電能的發展與使用，給予人們便利舒適的生活，然為提升舒適度而大量耗費不必要之能源，使能源危機與全球暖化等議題出現，並已危害部分生態圈發展，全球正積極推動節能減碳以緩解此症狀。住宅用電佔比台灣總用電約20%，其用電彈性相較工業、服務業等部門彈性更大，表節能潛力高。希冀藉提供實際及未來用電資訊，輔佐政府制訂節能政策方向；此外，政府所營運之台灣電力公司與綠能產業，需搭配智慧電網得知各地用電狀態，以利配電，而民眾可藉此平台監督節能計畫落實成果。有鑑於此，本研究望建立一自動化網路系統平台，提供各縣市住宅用電資訊。經文獻回顧，本文以縣市為蒐集基本單位，以月份為時間基本單位，資料集共含20個縣市，總長度為72個月，每一筆資料含17個影響住宅用電因子與住宅總用電量。應用資料探勘技術以預測未來住宅用電需求，此技術包含(1)線性回歸模型；(2)分類回歸樹；(3)支援向量基；(4)人工神經網路；(5)表決法；(6)重複採樣平均表決法，經交叉驗證得出Bagging-ANNs表現最佳，後續加入自然啟發式優化法PSO提高模型精準度與穩定性，建立混合模型PSO-Bagging-ANNs，其預測值與實際值間相關係數(correlation coefficient, R)為0.999、絕對誤差(mean absolute error, MAE)為2,059,993kWh、方均根誤差(root mean square error, RMSE)為5,311,887kWh、平均絕對值誤差率(mean absolute percentage error, MAPE)為1.17%。全台住宅每月總用電平均約為2億kWh，絕對誤差約為0.02億kWh，精準率可達1%。各評估指標顯示，此模型精準度優良，可提供有效資訊以供參考。自動化系統網路平台為基於此模型並結合自動索引程式建立，而後加入自動化排程，茲以提供各縣市每月住宅用電資訊。

The development and use of electrical energy give people a convenient and comfortable life. However, people consume a large amount of unnecessary energy to increase comfort, creating an energy crisis and global warming, and damaging some ecological circles. The world is actively promoting energy saving and carbon reduction to alleviate this problem. Residential electricity comprises about 20% of Taiwan's total electricity consumption, and has greater electric elasticity than electricity for industrial and business uses, representing high energy-saving potential. This study aims to assist government to formulate the direction of energy conservation policies. Additionally, the Taiwan power company and green energy industry, which are both operated by government, need to utilize the smart grid to realize the state of electricity consumption, in order to facilitate distribution. The public can use this platform to supervise the implementation of energy conservation plans. Accordingly, this investigation establishes an automated network system platform, providing information on residential electricity consumption in each county and city. After literature review, this collected data from 20 counties and cities each month over a period of 72 months. The data included 17 influence factors with residential electricity consumption during a month as a dependent variable. Data mining technology was employed to forecast future residential electricity demand. The forecasting systems adopted in this work were (1) linear regression, (2) classification and regression tree, (3) support vector machine/regression, (4) artificial neural networks, (5) Voting method and (6) Bagging method. Bagging-ANNs achieved the best performance among the tested models. A natural-inspired optimization method, namely PSO, was then applied to enhance the accuracy as well as stability of Bagging-ANNs, to develop a hybrid ensemble model, PSO-Bagging-ANNs. The correlation coefficient between prediction values and actual values was 0.99; the mean absolute error was 2,059,993kWh; the root mean square error was 5,311,887 kWh, and the mean absolute percentage error was 1.17%. The average of monthly electricity consumption in Taiwan is about 200,000,000kWh. The MAE is about 20,000kWh. The accuracy rate of the model is up to 1%. Evaluation indicators show that the proposed model is accurate, and provides effective information for reference. An automatic web-based system based on this model and combined with a web crawler and scheduled to run automatically to provide information on monthly residential electricity consumption in each county and city.

[1] P. Nejat, F. Jomehzadeh, M.M. Taheri, M. Gohari, M.Z. Abd. Majid, A global review of energy consumption, CO2 emissions and policy in the residential sector (with an overview of the top ten CO2 emitting countries), Renewable and Sustainable Energy Reviews 43 (2015) 843-862.
[2] W.-H. Huang, The determinants of household electricity consumption in Taiwan: Evidence from quantile regression, Energy 87 (2015) 120-133.
