Short-Term Energy Consumption Prediction in Korean Residential Buildings Using Optimized Multi-Layer Perceptron
Keywords:
Short-term energy consumption, hourly prediction, multi-layer perceptron, residential buildingsAbstract
For the designing and management of energy production and storage systems, the prediction of household short-term energy consumption is of vital importance. In this paper, we present the prediction methodology for short-term energy consumption using optimized multi-layer perceptron. A total of 20 models of multi-layer perceptrons with different architectures were developed for hourly energy consumption prediction. For the determination of best combinations of learning algorithms, hidden layers’ transfer functions and output layer functions, different types of training algorithms and hidden layer and output layer functions were considered. Two main training algorithms namely scaled conjugate gradient, and Levenberg-Marquardt back propagation algorithms were used for training. In the hidden layer, tangent and logarithmic sigmoid equations were used as activation functions and linear, logarithmic sigmoid and tangent sigmoid were used as output functions. The evaluation of performance of models was based on mean absolute error (MAE), mean square error (MSE) and root mean square error (RMSE).The performance and feasibility of the proposed model have been tested on real data of some residential buildings of Seoul, Republic of Korea for a specific period of time. We have total of 14260 (20 Apartments x 31 Days x 23 Hours) samples’ data which was divided into 70% (9982 samples) training and 30% (4278 samples) testing.
References
ÖZBAY, Y. K. & TEZEL, G. L. A new method for classification of ECG arrhythmias using neural network with adaptive activation function. Digital Signal Processing, 20, 1040-1049.
ALI, S. & KIM, D.-H. Effective and comfortable power control model using Kalman filter for building energy management. Wireless personal communications, 73, 1439-1453.
ALI, S. & KIM, D.-H. Optimized Power Control Methodology Using Genetic Algorithm. Wireless personal communications, 1-13.
AMIN-NASERI, M. & SOROUSH, A.2008 Combined use of unsupervised and supervised learning for daily peak load forecasting. Energy conversion and management, 49, 1302-1308.
ÅŽAHIN, M. Comparison of modelling ANN and ELM to estimate solar radiation over Turkey using NOAA satellite data. International journal of remote sensing, 34, 7508-7533.
ÅŽAHIN, M. Modelling of air temperature using remote sensing and artificial neural network in Turkey. Advances in Space Research, 50, 973-985.
BAKIRTZIS, A., THEOCHARIS, J., KIARTZIS, S. & SATSIOS, K.1995 Short term load forecasting using fuzzy neural networks. Power Systems, IEEE Transactions on, 10, 1518-1524.
CARPINTEIRO, O. A., REIS, A. J. & DA SILVA, A. P.2004 A hierarchical neural model in short-term load forecasting. Applied Soft Computing, 4, 405-412.
CHOW, T., ZHANG, G., LIN, Z. & SONG, C.2002 Global optimization of absorption chiller system by genetic algorithm and neural network. Energy and buildings, 34, 103-109.
EL-TELBANY, M. & EL-KARMI, F.2008 Short-term forecasting of Jordanian electricity demand using particle swarm optimization. Electric Power Systems Research, 78, 425-433.
GROSS, G. & GALIANA, F. D.1987 Short-term load forecasting. Proceedings of the IEEE, 75, 1558-1573.
HARRINGTON, P. D. B.1993 Sigmoid transfer functions in backpropagation neural networks. Analytical Chemistry, 65, 2167-2168.
HIPPERT, H. S., PEDREIRA, C. E. & SOUZA, R. C.2001 Neural networks for short-term load forecasting: A review and evaluation. Power Systems, IEEE Transactions on, 16, 44-55.
IRISARRI, G., WIDERGREN, S. & YEHSAKUL, P.1982 On-line load forecasting for energy control center application. IEEE Power Engineering Review, 1, 23.
KARLIK, B. & OLGAC, A. V. Performance analysis of various activation functions in generalized MLP architectures of neural networks. Int. J. Artificial Intell. Expert Syst, 1, 111-122.
KIARTZIS, S., BAKIRTZIS, A., THEOCHARIS, J. & TSAGAS, G. 2000 A fuzzy expert system for peak load forecasting. Application to the Greek power system, IEEE
KUMAR, M., RAGHUWANSHI, N., SINGH, R., WALLENDER, W. & PRUITT, W.2002 Estimating evapotranspiration using artificial neural network. Journal of Irrigation and Drainage Engineering, 128, 224-233.
LAURET, P., FOCK, E., RANDRIANARIVONY, R. N. & MANICOM-RAMSAMY, J.-F. O.2008 Bayesian neural network approach to short time load forecasting. Energy conversion and management, 49, 1156-1166.
MCCULLOCH, W. S. & PITTS, W.1943 A logical calculus of the ideas immanent in nervous activity. The bulletin of mathematical biophysics, 5, 115-133.
MIRANDA, V. & MONTEIRO, C. U. 2000 Fuzzy inference in spatial load forecasting, IEEE
MM., B. 1986A short guide to electric utility load forecasting
MORID, S., SMAKHTIN, V. & BAGHERZADEH, K.2007 Drought forecasting using artificial neural networks and time series of drought indices. International Journal of Climatology, 27, 2103-2111.
MOUSTRIS, K. P., LARISSI, I. K., NASTOS, P. T. & PALIATSOS, A. G. Precipitation forecast using artificial neural networks in specific regions of Greece. Water resources management, 25, 1979-1993.
NENGLING, T., STENZEL, J. R. & HONGXIAO, W.2006 Techniques of applying wavelet transform into combined model for short-term load forecasting. Electric Power Systems Research, 76, 525-533.
SöZEN, A. & AKçAYOL, M. A.2004 Modelling (using artificial neural-networks) the performance parameters of a solar-driven ejector-absorption cycle. Applied Energy, 79, 309-325.
SAINI, L. M.2008 Peak load forecasting using Bayesian regularization, Resilient and adaptive backpropagation learning based artificial neural networks. Electric Power Systems Research, 78, 1302-1310.
SRINIVASAN, D., CHANG, C. & LIEW, A.1995 Demand forecasting using fuzzy neural computation, with special emphasis on weekend and public holiday forecasting. Power Systems, IEEE Transactions on, 10, 1897-1903.
VOGL, T. P., MANGIS, J., RIGLER, A., ZINK, W. & ALKON, D.1988 Accelerating the convergence of the back-propagation method. Biological cybernetics, 59, 257-263.
WASU, M. R. V. AN APPROACH TO ELECTRICITY LOAD FORECASTING AND TECHNIQUES: A REVIEW.
YAO, S., SONG, Y., ZHANG, L. & CHENG, X.2000 Wavelet transform and neural networks for short-term electrical load forecasting. Energy conversion and management, 41, 1975-1988.
