Reproduce the annual consumption of a building

Hello,

I have the annual consumption of a building in MWh per day. In order to simulate the consumption of this building for the years to come, I would like to create a series of data of the same type (consumption in MWh/day for one year) in a random way but with the same characteristics. That is to say to have the same average (within x%), close minimums and maximums and an equivalent distribution.

I think this would involve AI or Deep Learning. For this I have 3 years available to teach the algorithm the characteristics of my data to reproduce.

Am I clear enough? Do you have any idea how to solve my problem?

Thanks in advance.

Answer 1

[Ayush]

Kindly use the following link to get started with deep learning using MATLAB.

[Armel]

So sorry but this doesn't help me. :(

I don't want to classify images.

[Ayush]

I understand that you need to predict the data by using past 3 years data as input by using regression technique, kindly read about "Deep Learning with Time Series and Sequence Data" and the example provided "Time Series Forecasting Using Deep Learning" in mathworks documentation.

Link for the same is here.

[Armel]

Hello,

Thanks for the link, I spent the day trying to make the example work for me. I have learned a lot, solved some problems but I don't get a usable result and despite my efforts, I can't solve my problem. Here is the steps I followed : https://www.mathworks.com/help/deeplearning/ug/time-series-forecasting-using-deep-learning.html

Here are the wind data I give to Matlab for training and what I expect in output as well (predicting the wind speed per hour over a year).

I think that learning works. The program is running well so far. When we get to the prediction phase, it doesn't work anymore. The vector YTest :

YTest = predict(net,XTest,SequencePaddingDirection="left");

The YTest vector is not complete, and "NaN" appear very quickly. I work with vectors of dimensions 8760x1 (nb hours in a year). First thing I don't understand.

Therefore the part about RMSE doesn't work, but it's not very serious.

I then tried to run the "close loop forecasting", but the figure it displays doesn't make sense. This is the most blocking point, I don't know how to fix it, the values are weird. I remind that my wind data are between 0m/s and 30m/s. Moreover there is no forecasted curve that appears.

Here is my code, if you have time to look at it to help me I will be very grateful.

load data_vent

data_vent(1:3);

numChannels = size(data_vent{1},1);

figure

tiledlayout(3,1)

for i = 1:3

nexttile

stackedplot(data_vent{i}')

xlabel("Time Step")

end

numObservations = numel(data_vent);

idxTrain = 1:floor(0.9*numObservations);

idxTest = floor(0.9*numObservations)+1:numObservations;

dataTrain = data_vent(idxTrain);

dataTest = data_vent(idxTest);

for n = 1:numel(dataTrain)

X = dataTrain{n};

XTrain{n} = X(:,1:end-1);

TTrain{n} = X(:,2:end);

end

muX = mean(cat(1,XTrain{:}),1);

sigmaX = std(cat(1,XTrain{:}),0,1);

muT = mean(cat(1,TTrain{:}),1);

sigmaT = std(cat(1,TTrain{:}),0,1);

for n = 1:numel(XTrain)

XTrain{n} = (XTrain{n} - muX) ./ sigmaX;

TTrain{n} = (TTrain{n} - muT) ./ sigmaT;

end

layers = [

sequenceInputLayer(numChannels)

lstmLayer(128)

fullyConnectedLayer(numChannels)

regressionLayer];

options = trainingOptions("adam", ...

MaxEpochs=8760, ...

SequencePaddingDirection="left", ...

Shuffle="every-epoch", ...

Plots="training-progress", ...

Verbose=0);

net = trainNetwork(XTrain,TTrain,layers,options);

for n = 1:size(dataTest,1)

X = dataTest{n};

XTest{n} = (X(:,1:end-1) - muX) ./ sigmaX;

TTest{n} = (X(:,2:end) - muT) ./ sigmaT;

end

YTest = predict(net,XTest,SequencePaddingDirection="left");

for i = 1:size(YTest,1)

rmse(i) = sqrt(mean((YTest{i} - TTest{i}).^2,"all"));

end

figure

histogram(rmse)

xlabel("RMSE")

ylabel("Frequency")

mean(rmse)

idx = 2;

X = XTest{idx};

T = TTest{idx};

figure

stackedplot(X',DisplayLabels="Channel " + (1:numChannels))

xlabel("Time Step")

title("Test Observation " + idx)

net = resetState(net);

offset = 75;

[net,~] = predictAndUpdateState(net,X(:,1:offset));

numTimeSteps = size(X,2);

numPredictionTimeSteps = numTimeSteps - offset;

Y = zeros(numChannels,numPredictionTimeSteps);

for t = 1:numPredictionTimeSteps

Xt = X(:,offset+t);

[net,Y(:,t)] = predictAndUpdateState(net,Xt);

end

figure

t = tiledlayout(numChannels,1);

title(t,"Open Loop Forecasting")

for i = 1:numChannels

nexttile

plot(T(i,:))

hold on

plot(offset:numTimeSteps,[T(i,offset) Y(i,:)],'--')

ylabel("Channel " + i)

end

xlabel("Time Step")

nexttile(1)

legend(["Input" "Forecasted"])

net = resetState(net);

offset = size(X,2);

[net,Z] = predictAndUpdateState(net,X);

numPredictionTimeSteps = 2000;

Xt = Z(:,end);

Y = zeros(numChannels,numPredictionTimeSteps);

for t = 1:numPredictionTimeSteps

[net,Y(:,t)] = predictAndUpdateState(net,Xt);

Xt = Y(:,t);

end

numTimeSteps = offset + numPredictionTimeSteps;

figure

t = tiledlayout(numChannels,1);

title(t,"Closed Loop Forecasting")

for i = 1:numChannels

nexttile

plot(T(i,1:offset))

hold on

plot(offset:numTimeSteps,[T(i,offset) Y(i,:)],'--')

ylabel("Channel " + i)

end

xlabel("Time Step")

nexttile(1)

legend(["Input" "Forecasted"])