[3] N.S.M. Nazar, M.P. Abdullah, M.Y. Hassan, F. Hussin, Time-based electricity pricing for Demand Response implementation in monopolized electricity market, 2012 IEEE Student Conference on Research and Development (SCOReD), 2012, pp. 178-181.
[4] H. Li, X. Zhao, Y. Yu, T. Wu, Y. Qi, China's numerical management system for reducing national energy intensity, Energy Policy 94 (2016) 64-76.
[5] S. Papantoniou, D. Kolokotsa, K. Kalaitzakis, Building optimization and control algorithms implemented in existing BEMS using a web based energy management and control system, Energy and Buildings 98 (2015) 45-55.
[6] M. Molina-Solana, M. Ros, M.D. Ruiz, J. Gómez-Romero, M.J. Martin-Bautista, Data science for building energy management: A review, Renewable and Sustainable Energy Reviews 70 (2017) 598-609.
[7] R. Nesbakken, Price sensitivity of residential energy consumption in Norway, Energy Economics 21 (6) (1999) 493-515.
[8] J. Ahn, S. Cho, Anti-logic or common sense that can hinder machine’s energy performance: Energy and comfort control models based on artificial intelligence responding to abnormal indoor environments, Applied Energy 204 (2017) 117-130.
[9] A. Ananieva, B. Onykiy, A. Artamonov, K. Ionkina, I. Galin, D. Kshnyakov, Thematic Thesauruses in Agent Technologies for Scientific and Technical Information Search, Procedia Computer Science 88 (2016) 493-498.
[10] A. Vijayaraghavan, D. Dornfeld, Automated energy monitoring of machine tools, CIRP Annals 59 (1) (2010) 21-24.
[11] M.-F. Hung, T.-H. Huang, Dynamic demand for residential electricity in Taiwan under seasonality and increasing-block pricing, Energy Economics 48 (2015) 168-177.
[12] J. Jazaeri, R.L. Gordon, T. Alpcan, Influence of building envelopes, climates, and occupancy patterns on residential HVAC demand, Journal of Building Engineering 22 (2019) 33-47.
[13] H. Son, C. Kim, Short-term forecasting of electricity demand for the residential sector using weather and social variables, Resources, Conservation and Recycling 123 (2017) 200-207.
[14] H. Estiri, Building and household X-factors and energy consumption at the residential sector: A structural equation analysis of the effects of household and building characteristics on the annual energy consumption of US residential buildings, Energy Economics 43 (2014) 178-184.
[15] Z. Guo, K. Zhou, C. Zhang, X. Lu, W. Chen, S. Yang, Residential electricity consumption behavior: Influencing factors, related theories and intervention strategies, Renewable and Sustainable Energy Reviews 81 (2018) 399-412.
[16] S. Karatasou, M. Laskari, M. Santamouris, Determinants of high electricity use and high energy consumption for space and water heating in European social housing: Socio-demographic and building characteristics, Energy and Buildings 170 (2018) 107-114.
[17] H. Doukas, K.D. Patlitzianas, K. Iatropoulos, J. Psarras, Intelligent building energy management system using rule sets, Building and Environment 42 (10) (2007) 3562-3569.
[18] S.K. Jha, J. Bilalovic, A. Jha, N. Patel, H. Zhang, Renewable energy: Present research and future scope of Artificial Intelligence, Renewable and Sustainable Energy Reviews 77 (2017) 297-317.
[19] R.A. Begum, K. Sohag, S.M.S. Abdullah, M. Jaafar, CO2 emissions, energy consumption, economic and population growth in Malaysia, Renewable and Sustainable Energy Reviews 41 (2015) 594-601.
[20] K. Amasyali, N.M. El-Gohary, A review of data-driven building energy consumption prediction studies, Renewable and Sustainable Energy Reviews 81 (2018) 1192-1205.
[21] A. Zendehboudi, M.A. Baseer, R. Saidur, Application of support vector machine models for forecasting solar and wind energy resources: A review, Journal of Cleaner Production 199 (2018) 272-285.
[22] A. Genender-Feltheimer, Visualizing High Dimensional and Big Data, Procedia Computer Science 140 (2018) 112-121.
[23] Y. Wei, X. Zhang, Y. Shi, L. Xia, S. Pan, J. Wu, M. Han, X. Zhao, A review of data-driven approaches for prediction and classification of building energy consumption, Renewable and Sustainable Energy Reviews 82 (2018) 1027-1047.
