Machine Learning Platform for Profiling and Forecasting at Microgrid Level

Enea Mele 1 , Charalambos Elias 2 , and Aphrodite Ktena 3
  • 1 National and Kapodistrian University of Athens, , Athens, Greece
  • 2 National and Kapodistrian University of Athens, , Athens, Greece
  • 3 National and Kapodistrian University of Athens, , Athens, Greece


The shift towards distributed generation and microgrids has renewed the interest in forecasting algorithms and methods, which need to take into account the advances in information, metering and control technologies in order to address the challenges of forecasting problems. Technologies such as machine learning have been proven useful for short-term electricity load forecasting, especially for microgrids, as they can also take into account several types of historical data and can adapt to changes often encountered in small-scale systems and on a short time scale. In this paper, we present a flexible and easily customized modular toolbox, called Divinus, for electricity use profiling and forecasting in microgrids. Divinus may support a variety of machine learning algorithms for forecasting and profiling that can be used independently or combined. For demonstration purposes, we have implemented Self-Organizing Maps for profiling and k-Neighbors for forecasting. The testing of the platform was based on electricity consumption data of the Euripus campus of the National and Kapodistrian University of Athens in Evia, Greece, from January 2010 till March 2018. The tests that have been carried out so far show that the platform can be easily customized and the algorithms examined yield high accuracy and acceptable mean errors for the case of a university campus energy profile.

If the inline PDF is not rendering correctly, you can download the PDF file here.

  • [1] T. V. Ark, “Ask About AI - The Future of Work and Learning,” Getting Smart Staff, 2017.

  • [2] E. Koblentz, “How to implement AI and machine learning,” TechRepublic, 2016.

  • [3] Z. Mohamed and P. Bodger, “Forecasting electricity consumption in New Zealand using economic and demographic variables,” Energy, vol. 30, no. 10, pp. 1833–1843, 2005.

  • [4] M. Yang and X. Yu, “China’s rural electricity market – a quantitative analysis,” Energy, vol. 29, no. 7, pp. 961–977, 2004.

  • [5] E. Mele, A. Ktena and C. Elias, “Electricity use profiling and forecasting at microgrid level,” in RTUCON 2018, Riga, Latvia, 2018.

  • [6] T. Haida and S. Muto, “Regression based peak load forecasting using a transformation technique,” IEEE Trans. Power Syst., vol. 9, no. 4, pp. 1788–1794, Nov. 1994.

  • [7] S. Mirasgedis, Y. Safaridis, E. Georgopoulou, D. P. Lalas, M. Moschovits, F. Karagiannis and D. Papakonstantinou, “Models for mid-term electricity demand forecasting incorporating weather influences,” Energy, vol. 31, no. 2-3, pp. 208–227, 2006.

  • [8] H. L. Willis and J. E. D. Northcote-green, “Comparison tests of fourteen distribution load forecasting methods,” IEEE Trans. Power App. Syst., vol. 103, no. 6, pp. 1190–1197, 1984.

  • [9] H. L. Willis, R. W. Powell, and D. L. Wall, “Load transfer coupling regression curve fitting for distribution load forecasting,” IEEE Trans Power App. Syst., vol. 103, no. 5, pp. 1070–1076, 1984.

  • [10] E. Doveh, P. Feigin, D. Greig and L. Hyams, “Experience with FNN models for medium term power demand predictions,” IEEE Trans. Power Syst., vol. 14, no. 2, pp. 538–546, May 2002.

  • [11] G. J. Tsekouras, N. D. Hatziargyriou and E. N. Dialynas, “An optimized adaptive neural network for annual midterm energy forecasting,” IEEE Trans. Power Syst., vol. 21, no. 1, pp. 385–391, Feb. 2006.

  • [12] M. Y. Chow, J. Zhu and H. Tram, “Application of fuzzy multi-objective decision making in spatial load forecasting,” IEEE Trans. Power Syst., vol. 13, no. 3, pp. 1185–1190, Aug. 1998.

  • [13] C. N. Elias and N. D. Hatziargyriou, “An Annual Midterm Energy Forecasting Model Using Fuzzy Logic,” IEEE Transactions On Power Systems, vol. 24, no. 1, pp. 469–478, Feb. 2009.

  • [14] G. J. Chen, K. K. Li, T. S. Chung, H. B. Sun and G. Q. Tang, “Application of an innovative combined forecasting method in power system load forecasting,” Elect. Power Syst. Res., vol. 59, no. 2, pp. 131–137, 2001.

