Energy management of hybrid energy system sources based on machine learning classification algorithms

Abstract Hybrid energy systems (HES) that contain renewable energy sources, such as wind and solar energy help to minimize CO2 emissions. Therefore, studying these systems to improve their performance has become one of the critical needs these days due to the environmental crisis. Within HES, energy management (EM) of HES is an essential topic that has been covered in detail by numerous studies, as errors in EM can lead to HES blackouts. Recent research has experimented with energy management strategy (EMS) to achieve optimal EM. This work aims to generate a robust forecasting model for one hour ahead of EM. The present research work has two main objectives. The first objective is to determine which energy source should supply the demand side, using different machine-learning algorithms such as Random Forest (RF), Decision Tree (DT), Gaussian Naive Bayes (Gaussian NB) and K-Nearest Neighbors (KNN). The second objective is to compare the results of these algorithms to choose the algorithm with the best performance and to rank them based on performance as well as accuracy. The work is validated using different algorithms. The results show that DT algorithm has achieved the best performance compared to the RF and Gaussian NB algorithms. KNN algorithm gives the lowest accuracy especially over class 3. The results proof that RF, DT, and Gaussian NB algorithms are reliable.

[1]  Jiani Heng,et al.  A hybrid forecasting system based on fuzzy time series and multi-objective optimization for wind speed forecasting , 2019, Applied Energy.

[2]  C. P. Sumathi,et al.  An Automated Technique using Gaussian Naïve Bayes Classifier to Classify Breast Cancer , 2016 .

[3]  D. Baczyński,et al.  Short-term electric energy production forecasting at wind power plants in pareto-optimality context , 2017 .

[4]  Hamed H. H. Aly,et al.  A Proposed ANN and FLSM Hybrid Model for Tidal Current Magnitude and Direction Forecasting , 2014, IEEE Journal of Oceanic Engineering.

[5]  Lambros Ekonomou,et al.  Design of artificial neural network models for the prediction of the Hellenic energy consumption , 2010, 10th Symposium on Neural Network Applications in Electrical Engineering.

[6]  Abinet Tesfaye Eseye,et al.  Short-term photovoltaic solar power forecasting using a hybrid Wavelet-PSO-SVM model based on SCADA and Meteorological information , 2018 .

[7]  Syed Talha Mehmood,et al.  PERFORMANCE EVALUATION OF NEW AND ADVANCED NEURAL NETWORKS FOR SHORT TERM LOAD FORECASTING: CASE STUDIES FOR MARITIMES AND ONTARIO , 2014 .

[8]  J. M. Al-Tuwaijari,et al.  Cancer Classification Using Gaussian Naive Bayes Algorithm , 2019, 2019 International Engineering Conference (IEC).

[9]  Mohamed E. El-Hawary,et al.  An overview of forecasting techniques for load, wind and solar powers , 2017, 2017 IEEE Electrical Power and Energy Conference (EPEC).

[10]  Cihan H. Dagli,et al.  Solar Irradiance Forecasting Using Deep Neural Networks , 2017 .

[11]  Vasiliki Vita,et al.  Techno-Economic Assessment of Hybrid Energy Off-Grid System - A Case Study for Masirah Island in Oman , 2017 .

[12]  Pradip Kumar Sadhu,et al.  Forecasting PV power from solar irradiance and temperature using neural networks , 2017, INFOCOM 2017.

[13]  Hamed H.H. Aly,et al.  A novel deep learning intelligent clustered hybrid models for wind speed and power forecasting , 2020 .

[14]  Hamed H. H. Aly,et al.  An intelligent hybrid model of neuro Wavelet, time series and Recurrent Kalman Filter for wind speed forecasting , 2020 .

[15]  Hamed H. H. Aly,et al.  A proposed intelligent short-term load forecasting hybrid models of ANN, WNN and KF based on clustering techniques for smart grid , 2020 .

[16]  Gerhard-Wilhelm Weber,et al.  Long-term load forecasting: models based on MARS, ANN and LR methods , 2018, Central European Journal of Operations Research.

[17]  Mo El-Hawary,et al.  SARIMA Model Forecasting of Short-Term Electrical Load Data Augmented by Fast Fourier Transform Seasonality Detection , 2019, 2019 IEEE Canadian Conference of Electrical and Computer Engineering (CCECE).

[18]  Hamed H. H. Aly.  A novel approach for harmonic tidal currents constitutions forecasting using hybrid intelligent models based on clustering methodologies , 2020 .

[19]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[20]  Ian H. Witten,et al.  Weka: Practical machine learning tools and techniques with Java implementations , 1999 .

[21]  Ta-Sung Lee,et al.  Design of an FMCW radar baseband signal processing system for automotive application , 2016, SpringerPlus.

[22]  Vandana,et al.  Survey of Nearest Neighbor Techniques , 2010, ArXiv.

[23]  Jindrich Stuchly,et al.  Solar Power Production Forecasting Based on Recurrent Neural Network , 2015, AECIA.

[24]  Yi Ren,et al.  Short-term wind speed forecasting based on autoregressive moving average with echo state network compensation , 2020 .

[25]  Lambros Ekonomou,et al.  Adaptive load forecasting of the Hellenic electric grid , 2008 .

[26]  Bodo Rosenhahn,et al.  Learning Convolutional Neural Networks for Object Detection with Very Little Training Data , 2019, Multimodal Scene Understanding.

[27]  Senén Barro,et al.  Do we need hundreds of classifiers to solve real world classification problems? , 2014, J. Mach. Learn. Res..

[28]  Mehmet Çunkas,et al.  Short-term load forecasting using fuzzy logic and ANFIS , 2015, Neural Computing and Applications.

[29]  Sudhansu Kumar Mishra,et al.  A Review of Short Term Load Forecasting using Artificial Neural Network Models , 2015 .

[30]  Vijay Kotu,et al.  Predictive Analytics and Data Mining: Concepts and Practice with RapidMiner , 2014 .

[31]  Hamed H.H. Aly.  Intelligent optimized deep learning hybrid models of neuro wavelet, Fourier Series and Recurrent Kalman Filter for tidal currents constitutions forecasting , 2020 .

[32]  Ping-Feng Pai,et al.  A Survey of Machine Learning Models in Renewable Energy Predictions , 2020, Applied Sciences.

[33]  Yacine Rezgui,et al.  Predictive modelling for solar thermal energy systems: A comparison of support vector regression, random forest, extra trees and regression trees , 2018, Journal of Cleaner Production.

[34]  Ke Yan,et al.  Short-Term Solar Irradiance Forecasting Based on a Hybrid Deep Learning Methodology , 2020, Inf..

[35]  Chih-Fong Tsai,et al.  The distance function effect on k-nearest neighbor classification for medical datasets , 2016, SpringerPlus.

[36]  Hamidreza Zareipour,et al.  Forecasting Solar Photovoltaic power production at the aggregated system level , 2014, 2014 North American Power Symposium (NAPS).

[37]  Vikas Kumar Gupta.  An Overview of Different Types of Load Forecasting Methods and the Factors Affecting the Load Forecasting , 2017 .

[38]  Ramazan Bayindir,et al.  A Novel Application of Naive Bayes Classifier in Photovoltaic Energy Prediction , 2017, 2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA).

[39]  Naresh K. Sehgal,et al.  Introduction to Machine Learning in the Cloud with Python: Concepts and Practices , 2021 .