Cost < Best_Planets(i).Cost

Best_Planets(i) = new;

best=Best_Planets(i).Location;

end

if Best_Planets(i).Cost < Best_Planet.Cost

Best_Planet = Best_Planets(i);

end

% Results

Bestss(it)=Best_Planet.Cost;

end

🔗 参考文献

🍅更多免费数学建模和仿真教程关注领取

脑启社区

脑启社区是一个专注类脑智能领域的开发者社区。欢迎加入社区，共建类脑智能生态。社区为开发者提供了丰富的开源类脑工具软件、类脑算法模型及数据集、类脑知识库、类脑技术培训课程以及类脑应用案例等资源。

更多推荐

具身智能VLA模型全景图：从Pi0到HoloBrain-0的15大开源力作

从Physical Intelligence的Pi0到地平线的HoloBrain-0，这15个模型不仅代表了当前VLA技术的水平，更展示了具身智能从‘单一任务’向‘通用操作’迈进的坚定步伐。无论是追求极致的灵巧控制，还是探索类脑架构的安全性，开源社区正在以前所未有的速度缩小仿真与现实的差距。同步开源了仅 0.2B 参数的端侧友好版本及全栈基础设施 RoboOrchard，提供从数据采集、标准化规范