Machine learning for energy-water nexus: challenges and opportunities

Figures & data

Table 1. Overview of machine learning techniques used in energy-water nexus.

Target Problems	Supervised Learning	Unsupervised Learning	Reinforcement Learning	Ensemble Learning
Energy generation	Table 2	–	–	Table 5
Energy use	Table 2	Table 4	–	Table 5
Water use	Table 3	Table 4	–	Table 5
Energy for water	Table 3	Table 4	–	–
Water for energy	Table 3	Table 4	Section 3.4	–

Table 2. Supervised learning techniques in energy generation and use.

Technique	Energy generation	Energy use
ANN		(Brown & Matin, 1995)
		(Suykens et al., 1996)
		(Khotanzad & Elragal, 1999b)
	(Gomes & Castro, 2012)	(Tso & Yau, 2007)
	(Bugal-a et al., 2018)	(Geem & Roper, 2009)
		(Sabo et al., 2011)
		(DEMI˙REL et al., 2012)
		(Ahmad et al., 2014)
		(Zhang & Yang, 2015)
SVM	(Mohandes et al., 2004)	(Ahmad et al., 2014)
	(Sharma et al., 2011)
Regression		(Parikh et al., 2007)
	(Abuella & Chowdhury, 2015)	(Tso & Yau, 2007)
	(Dedgaonkar et al., 2016)	(Sabo et al., 2011)
		(DEMI^˙REL et al., 2012)
		(Taspnar et al., 2013)
		(Bianco et al., 2014)
Time series	(Hill et al., 2012)	(Dilaver et al., 2014)
	(Huang et al., 2012)	(DEMI^˙REL et al., 2012)
Decision trees		(Tso & Yau, 2007)
	–	(Al-Gunaid et al., 2016)

Table 3. Supervised learning techniques in energy for water, water for energy and water use.

Technique	Energy for water/Water for energy	Water use
ANN		(Jain et al., 2000)
	Water for energy	(Bougadis et al., 2005)
	(Sauhats et al., 2016)	(Msiza et al., 2007)
		(Suh, Kim, & Kim, 2015)
SVM	Energy for water	(Chen & Zhang, 2006)
	(Zeng, Cai, Ringler, & Zhu, 2017)	(Tu-Qiao, 2006)
	(Vitter & Webber, 2018	(Msiza et al., 2007)
Regression	Water for Energy
	(Cook et al., 2015)	(Oh & Yamauchi, 1974)
		(Tinker, Bame, Burt, & Speed, 2005)
	Energy for water	(Zhang & Brown, 2005)
	(Carlson & Walburger, 2007)	(Schleich & Hillenbrand, 2009)
	(Spruston, Kolesov, & Main, 2012)
	(Molinos-Senante et al., 2018)
Time series		(Miaou, 1990)
	–	(Jowitt & Xu, 1992)
		(Arandia, Ba, Eck, & McKenna, 2015)
		(Al-Zahrani & Abo-Monasar, 2015)

Table 4. Unsupervised learning techniques used in energy-water nexus.

Technique	Energy for water/Water for energy	Energy use/Water use
K-medoids clustering		Water use
	–	(Pastor-Jabaloyes et al., 2018)
K-means clustering	Water for energy
	(Grubert, 2016)	–
Hierarchical clustering	Energy for water	Water use
	(Helmbrecht et al., 2017)	(Noiva et al., 2016)
DBSCAN		Water use
	–	(Zhang et al., 2016)
HMM		Water use
	Energy for water	(Nguyen et al., 2013a)
	(Nguyen, Stewart, & Zhang, 2017)	(Nguyen et al., 2013b)
		(Nguyen et al., 2014b)
		(Nguyen et al., 2015)
		Energy use
		(Parson et al., 2014)
		(Kolter & Jaakkola, 2012)
PCA		Energy use
	–	(Lam et al., 2008)
		(Ndiaye & Gabriel, 2011)

Table 5. Ensemble learning techniques used in energy-water nexus.

Technique	Water Use	Energy Generation/Use
Bayesian model averaging	–	Energy use
		(Zhang & Yang, 2015)
Random forests		Energy generation
	(McManamay, 2014)	(Lin et al., 2015)
	(Chen et al., 2017)	(Lahouar & Slama, 2017)
		Energy use
		(Ma & Cheng, 2016)
Hybrid models		Energy use
		(Tang, Wang, Li, Yu, & Zhang, 2015)
	(Tiwari & Adamowski, 2014)	Energy generation
	(Tiwari & Adamowski, 2017)	(Liu, Tian, Chen, & Li, 2010)
		(Hossain et al., 2012)
		(Azimi, Ghayekhloo, & Ghofrani, 2016)
		(Hussain & AlAlili, 2017)
		(Peng, Zhou, Zhang, & Zheng, 2017)

Figure 1. Artificial neural network schematic.

