現今社會產業發展迅速，導致能源需求擴增。為減少地球能源消耗，各國皆著手擘劃能源轉型策略，臺灣政府能源單位亦積極提出整合能源節約及智慧系統，希冀透過智慧電網落實配電及用電管理，茲以提升能源使用效率，確保電力供應的穩定性，達到中長期能源供需平衡。而住宅建築能耗佔臺灣總電能消耗近20%，且易受其他因素影響、變動性高。現今深度學習技術發展完善，透過影像辨識技術可建構高精確度的能耗預測模型。本研究根據回顧文獻內容，蒐集全台20個縣市六年的用電量，以及17個影響住宅用電特徵因子的原始數值資料。在資料預處理過程中，先將原始時序性能源歷史資料結合特徵因子，轉換成為2維影像圖，接續應用深度卷積神經網路技術(CNN)預測未來用電量。為選定深度學習模型之最佳超參數，則採一新穎開發之仿生優化演算法-水母演算法(Jellyfish, JS)進行搜尋，以提高模型預測精確度與穩定性。最後建構之混合模型(JS-CNN)以交叉驗證法及多種性能指標評估模型之績效，獲得最佳電量預測模型。研發模式可作為能源趨勢預測工具，及時提供臺灣各縣市總用電量態樣，探討區域用電行為的合理性；對於管理單位可做為地區性配電規劃依據，降低非必要的能源傳輸及預儲耗損。

The rapid development of various industries in modern society has led to an increase in energy demand. Therefore, countries plan energy conversion strategies in order to decrease worldwide energy consumption. To achieve adequate medium-term and long-term energy supply to meet demand, the Taiwanese government has proposed to integrate energy-saving and smart system planning through a smart grid program and electricity management, to promote energy efficiency and ensure the stability of power supply, hoping. Residential houses account for nearly 20% of Taiwan’s total electricity consumption, and are susceptible to human behavior and other factors, with high variability. Deep learning technology is now well developed, enabling the construction of an energy consumption prediction system using high-precision estimates generated by image recognition, in conjunction with the promotion of green energy plans. Based on a literature review, this work collects the electricity consumption of 20 counties and cities in Taiwan over six years, as well as 17 factors affecting residential electricity consumption as original data; The original time series historical energy data are then converted into 2D image data to form a training dataset for the deep learning model. Deep convolutional neural networks technology is applied to predict future power consumption. The Jellyfish search (JS) is then utilized as a metaheuristic optimization algorithm to construct a hybrid model JS-CNN by optimizing hyperparameters to improve model accuracy and stability. The models are cross-validated, with each performance index evaluating the prediction accuracy of each model to achieve the best prediction model. The research results can be applied to predict energy trend prediction; provide users with county-level electricity usage status checks, and examine the rationality and correctness of electricity usage behaviors. Management units can adopt the proposed model as a basis for energy policy formulation and electricity reference, and thus reduce unnecessary energy consumption.

[1] H. Zhong, J. Wang, H. Jia, Y. Mu, and S. Lv, "Vector field-based support vector regression for building energy consumption prediction," Applied Energy, vol. 242, pp. 403-414, 2019/05/15/ 2019, doi: https://doi.org/10.1016/j.apenergy.2019.03.078.
[2] R. K. Jana, I. Ghosh, and M. K. Sanyal, "A granular deep learning approach for predicting energy consumption," Applied Soft Computing, vol. 89, p. 106091, 2020/04/01/ 2020, doi: https://doi.org/10.1016/j.asoc.2020.106091.
[3] B. Lundgren and M. Schultzberg, "Application of the economic theory of self-control to model energy conservation behavioral change in households," Energy, vol. 183, pp. 536-546, 2019/09/15/ 2019, doi: https://doi.org/10.1016/j.energy.2019.05.217.
[4] N. Wei, C. Li, X. Peng, Y. Li, and F. Zeng, "Daily natural gas consumption forecasting via the application of a novel hybrid model," Applied Energy, vol. 250, pp. 358-368, 2019.
[5] P. Sen, M. Roy, and P. Pal, "Application of ARIMA for forecasting energy consumption and GHG emission: A case study of an Indian pig iron manufacturing organization," Energy, vol. 116, pp. 1031-1038, 2016/12/01/ 2016, doi: https://doi.org/10.1016/j.energy.2016.10.068.
[6] S. Xu, H. K. Chan, and T. Zhang, "Forecasting the demand of the aviation industry using hybrid time series SARIMA-SVR approach," Transportation Research Part E: Logistics and Transportation Review, vol. 122, pp. 169-180, 2019/02/01/ 2019, doi: https://doi.org/10.1016/j.tre.2018.12.005.
[7] S. Moonchai and N. Chutsagulprom, "Short-term forecasting of renewable energy consumption: Augmentation of a modified grey model with a Kalman filter," Applied Soft Computing, vol. 87, p. 105994, 2020/02/01/ 2020, doi: https://doi.org/10.1016/j.asoc.2019.105994.