[24] Z. Wang, R.S. Srinivasan, A review of artificial intelligence based building energy use prediction: Contrasting the capabilities of single and ensemble prediction models, Renewable and Sustainable Energy Reviews 75 (2017) 796-808.
[25] K.L. Ku, J.S. Liaw, M.Y. Tsai, T.S. Liu, Automatic Control System for Thermal Comfort Based on Predicted Mean Vote and Energy Saving, IEEE Transactions on Automation Science and Engineering 12 (1) (2015) 378-383.
[26] A.R. Khan, S. Razzaq, T. Alquthami, M.R. Moghal, A. Amin, A. Mahmood, Day ahead load forecasting for IESCO using Artificial Neural Network and Bagged Regression Tree, 2018 1st International Conference on Power, Energy and Smart Grid (ICPESG), 2018, pp. 1-6.
[27] A.L.I. Oliveira, P.L. Braga, R.M.F. Lima, M.L. Cornélio, GA-based method for feature selection and parameters optimization for machine learning regression applied to software effort estimation, Information and Software Technology 52 (11) (2010) 1155-1166.
[28] Y. Song, Z. Chen, Z. Yuan, New Chaotic PSO-Based Neural Network Predictive Control for Nonlinear Process, IEEE Transactions on Neural Networks 18 (2) (2007) 595-601.
[29] S.M. Zahraee, M. Khalaji Assadi, R. Saidur, Application of Artificial Intelligence Methods for Hybrid Energy System Optimization, Renewable and Sustainable Energy Reviews 66 (2016) 617-630.
[30] S. Wang, S. Lin, J. Li, Exploring the effects of non-cognitive and emotional factors on household electricity saving behavior, Energy Policy 115 (2018) 171-180.
[31] K.-T. Huang, R.-L. Hwang, Future trends of residential building cooling energy and passive adaptation measures to counteract climate change: The case of Taiwan, Applied Energy 184 (2016) 1230-1240.
[32] S.-H. Hong, S.-K. Lee, J.-H. Yu, Automated management of green building material information using web crawling and ontology, Automation in Construction 102 (2019) 230-244.
[33] S. Khalil, M. Fakir, RCrawler: An R package for parallel web crawling and scraping, SoftwareX 6 (2017) 98-106.
[34] T. Bodnar, M.L. Dering, C. Tucker, K.M. Hopkinson, Using Large-Scale Social Media Networks as a Scalable Sensing System for Modeling Real-Time Energy Utilization Patterns, IEEE Transactions on Systems, Man, and Cybernetics: Systems 47 (10) (2017) 2627-2640.
[35] S. Jangiti, V.S.S. Sriram, R. Logesh, The role of cloud computing infrastructure elasticity in energy efficient management of datacenters, 2017 IEEE International Conference on Power, Control, Signals and Instrumentation Engineering (ICPCSI), 2017, pp. 758-763.
[36] V. Tanasiev, H. Necula, G. Darie, A. Badea, Web service-based monitoring system for smart management of the buildings, 2016 International Conference and Exposition on Electrical and Power Engineering (EPE), 2016, pp. 025-030.
[37] J. Kohlbrecher, S. Hakobyan, J. Pickert, U. Grossmann, Visualizing energy information on mobile devices, Proceedings of the 6th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems, Vol. 2, 2011, pp. 817-822.
[38] L. Liu, T. Zhu, Y. Pan, H. Wang, Multiple energy complementation based on distributed energy systems – Case study of Chongming county, China, Applied Energy 192 (2017) 329-336.
[39] F. Shariff, N.A. Rahim, W.P. Hew, Zigbee-based data acquisition system for online monitoring of grid-connected photovoltaic system, Expert Systems with Applications 42 (3) (2015) 1730-1742.
[40] M. Alaa, A.A. Zaidan, B.B. Zaidan, M. Talal, M.L.M. Kiah, A review of smart home applications based on Internet of Things, Journal of Network and Computer Applications 97 (2017) 48-65.
[41] G. Cao, L. Wu, Support vector regression with fruit fly optimization algorithm for seasonal electricity consumption forecasting, Energy 115 (2016) 734-745.
[42] A.K. Yadav, S.S. Chandel, Identification of relevant input variables for prediction of 1-minute time-step photovoltaic module power using Artificial Neural Network and Multiple Linear Regression Models, Renewable and Sustainable Energy Reviews 77 (2017) 955-969.
