Load Forecasting in Microgrid Systems with R and Cortana Intelligence Suite

Energy production optimization has been traditionally very important for utilities in order to improve resource consumption. However, load forecasting is a challenging task, as there are a large number of relevant variables that must be considered, and several strategies have been used to deal with this complex problem. This is especially true also in microgrids where many elements have to adjust their performance depending on the future generation and consumption conditions. The goal of this paper is to present a solution for short-term load forecasting in microgrids, based on three machine learning experiments developed in R and web services built and deployed with different components of Cortana Intelligence Suite: Azure Machine Learning, a fully managed cloud service that enables to easily build, deploy, and share predictive analytics solutions; SQL database, a Microsoft database service for app developers; and PowerBI, a suite of business analytics tools to analyze data and share insights. Our results show that Boosted Decision Tree and Fast Forest Quantile regression methods can be very useful to predict hourly short-term consumption in microgrids; moreover, we found that for these types of forecasting models, weather data (temperature, wind, humidity and dew point) can play a crucial role in improving the accuracy of the forecasting solution. Data cleaning and feature engineering methods performed in R and different types of machine learning algorithms (Boosted Decision Tree, Fast Forest Quantile and ARIMA) will be presented, and results and performance metrics discussed.

• F. Lazzeri
• I. Reiter

• Time-series
• features engineering methods for forecasting
• energy demand forecasting
• Azure machine learning.

[1] W. Su, J. Wang, “Energy Management Systems in Microgrid Operations”, The Electricity Journal, vol. 25, no. 8, pp. 45–60, October 2012.
[2] M.A Ancona, L. Branchini, A. De Pascale, F. Melino, “Smart District Heating: Distributed Generation Systems’ Effects on the Network”, Energy Procedia, vol. 75, pp. 1208-1213, 2015.
[3] T.S. Ustun, C. Ozansoy, A. Zayegh, “Recent developments in microgrids and example cases around the world: A review”, Renewable and Sustainable Energy Reviews, vol. 15, no. 8, pp. 4030-4041, October 2011.
[4] https://doh.dc.gov/sites/default/files/dc/sites/ddoe/service_content/attachments/DOEE%20Microgrid%20101%20Presentation%20%28Sept%202015%29.pdf, September 2015.
[5] http://www.nrg.com/renewables/technologies /microgrids/, August 2016.
[6] https://github.com/edsfocci/azure-content/blob/master/articles/cortana-analytics-playbook-demand-forecasting-energy.md, January 2016.
[7] http://www.reed.edu/physics/courses/Physics331.f08/pdf/Fourier.pdf, 2008.
[8] M. Prabhugoud, K. Peters, J. Pearson, M. A. Zikry, “Independent measurement of strain and sensor failure features in Bragg grating sensors through multiple mode coupling”, Sensors and Actuators A Physical, vol. 135, no. 2, pp. 433-442, April 2007.
[9] https://gallery.cortanaintelligence.com/CustomModule/Generate-Lag-Features-1, October 2016.
[10] https://msdn.microsoft.com/en-us/library/azure/dn905801.aspx, June 9, 2016.
[11] N. Meinshausen, “Quantile Regression Forests”, Journal of Machine Learning Research, vol. 7, pp. 983-999, 2006.
[12] http://stat.cmu.edu/~hseltman/618/LNTS4.pdf, March 3, 2016.
[13] X. Chang, M. Gao, Y. Wang, X. Hou, “Seasonal autoregressive integrated moving average model for precipitation time series”, Journal of Mathematics and Statistics, vol. 8, no. 4, pp. 500-505, 2012.
[14] K. Xian-guo, L. Zong-qi, Z. Jian-hua, “New Power Management Strategies for a Microgrid with Energy Storage Systems”, Energy Procedia, vol. 16, part C, pp. 1678-1684, 2012.
[15] H. Jiayi, J. Chuanwen, X. Rong, “A review on distributed energy resources and MicroGrid”, Renewable and Sustainable Energy Reviews, vol. 12, no. 9, pp. 2472-2483, December 2008.