Brown, R. H., & Matin, I. (1995). Development of artificial neural network models to predict daily gas consumption. In Industrial Electronics, Control, and Instrumentation, 1995., Proceedings of the 1995 IEEE IECON 21st International Conference (Vol. 2, pp. 1389–1394). Orlando, FL, USA: IEEE.

 Google Scholar

Suykens, J., Lemmerling, P., Favoreel, W., De Moor, B., Crepel, M., & Briol, P. (1996). Modelling the Belgian gas consumption using neural networks. Neural Processing Letters, 4(3), 157–166.

 Web of Science ®Google Scholar

Khotanzad, A., & Elragal, H. (1999b). Natural gas load forecasting with combination of adaptive neural networks. In Neural Networks, 1999. IJCNN’99. International Joint Conference (Vol. 6, pp. 4069–4072). Washington, DC: IEEE.

 Google Scholar

Gomes, P., & Castro, R. (2012). Wind speed and wind power forecasting using statistical models: Autoregressive moving average (arma) and artificial neural networks (ann). International Journal of Sustainable Energy Development, 1(1/2).

 Google Scholar

Tso, G. K., & Yau, K. K. (2007). Predicting electricity energy consumption: A comparison of regression analysis, decision tree and neural networks. Energy, 32(9), 1761–1768.

 Web of Science ®Google Scholar

Bugała, A., Zaborowicz, M., Boniecki, P., Janczak, D., Koszela, K., Czekaa, W., & Lewicki, A. (2018). Short-term forecast of generation of electric energy in photovoltaic systems. Renewable and Sustainable Energy Reviews, 81, 306–312.

 Web of Science ®Google Scholar

Geem, Z. W., & Roper, W. E. (2009). Energy demand estimation of South Korea using artificial neural network. Energy Policy, 37(10), 4049–4054.

 Web of Science ®Google Scholar

Sabo, K., Scitovski, R., Vazler, I., & Zekić-Sušac, M. (2011). Mathematical models of natural gas consumption. Energy Conversion and Management, 52(3), 1721–1727.

 Web of Science ®Google Scholar

Demirel, Ö. F., Zaim, S., Çalişkan, A., & Özuyar, P. (2012). Forecasting natural gas consumption in istanbul using neural networks and multivariate time series methods. Turkish Journal of Electrical Engineering & Computer Sciences, 20(5), 695–711.

 Web of Science ®Google Scholar

Ahmad, A., Hassan, M., Abdullah, M., Rahman, H., Hussin, F., Abdullah, H., & Saidur, R. (2014). A review on applications of ann and svm for building electrical energy consumption forecasting. Renewable and Sustainable Energy Reviews, 33, 102–109.

 Web of Science ®Google Scholar

Zhang, W., & Yang, J. (2015). Forecasting natural gas consumption in China by Bayesian model averaging. Energy Reports, 1, 216–220.

 Web of Science ®Google Scholar

Mohandes, M. A., Halawani, T. O., Rehman, S., & Hussain, A. A. (2004). Support vector machines for wind speed prediction. Renewable Energy, 29(6), 939–947.

 Web of Science ®Google Scholar

Sharma, N., Sharma, P., Irwin, D., & Shenoy, P. (2011). Predicting solar generation from weather forecasts using machine learning. In Smart Grid Communications (SmartGridComm), 2011 IEEE International Conference (pp. 528–533). Brussels, Belgium: IEEE.

 Google Scholar

Parikh, J., Purohit, P., & Maitra, P. (2007). Demand projections of petroleum products and natural gas in India. Energy, 32(10), 1825–1837.

 Web of Science ®Google Scholar

Abuella, M., & Chowdhury, B. (2015). Solar power probabilistic forecasting by using multiple linear regression analysis. In SoutheastCon 2015 (pp. 1–5). IEEE.

 Google Scholar

Dedgaonkar, S., Patil, V., Rathod, N., Hakare, G., & Bhosale, J. (2016). Solar energy prediction using least square linear regression method. International Journal of Current Engineering and Technology, 6(5), 1549–1552.