[43] Y. Xia, C. Liu, Y. Li, N. Liu, A boosted decision tree approach using Bayesian hyper-parameter optimization for credit scoring, Expert Systems with Applications 78 (2017) 225-241.
[44] A.J. Smola, B. Schölkopf, A tutorial on support vector regression, Statistics and Computing 14 (3) (2004) 199-222.
[45] J. Eynard, S. Grieu, M. Polit, Wavelet-based multi-resolution analysis and artificial neural networks for forecasting temperature and thermal power consumption, Engineering Applications of Artificial Intelligence 24 (3) (2011) 501-516.
[46] R. Pino, J. Parreno, A. Gomez, P. Priore, Forecasting next-day price of electricity in the Spanish energy market using artificial neural networks, Engineering Applications of Artificial Intelligence 21 (1) (2008) 53-62.
[47] J. Wang, H. Peng, W. Yu, J. Ming, M.J. Pérez-Jiménez, C. Tao, X. Huang, Interval-valued fuzzy spiking neural P systems for fault diagnosis of power transmission networks, Engineering Applications of Artificial Intelligence 82 (2019) 102-109.
[48] M. Sabzevari, G. Martínez-Muñoz, A. Suárez, Vote-boosting ensembles, Pattern Recognition 83 (2018) 119-133.
[49] K. Szafranek, Bagged neural networks for forecasting Polish (low) inflation, International Journal of Forecasting (2019).
[50] E.M. de Oliveira, F.L. Cyrino Oliveira, Forecasting mid-long term electric energy consumption through bagging ARIMA and exponential smoothing methods, Energy 144 (2018) 776-788.
[51] S. Ho Park, K. Uhn Ahn, S. Hwang, S. Choi, C.-S. Park, Machine learning vs. hybrid machine learning model for optimal operation of a chiller, 2018.
[52] M. Talaat, M.H. Gobran, M. Wasfi, A hybrid model of an artificial neural network with thermodynamic model for system diagnosis of electrical power plant gas turbine, Engineering Applications of Artificial Intelligence 68 (2018) 222-235.
[53] J. Kennedy, R. Eberhart, Particle swarm optimization, Proceedings of ICNN'95 - International Conference on Neural Networks, Vol. 4, 1995, pp. 1942-1948 vol.1944.
[54] H. Yang, M. Gunzburger, L. Ju, Fast spherical centroidal Voronoi mesh generation: A Lloyd-preconditioned LBFGS method in parallel, Journal of Computational Physics 367 (2018) 235-252.
[55] T. Nguyen-ky, S. Mushtaq, A. Loch, K. Reardon-Smith, D.-A. An-Vo, D. Ngo-Cong, T. Tran-Cong, Predicting water allocation trade prices using a hybrid Artificial Neural Network-Bayesian modelling approach, Journal of Hydrology 567 (2018) 781-791.
[56] T.H. Nguyen, D. Nong, K. Paustian, Surrogate-based multi-objective optimization of management options for agricultural landscapes using artificial neural networks, Ecological Modelling 400 (2019) 1-13.
[57] M. Hasanipanah, M. Noorian-Bidgoli, D. Jahed Armaghani, H. Khamesi, Feasibility of PSO-ANN model for predicting surface settlement caused by tunneling, Engineering with Computers 32 (4) (2016) 705-715.
[58] Z. Zhan, J. Zhang, Y. Li, H.S. Chung, Adaptive Particle Swarm Optimization, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics) 39 (6) (2009) 1362-1381.
[59] G. Oğcu, O.F. Demirel, S. Zaim, Forecasting Electricity Consumption with Neural Networks and Support Vector Regression, Procedia - Social and Behavioral Sciences 58 (2012) 1576-1585.
[60] P.-C. Chang, C.-Y. Fan, J.-J. Lin, Monthly electricity demand forecasting based on a weighted evolving fuzzy neural network approach, International Journal of Electrical Power & Energy Systems 33 (1) (2011) 17-27.
[61] H.-T. Pao, Comparing linear and nonlinear forecasts for Taiwan's electricity consumption, Energy 31 (12) (2006) 2129-2141.
[62] H.T. Pao, Forecasting energy consumption in Taiwan using hybrid nonlinear models, Energy 34 (10) (2009) 1438-1446.