[8] J. S. Chou and N. T. Ngo, "Time series analytics using sliding window metaheuristic optimization-based machine learning system for identifying building energy consumption patterns," Applied Energy, vol. 177, pp. 751-770, 2016/09/01/ 2016, doi: https://doi.org/10.1016/j.apenergy.2016.05.074.
[9] D. H. Tran, D. L. Luong, and J. S. Chou, "Nature-inspired metaheuristic ensemble model for forecasting energy consumption in residential buildings," Energy, vol. 191, p. 116552, 2020/01/15/ 2020, doi: https://doi.org/10.1016/j.energy.2019.116552.
[10] S. Thapar, "Energy consumption behavior: A data-based analysis of urban Indian households," Energy Policy, vol. 143, p. 111571, 2020/08/01/ 2020, doi: https://doi.org/10.1016/j.enpol.2020.111571.
[11] X. Liu and T. Sun, "Dynamic driving and counterfactual decomposition of the influencing factors of household energy consumption among provinces in China," Journal of Cleaner Production, vol. 230, pp. 1229-1240, 2019/09/01/ 2019, doi: https://doi.org/10.1016/j.jclepro.2019.05.189.
[12] Z. Chun-sheng, N. Shu-wen, and Z. Xin, "Effects of household energy consumption on environment and its influence factors in rural and urban areas," Energy Procedia, vol. 14, pp. 805-811, 2012/01/01/ 2012, doi: https://doi.org/10.1016/j.egypro.2011.12.1015.
[13] M.-J. Kim, "Understanding the determinants on household electricity consumption in Korea: OLS regression and quantile regression," The Electricity Journal, vol. 33, no. 7, p. 106802, 2020/08/01/ 2020, doi: https://doi.org/10.1016/j.tej.2020.106802.
[14] 許陞銘, "利用自動索引程式及人工智慧建立自動化網絡系統預測住宅總用電量," 2019. [Online]. Available: https://hdl.handle.net/11296/92vb74. 國立臺灣科技大學營建工程系碩士論文，台北市.
[15] C. Li, Z. Ding, D. Zhao, J. Yi, and G. Zhang, "Building energy consumption prediction: An extreme deep learning approach," Energies, vol. 10, no. 10, p. 1525, 2017.
[16] M. Längkvist, L. Karlsson, and A. Loutfi, "A review of unsupervised feature learning and deep learning for time-series modeling," Pattern Recognition Letters, vol. 42, pp. 11-24, 2014/06/01/ 2014, doi: https://doi.org/10.1016/j.patrec.2014.01.008.
[17] T.-Y. Kim and S.-B. Cho, "Predicting residential energy consumption using CNN-LSTM neural networks," Energy, vol. 182, pp. 72-81, 2019/09/01/ 2019, doi: https://doi.org/10.1016/j.energy.2019.05.230.
[18] T. Le, M. T. Vo, B. Vo, E. Hwang, S. Rho, and S. W. Baik, "Improving electric energy consumption prediction using CNN and Bi-LSTM," Applied Sciences, vol. 9, no. 20, p. 4237, 2019.
[19] S. Saha et al., "Predicting motor outcome in preterm infants from very early brain diffusion MRI using a deep learning convolutional neural network (CNN) model," NeuroImage, p. 116807, 2020/04/09/ 2020, doi: https://doi.org/10.1016/j.neuroimage.2020.116807.
[20] B. Guan, J. Yao, G. Zhang, and X. Wang, "Thigh fracture detection using deep learning method based on new dilated convolutional feature pyramid network," Pattern Recognition Letters, vol. 125, pp. 521-526, 2019/07/01/ 2019, doi: https://doi.org/10.1016/j.patrec.2019.06.015.
[21] Y. Guo, Y. Xu, and S. Li, "Dense construction vehicle detection based on orientation-aware feature fusion convolutional neural network," Automation in Construction, vol. 112, p. 103124, 2020/04/01/ 2020, doi: https://doi.org/10.1016/j.autcon.2020.103124.
[22] W. Fang, L. Ding, B. Zhong, P. E. D. Love, and H. Luo, "Automated detection of workers and heavy equipment on construction sites: A convolutional neural network approach," Advanced Engineering Informatics, vol. 37, pp. 139-149, 2018/08/01/ 2018, doi: https://doi.org/10.1016/j.aei.2018.05.003.
[23] H. Zang, L. Cheng, T. Ding, K. W. Cheung, Z. Wei, and G. Sun, "Day-ahead photovoltaic power forecasting approach based on deep convolutional neural networks and meta learning," International Journal of Electrical Power & Energy Systems, vol. 118, p. 105790, 2020/06/01/ 2020, doi: https://doi.org/10.1016/j.ijepes.2019.105790.
[24] O. B. Sezer and A. M. Ozbayoglu, "Algorithmic financial trading with deep convolutional neural networks: Time series to image conversion approach," Applied Soft Computing, vol. 70, pp. 525-538, 2018/09/01/ 2018, doi: https://doi.org/10.1016/j.asoc.2018.04.024.