 Google Scholar

Taspnar, F., Celebi, N., & Tutkun, N. (2013). Forecasting of daily natural gas consumption on regional basis in turkey using various computational methods. Energy and Buildings, 56, 23–31.

 Web of Science ®Google Scholar

Bianco, V., Scarpa, F., & Tagliafico, L. A. (2014). Scenario analysis of nonresidential natural gas consumption in Italy. Applied Energy, 113, 392–403.

 Web of Science ®Google Scholar

Hill, D. C., McMillan, D., Bell, K. R., & Infield, D. (2012). Application of auto-regressive models to UK wind speed data for power system impact studies. IEEE Transactions on Sustainable Energy, 3(1), 134–141.

 Web of Science ®Google Scholar

Dilaver, Ö., Dilaver, Z., & Hunt, L. C. (2014). What drives natural gas consumption in Europe? analysis and projections. Journal of Natural Gas Science and Engineering, 19, 125–136.

 Web of Science ®Google Scholar

Huang, R., Huang, T., Gadh, R., & Li, N. (2012). Solar generation prediction using the arma model in a laboratory-level micro-grid. In Smart Grid Communications (SmartGridComm), 2012 IEEE Third International Conference (pp. 528–533). Tainan City, Taiwan: IEEE.

 Google Scholar

Al-Gunaid, M. A., Shcherbakov, M. V., Skorobogatchenko, D. A., Kravets, A. G., & Kamaev, V. A. (2016). Forecasting energy consumption with the data reliability estimation in the management of hybrid energy system using fuzzy decision trees. In Information, Intelligence, Systems & Applications (IISA), 2016 7th International Conference (pp. 1–8). Chalkidiki, Greece: IEEE.

 Google Scholar

Jain, D. A., Joshi, U. C., & Varshney, A. K. (2000). Short-term water demand forecasting using artificial neural networks: IIT Kanpur experience. In Pattern Recognition, 2000. Proceedings. 15th International Conference (Vol. 2, pp. 459–462). Barcelona, Spain: IEEE.

 Google Scholar

Bougadis, J., Adamowski, K., & Diduch, R. (2005). Short-term municipal water demand forecasting. Hydrological Processes, 19(1), 137–148.

 Web of Science ®Google Scholar

Sauhats, A., Petrichenko, R., Broka, Z., Baltputnis, K., & Sobolevskis, D. (2016). Ann-based forecasting of hydropower reservoir inflow. In Power and Electrical Engineering of Riga Technical University (RTUCON), 2016 57th International Scientific Conference (pp. 1–6). Riga, Latvia: IEEE.

 Google Scholar

Msiza, I. S., Nelwamondo, F. V., & Marwala, T. (2007). Artificial neural networks and support vector machines for water demand time series forecasting. In Systems, Man and Cybernetics, 2007. ISIC. IEEE International Conference (pp. 638–643). Montreal, Que., Canada: IEEE.

 Google Scholar

Suh, D., Kim, H., & Kim, J. (2015). Estimation of water demand in residential building using machine learning approach. In IT Convergence and Security (ICITCS), 2015 5th International Conference (pp. 1–2). Kuala Lumpur, Malaysia: IEEE.

 Google Scholar

Chen, L., & Zhang, T.-Q. (2006). Hourly water demand forecast model based on least squares support vector machine. Journal of Harbin Institute of Technology, 9, 030.

 Google Scholar

Zeng, R., Cai, X., Ringler, C., & Zhu, T. (2017). Hydropower versus irrigation? An analysis of global patterns. Environmental Research Letters, 12(3), 034006.

 Web of Science ®Google Scholar

Tu-Qiao, C. L. Z. (2006). Hourly water demand forecast model based on Bayesian least squares support vector machine [j]. Journal of Tianjin University, 9, 005.

 Google Scholar

Vitter, J., & Webber, M. (2018). A non-intrusive approach for classifying residential water events using coincident electricity data. Environmental Modelling & Software, 100, 302–313.

 Web of Science ®Google Scholar

Cook, M. A., King, C. W., Davidson, F. T., & Webber, M. E. (2015). Assessing the impacts of droughts and heat waves at thermoelectric power plants in the united states using integrated regression, thermodynamic, and climate models. Energy Reports, 1, 193–203.

