A hybrid approach towards improved artificial neural network training for short-term load forecasting

The power of artificial neural networks to form predictive models for phenomenon that exhibit non-linear relationships is a given fact. Despite this advantage, artificial neural networks are known to suffer drawbacks such as long training times and computational intensity. The researchers propose a two-tiered approach to enhance the learning performance of artificial neural networks for phenomenon with time series where data exhibits predictable changes that occur every calendar year. This paper focuses on the initial results of the first phase of the proposed algorithm which incorporates clustering and classification prior to application of the backpropagation algorithm. The 2016--2017 zonal load data of France is used as the data set. K-means is chosen as the clustering algorithm and a comparison is made between Naïve Bayes and k-Nearest Neighbors to determine the better classifier for this data set. The initial results show that electrical load behavior is not necessarily reflective of calendar clustering even without using the min-max temperature recorded during the inclusive months. Simulating the day-type classification process using one cluster, initial results show that the k-nearest neighbors outperforms the Naïve Bayes classifier for this data set and that the best feature to be used for classification into day type is the daily min-max load. These classified load data is expected to reduce training time and improve the overall performance of short-term load demand predictive models in a future paper.

[1]  Deepak Kanojia,et al.  Comparison of Naive Basian and K-NN Classifier , 2013 .

[2]  Somboon Nuchprayoon.  Electricity load classification using K-means clustering algorithm , 2014 .

[3]  Morteza Saberi,et al.  Improved estimation of electricity demand function by using of artificial neural network, principal component analysis and data envelopment analysis , 2013, Comput. Ind. Eng..

[4]  Ikhsan Siregar,et al.  Optimization backpropagation algorithm based on Nguyen-Widrom adaptive weight and adaptive learning rate , 2017, 2017 4th International Conference on Industrial Engineering and Applications (ICIEA).

[5]  Ivan Nunes da Silva,et al.  Artificial Neural Networks , 2017 .

[6]  Uwe Aickelin,et al.  The Application of a Data Mining Framework to Energy Usage Profiling in Domestic Residences Using UK Data , 2011, ArXiv.

[7]  Yung-Cheol Byun,et al.  An Adaptive Stopping Criterion for Backpropagation Learning in Feedforward Neural Network , 2014, MUE 2014.

[8]  Olaf Wolkenhauer,et al.  Naïve Bayes classifier predicts functional microRNA target interactions in colorectal cancer. , 2015, Molecular bioSystems.

[9]  Nazri Mohd Nawi,et al.  The Effect of Data Pre-processing on Optimized Training of Artificial Neural Networks , 2013 .

[10]  Jaime Lloret,et al.  Artificial neural networks for short-term load forecasting in microgrids environment , 2014 .

[11]  J. J. Montaño Moreno,et al.  Artificial neural networks applied to forecasting time series. , 2011, Psicothema.

[12]  M.Y. Hassan,et al.  Short term load forecasting using data mining technique , 2008, 2008 IEEE 2nd International Power and Energy Conference.

[13]  Bobby D. Gerardo,et al.  Electric Load Consumption using Neural Networks , 2017 .

[14]  Yongbo Yuan,et al.  Improved Neural Networks with Random Weights for Short-Term Load Forecasting , 2015, PloS one.

[15]  Karin Kandananond.  Forecasting Electricity Demand in Thailand with an Artificial Neural Network Approach , 2011 .

[16]  Vom Fachbereich,et al.  Power System Short-term Load Forecasting , 2006 .

[17]  Celso André R. de Sousa,et al.  An overview on weight initialization methods for feedforward neural networks , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

[18]  Yannig Goude,et al.  Modeling and Forecasting Daily Electricity Load Curves: A Hybrid Approach , 2013, 1611.08632.

[19]  E. Crisostomi,et al.  Comparison and clustering analysis of the daily electrical load in eight European countries , 2016 .

[20]  Elmer Maravillas,et al.  Dynamic forecasting of electric load consumption using adaptive multilayer perceptron(AMLP) , 2014, 2014 International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment and Management (HNICEM).

[21]  Nadali Mahmoudi,et al.  Queensland load profiling by using clustering techniques , 2014, 2014 Australasian Universities Power Engineering Conference (AUPEC).

[22]  Chao-Rong Chen,et al.  k-Nearest Neighbor Neural Network Models for Very Short-Term Global Solar Irradiance Forecasting Based on Meteorological Data , 2017 .

[23]  June Ho Park,et al.  Comparative Study of Short-Term Electric Load Forecasting , 2014, 2014 5th International Conference on Intelligent Systems, Modelling and Simulation.

[24]  Iqbal H. Sarker,et al.  An Improved Naive Bayes Classifier-based Noise Detection Technique for Classifying User Phone Call Behavior , 2017, AusDM.

[25]  Pietro Ferraro,et al.  Clustering analysis of the electrical load in european countries , 2015, 2015 International Joint Conference on Neural Networks (IJCNN).

[26]  Ignacio Rojas,et al.  Bioinformatics and Biomedical Engineering , 2015, Lecture Notes in Computer Science.

[27]  Agus Zainal Arifin,et al.  Indonesian News Classification Using Naïve Bayes and Two-Phase Feature Selection Model , 2017 .

[28]  Bobby D. Gerardo,et al.  An Improved Data Mining Mechanism Based on PCA-GA for Agricultural Crops Characterization , 2014 .