Power Consumption Prediction based on Infrastructure for Technical Educational Institutions
-
https://doi.org/10.14419/ijet.v7i4.6.29037
-
ClassifierAttributeEval feature selection, Support Vector Machine, Neural Network, Random Forest, Stochastic Gradient Descent, 10-fold cross validation sampling -
Abstract
Electricity plays a vital role in our daily routine activities. Particularly, educational institution power requirements may vary every day and the infrastructure of the building determines the amount of power required for a day. Hence advance prediction of power for every building in a university is very important for effective management of electricity during power crisis. In this paper, prediction of power consumption of each building in a university is carried out based on the infrastructure of a building. Feature engineering is carried out using ClassifierAttributeEval. This helps in reducing the size of the dataset as well as the computation time of prediction models. To forecast the energy production and usage in advance, Support Vector Machine (SVM), Neural Network (NN), Random Forest (RF) and Stochastic Gradient Descent (SGD) models are applied. From the experimental results and 10-fold cross validation sampling type , it is proved that SGD has better prediction accuracy when compared to SVM, NN and RF with Mean Square Error (MSE) of 1.102 , Root Mean Square Error (RMSE) of 1.050, Mean Absolute Error (MAE) of 0.613 and Coefficient of determination (R2) of 1.0000.
Â
-
References
[1] Jihoon Moon, Jinwoong Park, Sanghoon Jun, Forecasting power consumption for higher educational institutions based on machine learning,Sprnger (2017).
[2] Morton A., Nagle N., Piburn J., Stewart R.N., McManamay R, A Hybrid Dasymetric and Machine Learning Approach to High-Resolution Residential Electricity Consumption Modeling, Advances in Geographic Information Science, Springe(2017).
[3] Cyril Voyant, Gilles Notton, Soteris Kalogirou, Marie-Laure Nivet, Christophe Paoli, Fabrice Motte, Alexis Fouilloy, Machine Learning methods for solar radiation forecasting: a review, Renewable Energy (2016).
[4] Thanchanok Teeraratkul, Daniel O’Neill, and Sanjay Lal, Shape-Based Approach to Household Electric Load Curve Clustering and Prediction, IEEE Transactions on Smart Grid (2016).
[5] Daut, M.A.M., Building electrical energy consumption forecasting analysis using conventional and artificial intelligence methods: A review, Renewable and Sustainable Energy Reviews, Elsevier (2016).
[6] B. Yildiz, J.I. Bilbao, A.B. Sproul, A review and analysis of regression and machine learning models on commercial building electricity load forecasting, Renewable and Sustainable Energy Reviews (2017).
[7] Luis M. Candanedo, Véronique Feldheim, Dominique Deramaix, Data driven prediction models of energy use of appliances in a low-energy house, Energy and Buildings ,Elsevier (2017).
[8] Wang, Z., Renewable and Sustainable Energy Reviews, Elsevier (2017)
[9] Greig Paterson, Dejan Mumovic, Payel Das, and Judit Kimpian, Energy use predictions with machine learning during architectural concept design, Science and Technology for the Built Environment (2017).
[10] Pan Li, Baosen Zhang, Yang Weng, and Ram Rajagopal, A Sparse Linear Model and Significance Test for Individual Consumption Prediction, IEEE Transactions on Power Systems (2017).
[11] Chun-Nam Yu, Piotr Mirowski, Tin Kam Ho, A Sparse Coding Approach to Household Electricity Demand Forecasting in Smart Grids, IEEE transactions on smart grid(2016).
[12] Cyril Voyant, Fabrice Motte, Alexis Fouilloy, Gilles Notton, Christophe Paoli, Marie-Laure Nivet, Forecasting method for global radiation time series without training phase: comparison with other well-known prediction methodologies, Energy (2016).
[13] Oğuz KAYNAR, Halil ÖZEKİCİOĞLU, Ferhan DEMİRKOPARAN, Forecasting of Turkey’s Electricity Consumption with Support Vector Regression and Chaotic Particle Swarm Algorithm, Yönetim Bilimleri Dergisi/Journal of Administrative Sciences Cilt (2017).
