Greek long-term energy consumption prediction using artificial neural networks

TLDR: The proposed approach can be useful in the effective implementation of energy policies, since accurate predictions of energy consumption affect the capital investment, the environmental quality, the revenue analysis, the market research management, while conserve at the same time the supply security.

About: This article is published in Energy.The article was published on 2010-02-01 and is currently open access. It has received 386 citations till now. The article focuses on the topics: Energy consumption & Energy policy.

Figures

Table 2 Designed MLP ANN model architectures

Fig. 4 Comparison of the predicted with the use of the ANN model, the and regression model and the support vector machine model Greek energy consumption with the actual one.

Table 1 MLP ANN input and output variables

Fig. 2 The Greek final energy consumption and gross domestic product from 1992 to 2008.

Table 4 Results of the proposed MLP ANN model

Fig. 3 The Greek installed power capacity and yearly per resident electricity consumption from 1992 to 2008.

Frequently asked questions

Q1. What are the contributions in this paper?

In this paper artificial neural networks ( ANN ) are addressed in order the Greek long-term energy consumption to be predicted. Furthermore it constitutes an accurate tool for the Greek long-term energy consumption prediction problem, which up today has not been faced effectively. 

Q2. What is the current work on energy consumption in Greece?

In the current work the Greek long-term energy consumption for the years ahead is predicted, exploiting ANN computational speed, ability to handle complex non-linear functions, robustness and great efficiency even in cases where full information for the studied problem is absent. 

Q3. How many epochs were used to train the ANN model?

The training process was repeated until a root mean square error between the actual output and the desired output reached the goal of 1 % or a maximum number of epochs (the presentation of the set of training data to the network and the calculation of new weights and biases) it was set to 15,000, was accomplished. 

Q4. What is the goal of this study?

The goal of this study is to develop an artificial neural network architecture capable to predict the Greek long-term energy consumption. 

Q5. What is the main purpose of the proposed approach?

The proposed approach can be very useful in the effective implementation of energy policies since accurate predictions of energy consumption affect the capital investment, the environmental quality, the revenue analysis, the market research management, while conserve at the same time the supply security. 

Q6. How many random samples were removed from the training set?

In each training iteration 20 % of random samples were removed from the training set and validation error was calculated for these data. 

Q7. What are the main purposes of long-term energy consumption predictions?

Long-term energy consumption predictions are essential and are required in the studies of capacity expansion, energy supply strategy, capital investment, revenueanalysis and market research management. 

Q8. How much energy has been consumed in Greece in the last 16 years?

In Greece the final energy consumption which includes all energy delivered to the final consumer’s door (industry, transport, households and other sectors) for all energy uses, has increased the last 16 years more than 60 %, from 14,079,000 Tones of Oil Equivalent (TOE) in 1992 to 22,552,000 TOE in 2007 following an average annual increase of approximately 4.1 % [17]. 

Q9. What is the next step in the learning algorithm?

Once the training process is completed and the weights and bias of each neuron in the neural network is set, the next step is to check the results of training by seeing how the network performs in situations encountered in training and in others not previously encountered. 

Q10. What is the definition of an artificial neural network?

An artificial neural network consists of a number of very simple and highly interconnected processors, called neurons, which are analogous to the biological neurons in the brain. 

Q11. What is the common method for normalizing the data?

The most commonly employed method for normalization involves mapping the data linearly over a specified range, whereby each value of a variable x is transformed as follows: minminminmaxminmax xxx xxxx x min minmax minmax min minmax minmax x xx xx xx xx xxoffsetxfactor (1)where maxx and minx are the expected maximum and minimum values of the concerned variable. 

Q12. What was the main characteristic of the MLP ANN model?

This MLP ANN model had the following characteristics: 2 hidden layers, with 20 and 17 neurons in each one of them, Levenberg-Marquardt backpropagation learning algorithm and logarithmic sigmoid transfer function. 

Q13. What is the main reason why the Greek energy consumption has increased?

Recent studies have concluded that the sensitivity of energy consumption to temperature has increased in the recent period [20, 21]. 

Q14. What is the main reason why the Greeks are interested in energy related questions?

Given the concern about global warming, these findings support the renewed interest in energy related questions by the policymakers. 

Q15. How much energy will be consumed in Greece?

According to the American Energy Information Administration (AEIA) and to the International Energy Agency (IEA), the world-wide energy consumption will on average continue to increase by 2.5 % per year and this forms a modest prediction. 

Q16. What is the percentage error between recorded final energy consumption and ANN computed final energy consumption given?

The percentage error between recorded final energy consumption and ANN computed final energy consumption given by (6) is approximately 2 % something which also clearly implies that the proposed ANN model is well working and has an acceptable accuracy.