  • [15] J. Llanos, D. Sáez, R. Palma-Behnke, A. Núñez and G. Jiménez-Estévez, “Load Profile Generator and Load Forecasting for a Renewable Based Microgrid Using Self Organizing Maps and Neural Networks,” in The 2012 International Joint Conference on Neural Networks (IJCNN), 2012.

  • [16] Z. H. Bohari, H. Azemy, M. N. M. Nasir, M. F. Baharom, M. F. Sulaima and M. H. Jali, “Reliable Short Term Load Forecasting Using Self Organizing Map (SOM) In Deregulated Electricity Market,” Journal of Theoretical and Applied Information Technology, vol. 79, no. 3, pp. 389–394, Sep. 2015.

  • [17] O. A. S. Carpinteiro and A. J. R. Reis, “A Hierarchical Self-Organizing Map Model In Short-Term Load Forecasting,” Journal of Intelligent and Robotic Systems, vol. 31, no. 1-3, pp. 105–113, May 2001.

  • [18] J. Che, J. Wang and G. Wang, “An adaptive fuzzy combination model based on self-organizing map and support,” Energy, vol. 37, no. 1, pp. 657–664, Jan. 2012.

  • [19] V. Jakkula, “Tutorial on Support Vector Machine (SVM)”, School of EECS, Washington State University, 2012.

  • [20] “1.4. Support Vector Machines,” scikit-learn, [Online]. Available: [Accessed 3 May 2019].

  • [21] A. Zhang, P. Zhang and Y. Feng, “Short-term load forecasting for microgrids based on DA-SVM,” COMPEL - The International Journal for Computation and Mathematics in Electrical and Electronic Engineering, vol. 38, no. 1, pp. 68–80, 2019.

  • [22] “scikit-learn,” scikit-learn developers, [Online]. Available: [Accessed May 26 2018].

  • [23] W. Li, D. Kong and J. Wu, “A Novel Hybrid Model Based on Extreme Learning Machine, k-Nearest Neighbor Regression and Wavelet Denoising Applied to Short-Term Electric Load Forecasting,” Energies 2017, vol. 10, no. 5, 2017.

  • [24] R. Zhang, Y. Xu, Z. Y. Dong, W. Kong and K. P. Wong, “A composite k-nearest neighbor model for day-ahead load forecasting with limited temperature forecasts,” 2016 IEEE Power and Energy Society General Meeting (PESGM), Jul. 2016.

  • [25] G. Hackeling, “Mastering Machine Learning with scikit-learn”, Birmingham: Packt Publishing, October 2014.

  • [26] N. Huang, Z. Hu, G. Cai and D. Yang, “Short Term Electrical Load Forecasting Using Mutual Information Based Feature Selection with Generalized Minimum-Redundancy and Maximum-Relevance Criteria,” Entropy 2016, vol. 18, no. 9, 2016.

  • [27] G. Dudek, “Short-Term Load Forecasting using Random Forests, Department of Electrical,” in Filev D. et al. (eds) Intelligent Systems’ 2014. Advances in Intelligent Systems and Computing, vol. 323. Springer, Cham. 2015.

  • [28] S. A. Kalogirou, “Artificial neural networks in energy applications in buildings,” International Journal of Low Carbon Technologies, vol. 1, no. 3, pp. 201–216, Jul. 2006.

  • [29] L. Hernández, C. Baladrón, J. M. Aguiar, B. Carro, A. Sánchez-Esguevillas and J. Lloret, “Artificial Neural Networks for Short-Term Load Forecasting in Microgrids Enviroment,” Energy, vol. 75, pp. 252–264, Oct. 2014.

  • [30] H. Chitsaz, H. Shaker, H. Zareipour, D. Wood and N. Amjady, “Short-term Electricity Load Forecasting of Buildings in Microgrids,” Energy and Buildings, vol. 99, pp. 50–60, Jul. 2015.

  • [31] The PostgreSQL Global Development Group, “PostgreSQL,” The PostgreSQL Global Development Group, [Online]. Available: [Accessed 20 02 2018].

  • [32] Django Software Foundation, “django,” Django Software Foundation, [Online]. Available: [Accessed 26 May 2018].

  • [33] G. Vettigli, “MiniSom: minimalistic and NumPy-based implementation of the Self Organizing Map,” 15 September 2013. [Online]. Available: w [Accessed 24 May 2018].


Journal + Issues