[25] S. Zhou and W. Song, "Deep learning-based roadway crack classification using laser-scanned range images: A comparative study on hyperparameter selection," Automation in Construction, vol. 114, p. 103171, 2020.
[26] L. Rere, M. I. Fanany, and A. M. Arymurthy, "Metaheuristic algorithms for convolution neural network," Computational intelligence and neuroscience, vol. 2016, 2016.
[27] W. Elmasry, A. Akbulut, and A. H. Zaim, "Evolving deep learning architectures for network intrusion detection using a double PSO metaheuristic," Computer Networks, vol. 168, p. 107042, 2020/02/26/ 2020, doi: https://doi.org/10.1016/j.comnet.2019.107042.
[28] J. S. Chou and D. N. Truong, "A novel metaheuristic optimization algorithm inspired by swarms of jellyfish in oceans (Under Re-review)," Applied Mathematics and Computation, 2020.
[29] S. Fong, S. Deb, and X.-s. Yang, "How Meta-heuristic Algorithms Contribute to Deep Learning in the Hype of Big Data Analytics," in Progress in Intelligent Computing Techniques: Theory, Practice, and Applications, Singapore, P. K. Sa, M. N. Sahoo, M. Murugappan, Y. Wu, and B. Majhi, Eds., 2018// 2018: Springer Singapore, pp. 3-25.
[30] W. S. McCulloch and W. Pitts, "A logical calculus of the ideas immanent in nervous activity," The bulletin of mathematical biophysics, vol. 5, no. 4, pp. 115-133, 1943/12/01 1943, doi: 10.1007/BF02478259.
[31] G. A. Seber and A. J. Lee, Linear regression analysis. John Wiley & Sons, 2012.
[32] A. K. Yadav and 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, vol. 77, pp. 955-969, 2017/09/01/ 2017, doi: https://doi.org/10.1016/j.rser.2016.12.029.
[33] H. Drucker, C. J. Burges, L. Kaufman, A. J. Smola, and V. Vapnik, "Support vector regression machines," in Advances in neural information processing systems, 1997, pp. 155-161.
[34] A. M. Prasad, L. R. Iverson, and A. Liaw, "Newer Classification and Regression Tree Techniques: Bagging and Random Forests for Ecological Prediction," Ecosystems, vol. 9, no. 2, pp. 181-199, 2006/03/01 2006, doi: 10.1007/s10021-005-0054-1.
[35] C. Nebauer, "Evaluation of convolutional neural networks for visual recognition," IEEE transactions on neural networks, vol. 9, no. 4, pp. 685-696, 1998.
[36] J. Wu, "Introduction to convolutional neural networks," National Key Lab for Novel Software Technology. Nanjing University. China, vol. 5, p. 23, 2017.
[37] F. Chollet, Deep Learning 深度學習必讀 - Keras 大神帶你用 Python 實作. (in 中文), 2019.
[38] A. Krizhevsky, I. Sutskever, and G. E. Hinton, "Imagenet classification with deep convolutional neural networks," in Advances in neural information processing systems, 2012, pp. 1097-1105.
[39] K. Simonyan and A. Zisserman, "Very deep convolutional networks for large-scale image recognition," arXiv preprint arXiv:1409.1556, 2014.
[40] K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770-778.
[41] J. S. Chou and D. N. Truong, "Multiobjective optimization inspired by behavior of jellyfish for solving structural design problems," Chaos, Solitons & Fractals, vol. 135, p. 109738, 2020/06/01/ 2020, doi: https://doi.org/10.1016/j.chaos.2020.109738.
[42] S. W. Greenhouse and S. Geisser, "On methods in the analysis of profile data," Psychometrika, vol. 24, no. 2, pp. 95-112, 1959.
[43] C. J. Willmott and K. Matsuura, "Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance," Climate research, vol. 30, no. 1, pp. 79-82, 2005.
[44] T. Chai and R. R. Draxler, "Root mean square error (RMSE) or mean absolute error (MAE)?–Arguments against avoiding RMSE in the literature," Geoscientific model development, vol. 7, no. 3, pp. 1247-1250, 2014.
[45] S. Kim and H. Kim, "A new metric of absolute percentage error for intermittent demand forecasts," International Journal of Forecasting, vol. 32, no. 3, pp. 669-679, 2016.
[46] D. Karaboga and B. Akay, "A comparative study of artificial bee colony algorithm," Applied mathematics and computation, vol. 214, no. 1, pp. 108-132, 2009.
[47] M. Y. Cheng and D. Prayogo, "Symbiotic organisms search: a new metaheuristic optimization algorithm," Computers & Structures, vol. 139, pp. 98-112, 2014.
[48] R. V. Rao, V. J. Savsani, and D. Vakharia, "Teaching–learning-based optimization: a novel method for constrained mechanical design optimization problems," Computer-Aided Design, vol. 43, no. 3, pp. 303-315, 2011.