 Web of Science ®Google Scholar

Oh, H.-S., & Yamauchi, H. (1974). An economic analysis of the patterns and trends in water consumption within the service area of the Honolulu board of water supply (pp. 84). Honolulu: Univ. of Honolulu Rep.

 Google Scholar

Tinker, A., Bame, S., Burt, R., & Speed, M. (2005). Impact of “non-behavioral fixed effects” on water use: Weather and economic construction differences on residential water use in Austin, Texas. Electronic Green Journal, 1, 22.

 Google Scholar

Zhang, H. H., & Brown, D. F. (2005). Understanding urban residential water use in Beijing and Tianjin, China. Habitat International, 29(3), 469–491.

 Web of Science ®Google Scholar

Carlson, S., & Walburger, A. (2007). Energy index development for benchmarking water and wastewater utilities. Denver, Colorado: American Water Works Association.

 Google Scholar

Schleich, J., & Hillenbrand, T. (2009). Determinants of residential water demand in Germany. Ecological Economics, 68(6), 1756–1769.

 Web of Science ®Google Scholar

Spruston, S., Kolesov, A., & Main, D. (2012). Leveraging the energy of the group to manage the energy of the utility: The nwwbi adopts industry tools to improve energy performance. Proceedings of the Water Environment Federation, 2012(14), 2383–2402.

 Google Scholar

Molinos-Senante, M., Sala-Garrido, R., & Iftimi, A. (2018). Energy intensity modeling for wastewater treatment technologies. Science of the Total Environment, 630, 1565–1572.

 Web of Science ®Google Scholar

Miaou, S.-P. (1990). A class of time series urban water demand models with nonlinear climatic effects. Water Resources Research, 26(2), 169–178.

 Web of Science ®Google Scholar

Jowitt, P. W., & Xu, C. (1992). Demand forecasting for water distribution systems. Civil Engineering Systems, 9(2), 105–121.

 Web of Science ®Google Scholar

Arandia, E., Ba, A., Eck, B., & McKenna, S. (2015). Tailoring seasonal time series models to forecast short-term water demand. Journal of Water Resources Planning and Management, 142(3), 04015067.

 Web of Science ®Google Scholar

Al-Zahrani, M. A., & Abo-Monasar, A. (2015). Urban residential water demand prediction based on artificial neural networks and time series models. Water Resources Management, 29(10), 3651–3662.

 Web of Science ®Google Scholar

Pastor-Jabaloyes, L., Arregui, F., & Cobacho, R. (2018). Water end use disaggregation based on soft computing techniques. Water, 10(1), 46.

 Web of Science ®Google Scholar

Grubert, E. A. (2016). Water consumption from hydroelectricity in the united states. Advances in Water Resources, 96, 88–94.

 Web of Science ®Google Scholar

Helmbrecht, J., Pastor, J., & Moya, C. (2017). Smart solution to improve water-energy nexus for water supply systems. Procedia Engineering, 186, 101–109.

 Google Scholar

Noiva, K., Fernández, J. E., & Wescoat, J. L., Jr. (2016). Cluster analysis of urban water supply and demand: Toward large-scale comparative sustainability planning. Sustainable Cities and Society, 27, 484–496.

 Web of Science ®Google Scholar

Zhang, H., Du, Q., Yao, M., & Ren, F. (2016). Evaluation and clustering maps of groundwater wells in the red beds of Chengdu, Sichuan, China. Sustainability, 8(1), 87.

 Web of Science ®Google Scholar

Nguyen, K. A., Stewart, R. A., & Zhang, H. (2013a). An intelligent pattern recognition model to automate the categorisation of residential water end-use events. Environmental Modelling & Software, 47, 108–127.

 Web of Science ®Google Scholar

Nguyen, K. A., Stewart, R. A., & Zhang, H. (2017). Water end-use classification with contemporaneous water-energy data and deep learning network. World Academy of Science, Engineering and Technology, International Journal of Computer, Electrical, Automation, Control and Information Engineering, 12(1), 1–6.

 Google Scholar

Nguyen, K. A., Zhang, H., & Stewart, R. A. (2013b). Development of an intelligent model to categorise residential water end use events. Journal of Hydro-Environment Research, 7(3), 182–201.

 Web of Science ®Google Scholar

Nguyen, K. A., Stewart, R. A., & Zhang, H. (2014b). An autonomous and intelligent expert system for residential water end-use classification. Expert Systems with Applications, 41(2), 342–356.

