Comparison of Machine Learning Algorithms for the Power Consumption Prediction : - Case Study of Tetouan city –

Predicting electricity power consumption is an important task which provides intelligence to utilities and helps them to improve their systems’ performance in terms of productivity and effectiveness. Machine learning models are the most accurate models used in prediction. The goal of our study is to predict the electricity power consumption every 10 minutes, and/or every hour with the determining objective of which approach is the most successful. To this end, we will compare different types of machine learning models that recently have gained popularity: feedforward neural network with backpropagation algorithm, random forest, decision tree, and support vector machine for regression (SVR) with radial basis function kernel. The parameters associated with the comparative models are optimized based on Grid-search method in order to find the accurate performance. The dataset that is used in this comparative study is related to three different power distribution networks of Tetouan city which is located in north Morocco. The historical data used has been taken from Supervisory Control and Data Acquisition system (SCADA) every 10 minutes for the period between 2017-01-01 and 2017- 12-31. The results indicate that random forest model achieved smaller prediction errors compared to their counterparts.

[1]  Phuong H. Nguyen,et al.  A relevant data selection method for energy consumption prediction of low energy building based on support vector machine , 2017 .

[2]  M. Pal,et al.  Random forests for land cover classification , 2003, IGARSS 2003. 2003 IEEE International Geoscience and Remote Sensing Symposium. Proceedings (IEEE Cat. No.03CH37477).

[3]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[4]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[5]  Ali A. Minai,et al.  On the derivatives of the sigmoid , 1993, Neural Networks.

[6]  Kuriakose Athappilly,et al.  A comparative predictive analysis of neural networks (NNs), nonlinear regression and classification and regression tree (CART) models , 2005, Expert Syst. Appl..

[7]  Thilo Sauter,et al.  Short-term electricity consumption forecast with artificial neural networks — A case study of office buildings , 2017, 2017 IEEE Manchester PowerTech.

[8]  Jean-Michel Poggi,et al.  Variable Selection Using Random Forests The VSURF R package , 2014 .

[9]  Pınar Tüfekci,et al.  Prediction of full load electrical power output of a base load operated combined cycle power plant using machine learning methods , 2014 .

[10]  Alexander J. Smola,et al.  Support Vector Regression Machines , 1996, NIPS.

[11]  M. Ataei,et al.  Using a Combination of Genetic Algorithm and the Grid Search Method to Determine Optimum Cutoff Grades of Multiple Metal Deposits , 2004 .

[12]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[13]  Manuel Berenguel,et al.  A Comparison of Energy Consumption Prediction Models Based on Neural Networks of a Bioclimatic Building , 2016 .

[14]  Sepp Hochreiter,et al.  Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) , 2015, ICLR.

[15]  J. Ross Quinlan,et al.  Induction of Decision Trees , 1986, Machine Learning.

[16]  K. Gnana Sheela,et al.  Review on Methods to Fix Number of Hidden Neurons in Neural Networks , 2013 .

[17]  Matthew Scotch,et al.  Comparison of ARIMA and Random Forest time series models for prediction of avian influenza H5N1 outbreaks , 2014, BMC Bioinformatics.

[18]  Sepp Hochreiter,et al.  Self-Normalizing Neural Networks , 2017, NIPS.

[19]  Yacine Rezgui,et al.  Trees vs Neurons: Comparison between random forest and ANN for high-resolution prediction of building energy consumption , 2017 .

[20]  V. Rodriguez-Galiano,et al.  Machine learning predictive models for mineral prospectivity: an evaluation of neural networks, random forest, regression trees and support vector machines , 2015 .

[21]  Tong Zhang,et al.  Solving large scale linear prediction problems using stochastic gradient descent algorithms , 2004, ICML.

[22]  Quoc V. Le,et al.  Searching for Activation Functions , 2018, arXiv.

[23]  S. Karsoliya,et al.  Approximating Number of Hidden layer neurons in Multiple Hidden Layer BPNN Architecture , 2012 .

[24]  M. A. Rafe Biswas,et al.  Regression analysis for prediction of residential energy consumption , 2015 .

[25]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[26]  Rui Jiang,et al.  A random forest approach to the detection of epistatic interactions in case-control studies , 2009, BMC Bioinformatics.

[27]  Lynne E. Parker,et al.  Energy and Buildings , 2012 .

[28]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[29]  Tianqi Chen,et al.  Empirical Evaluation of Rectified Activations in Convolutional Network , 2015, ArXiv.

[30]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[31]  M. E. Günay,et al.  Forecasting annual gross electricity demand by artificial neural networks using predicted values of socio-economic indicators and climatic conditions: Case of Turkey , 2016 .