[14] Oğuz KAYNAR, Halil ÖZEKİCİOĞLU, Ferhan DEMİRKOPARAN, Forecasting of Turkey’s Electricity Consumption with Support Vector Regression and Chaotic Particle Swarm Algorithm, Yönetim Bilimleri Dergisi/Journal of Administrative Sciences Cilt (2017).
[15] Wi YM, Kong S, Lee J, Joo SK ,Demand-side management program planning using stochastic, J Electr Eng Technol (2016)
[16] Son H, Kim C, Short-term forecasting of electricity demand for the residential sector using weather and social variables,Resources, conservation and recycling (2016).
[17] Grolinger K, L’Heureux A, Capretz MA, Seewald L, Energy forecasting for event venues: Big data and prediction accuracy. Energy Build 112:222–233(2016).
[18] Kyung-Bin Song, Young-sik Baek, Dug-Hun Hong,G.Jang, Short-term load forecasting for the holidays using fuzzy linear regression method,IEEE transactions on power systems(2005).
[19] A.D. Papalexopoulos, T.C.HesterBerg, A regression-based approach to short-term system load forecasting, IEEE transactions on power systems(1990).
[20] Seunghyeon Wang ,Hyeonyong Hae and Juhyung Kim, Development of Easily Accessible Electricity Consumption Model Using Open Data and GA-SVR,Energies (2018)
[21] Wu J, Wang J, Lu H, Dong Y, Lu X, Short term load forecasting technique based on the seasonal exponential adjustment method and the regression model, Energy Convers Manag (2013).
[22] Aowabin Rahman, Vivek Srikumar, Amanda D. Smith, Predicting electricity consumption for commercial and residential buildings using deep recurrent neural networks, Applied Energy (2018).
[23] A.S.Ahmad , M.Y.Hassan , M.P.Abdullah , H.A.Rahman , F.Hussin , H.Abdullah , R.Saidur, A review on applications of ANN and SVM for building electrical energy consumption forecasting, Renewable and sustianable Energy reviews (2015)
[24] M.E. Rinker, Sr. School of Construction Management, University of Florida, Gainesville, A review of artificial intelligence based building energy use prediction: Contrasting the capabilities of single and ensemble prediction models, Renewable and sustianable Energy reviews (2016)
[25] WILLIAM HEDÉN, Predicting Hourly Residential Energy Consumption using Random Forest and Support Vector Regression, TRITA-MAT-E 2016:20
[26] Selvam Nallathambi, Prediction of electricity consumption based on DT and RF: An application on USA country power consumption, IEEE Explore (2017).
[27] Muhammad WaseemAhmad, MonjurMourshed, YacineRezgui, Trees vs Neurons: Comparison between random forest and ANN for high-resolution prediction of building energy consumption, Energy and buildings (2017).
[28] David Rosenberg,Gradient and Stochastic Gradient Descent, New York University(2017).
[29] J, ustin Sirignano, Konstantinos SpiliopoulosStochastic Gradient Descent in Continuous Time: A Central Limit Theorem, Machine Learning (stat.ML),(2017).
[30] Ming Jin, Lin Zhang, Costas J. Spanos, Power Prediction through Energy Consumption Pattern Recognition for Smart Buildings, IEEE Xplore(2015).
[31] Khuram Pervez Amber, Muhammad Waqar Aslam 2, Anzar Mahmood, Anila Kousar, Muhammad Yamin Younis , Bilal Akbar, Ghulam Qadar Chaudhary and Syed Kashif HussainEnergy Consumption Forecasting for University Sector Buildings, Energies (2017).
[32] Evlauating Machine learning models, Jose Hernadas Orello, universitat politecnice vaencia
-
Downloads
-
How to Cite
Poonkavithai Kalamegam, D., & Dhaya C, D. (2018). Power Consumption Prediction based on Infrastructure for Technical Educational Institutions. International Journal of Engineering & Technology, 7(4.6), 590-593. https://doi.org/10.14419/ijet.v7i4.6.29037Received date: 2019-04-27
Accepted date: 2019-04-27