 Web of Science ®Google Scholar

Nguyen, K. A., Stewart, R. A., Zhang, H., & Jones, C. (2015). Intelligent autonomous system for residential water end use classification: Autoflow. Applied Soft Computing, 31, 118–131.

 Web of Science ®Google Scholar

Parson, O., Ghosh, S., Weal, M., & Rogers, A. (2014). An unsupervised training method for non-intrusive appliance load monitoring. Artificial Intelligence, 217, 1–19.

 Web of Science ®Google Scholar

Kolter, J. Z., & Jaakkola, T. (2012). Approximate inference in additive factorial hmms with application to energy disaggregation. In N. D. Lawrence & M. Girolami (Eds.), Artificial intelligence and statistics (pp. 1472–1482).

 Google Scholar

Lam, J. C., Wan, K. K., Cheung, K., & Yang, L. (2008). Principal component analysis of electricity use in office buildings. Energy and USbuildings, 40(5), 828–836.

 Web of Science ®Google Scholar

Ndiaye, D., & Gabriel, K. (2011). Principal component analysis of the electricity consumption in residential dwellings. Energy and Buildings, 43(2), 446–453.

 Web of Science ®Google Scholar

McManamay, R. A. (2014). Quantifying and generalizing hydrologic responses to dam regulation using a statistical modeling approach. Journal of Hydrology, 519, 1278–1296.

 Web of Science ®Google Scholar

Lin, Y., Kruger, U., Zhang, J., Wang, Q., Lamont, L., & El Chaar, L. (2015). Seasonal analysis and prediction of wind energy using random forests and arx model structures. IEEE Transactions on Control Systems Technology, 23(5), 1994–2002.

 Web of Science ®Google Scholar

Chen, G., Long, T., Xiong, J., & Bai, Y. (2017). Multiple random forests modelling for urban water consumption forecasting. Water Resources Management, 31(15), 4715–4729.

 Web of Science ®Google Scholar

Lahouar, A., & Slama, J. B. H. (2017). Hour-ahead wind power forecast based on random forests. Renewable Energy, 109, 529–541.

 Web of Science ®Google Scholar

Ma, J., & Cheng, J. C. (2016). Identifying the influential features on the regional energy use intensity of residential buildings based on random forests. Applied Energy, 183, 193–201.

 Web of Science ®Google Scholar

Tang, L., Wang, Z., Li, X., Yu, L., & Zhang, G. (2015). A novel hybrid fa-based lssvr learning paradigm for hydropower consumption forecasting. Journal of Systems Science and Complexity, 28(5), 1080–1101.

 Web of Science ®Google Scholar

Tiwari, M. K., & Adamowski, J. F. (2014). Medium-term urban water demand forecasting with limited data using an ensemble wavelet–Bootstrap machine-learning approach. Journal of Water Resources Planning and Management, 141(2), 04014053.

 Web of Science ®Google Scholar

Tiwari, M. K., & Adamowski, J. F. (2017). An ensemble wavelet bootstrap machine learning approach to water demand forecasting: A case study in the city of Calgary, Canada. Urban Water Journal, 14(2), 185–201.

 Web of Science ®Google Scholar

Liu, H., Tian, H.-Q., Chen, C., & Li, Y.-F. (2010). A hybrid statistical method to predict wind speed and wind power. Renewable Energy, 35(8), 1857–1861.

 Web of Science ®Google Scholar

Hossain, M. R., Oo, A. M. T., & Ali, A. S. (2012). Hybrid prediction method of solar power using different computational intelligence algorithms. In Power Engineering Conference (AUPEC), 2012 22nd Australasian Universities (pp. 1–6). Bali, Indonesia: IEEE.

 Google Scholar

Azimi, R., Ghayekhloo, M., & Ghofrani, M. (2016). A hybrid method based on a new clustering technique and multilayer perceptron neural networks for hourly solar radiation forecasting. Energy Conversion and Management, 118, 331–344.

 Web of Science ®Google Scholar

Hussain, S., & AlAlili, A. (2017). A hybrid solar radiation modeling approach using wavelet multiresolution analysis and artificial neural networks. Applied Energy, 208, 540–550.

 Web of Science ®Google Scholar

Peng, T., Zhou, J., Zhang, C., & Zheng, Y. (2017). Multi-step ahead wind speed forecasting using a hybrid model based on two-stage decomposition technique and adaboost-extreme learning machine. Energy Conversion and Management, 153, 589–602.

 Web of Science ®Google Scholar