2 views (last 30 days)

Show older comments

Hi everyone, I'm building a neural network for the prediction of the reactive power of an HV / MV substation knowing the reactive power.

I started using the script that matlab allows me to create with the machine learning tool for training the neural network.

I inserted an additional hidden layer with a tansig function and increased the validation checks value.

Could you give me advice on how to improve the performance of my network?

Consider that the input is made up of a matrix of 6 columns and 70080 rows, of which the first column is composed of the quarterly active power values, the remaining rows are identifying the month, day, hour, indication of the day of the week and indices of the type of day (holiday, pre-holiday or working day).

The target consists of a column of 70080 lines with the reactive power values.

Does it make sense to use that number of neurons for the hidden layers?

Are there other types of networks that can help me get better results?

What training algorithms could I use?

% Solve an Input-Output Time-Series Problem with a Time Delay Neural Network

% Script generated by Neural Time Series app.

% Created 03-Dec-2020 16:01:08

%

% This script assumes these variables are defined:

%

% input - input time series.

% target - target time series.

load('input');

load('target');

X = tonndata(input,false,false);

T = tonndata(target,false,false);

% Choose a Training Function

% For a list of all training functions type: help nntrain

% 'trainlm' is usually fastest.

% 'trainbr' takes longer but may be better for challenging problems.

% 'trainscg' uses less memory. Suitable in low memory situations.

trainFcn = 'trainlm'; % Levenberg-Marquardt backpropagation.

% Create a Time Delay Network

inputDelays = 1:24;

hiddenlayer1.size = 48;

hiddenlayer1.transferfcn = 'logsig';

hiddenlayer2.size = 24;

hiddenlayer2.transferfcn = 'tansig';

hiddenLayerSize = [hiddenlayer1.size,hiddenlayer2.size];

net = timedelaynet(inputDelays,hiddenLayerSize,trainFcn);

% Choose Input and Output Pre/Post-Processing Functions

% For a list of all processing functions type: help nnprocess

net.input.processFcns = {'removeconstantrows','mapminmax'};

net.output.processFcns = {'removeconstantrows','mapminmax'};

% Prepare the Data for Training and Simulation

% The function PREPARETS prepares timeseries data for a particular network,

% shifting time by the minimum amount to fill input states and layer

% states. Using PREPARETS allows you to keep your original time series data

% unchanged, while easily customizing it for networks with differing

% numbers of delays, with open loop or closed loop feedback modes.

[x,xi,ai,t] = preparets(net,X,T);

% Setup Division of Data for Training, Validation, Testing

% For a list of all data division functions type: help nndivision

net.divideFcn = 'dividerand'; % Divide data randomly

net.divideMode = 'time'; % Divide up every sample

net.divideParam.trainRatio = 70/100;

net.divideParam.valRatio = 15/100;

net.divideParam.testRatio = 15/100;

% Set max fail

net.trainParam.max_fail = 100;

% Choose a Performance Function

% For a list of all performance functions type: help nnperformance

net.performFcn = 'mse'; % Mean Square Error

% Choose Plot Functions

% For a list of all plot functions type: help nnplot

net.plotFcns = {'plotperform','plottrainstate', 'ploterrhist', ...

'plotregression', 'plotresponse', 'ploterrcorr', 'plotinerrcorr'};

% Train the Network

[net,tr] = train(net,x,t,xi,ai);

% Test the Network

y = net(x,xi,ai);

e = gsubtract(t,y);

performance = perform(net,t,y);

% Recalculate Training, Validation and Test Performance

trainTargets = gmultiply(t,tr.trainMask);

valTargets = gmultiply(t,tr.valMask);

testTargets = gmultiply(t,tr.testMask);

trainPerformance = perform(net,trainTargets,y);

valPerformance = perform(net,valTargets,y);

testPerformance = perform(net,testTargets,y);

% View the Network

view(net)

% Plots

% Uncomment these lines to enable various plots.

%figure, plotperform(tr)

%figure, plottrainstate(tr)

%figure, ploterrhist(e)

%figure, plotregression(t,y)

%figure, plotresponse(t,y)

%figure, ploterrcorr(e)

%figure, plotinerrcorr(x,e)

% Step-Ahead Prediction Network

% For some applications it helps to get the prediction a timestep early.

% The original network returns predicted y(t+1) at the same time it is

% given x(t+1). For some applications such as decision making, it would

% help to have predicted y(t+1) once x(t) is available, but before the

% actual y(t+1) occurs. The network can be made to return its output a

% timestep early by removing one delay so that its minimal tap delay is now

% 0 instead of 1. The new network returns the same outputs as the original

% network, but outputs are shifted left one timestep.

nets = removedelay(net);

nets.name = [net.name ' - Predict One Step Ahead'];

view(nets)

[xs,xis,ais,ts] = preparets(nets,X,T);

ys = nets(xs,xis,ais);

stepAheadPerformance = perform(nets,ts,ys);

% Deployment

% Change the (false) values to (true) to enable the following code blocks.

% See the help for each generation function for more information.

if (true)

% Generate MATLAB function for neural network for application

% deployment in MATLAB scripts or with MATLAB Compiler and Builder

% tools, or simply to examine the calculations your trained neural

% network performs.

genFunction(net,'myNeuralNetworkFunction');

y = myNeuralNetworkFunction(x,xi,ai);

end

if (false)

% Generate a matrix-only MATLAB function for neural network code

% generation with MATLAB Coder tools.

genFunction(net,'myNeuralNetworkFunction','MatrixOnly','yes');

x1 = cell2mat(x(1,:));

xi1 = cell2mat(xi(1,:));

y = myNeuralNetworkFunction(x1,xi1);

end

if (false)

% Generate a Simulink diagram for simulation or deployment with.

% Simulink Coder tools.

gensim(net);

end

Prateek Rai
on 13 Sep 2021

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!