A New Method for Generating Short-Term Power Forecasting Based on Artificial Neural Networks and Optimization Methods for Solar Photovoltaic Power Plants

In recent times, solar PV power plants have been used worldwide due to their high solar energy potential. Although the PV power plants are highly preferred, the main disadvantage of the system is that the output power characteristics of the system are unstable. As PV power plant system is connected to the grid side, unbalanced power flow effects all systems controls. In addition, the load capacitys is not exactly known. For this reason, it has become an important issue to be known correctly in PV output power and their time-dependent changes. The main aim of this work is to eliminate power plant instability due to the output power imbalance. For the short-term, power prediction is estimated by real-time data of 1 MW PV power plant in use. Estimation power data are compared with real-time data and precision of the proposed method is demonstrated. In the first phase, traditional artificial intelligence algorithms are used. Then, these algorithms are trained with swarm based optimization methods and the performance analyses are presented in detail. Among all the algorithms used, the algorithm with the lowest error is determined. Thus, this study provides useful information and techniques to help researchers who are interested in planning and modeling PV power plants.

[1]  Wen-Yeau Chang,et al.  A Literature Review of Wind Forecasting Methods , 2014 .

[2]  Francesco Grimaccia,et al.  Hybrid model for hourly forecast of photovoltaic and wind power , 2013, 2013 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE).

[3]  Philippe Lauret,et al.  Probabilistic forecasting of the solar irradiance with recursive ARMA and GARCH models , 2016 .

[4]  Samia Nefti-Meziani,et al.  A Comprehensive Review of Swarm Optimization Algorithms , 2015, PloS one.

[5]  A. Bensoussan,et al.  Forecasting of daily global solar radiation using wavelet transform-coupled Gaussian process regression: Case study in Spain , 2016, 2016 IEEE Innovative Smart Grid Technologies - Asia (ISGT-Asia).

[6]  Henrik Madsen,et al.  Multi-site solar power forecasting using gradient boosted regression trees , 2017 .

[7]  E. Izgi,et al.  Short–mid-term solar power prediction by using artificial neural networks , 2012 .

[8]  Monjur Mourshed,et al.  Forecasting methods in energy planning models , 2018 .

[9]  Bernhard Sick,et al.  Deep Learning for solar power forecasting — An approach using AutoEncoder and LSTM Neural Networks , 2016, 2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC).

[10]  S. N. Singh,et al.  Solar irradiance forecasting using wavelet neural network , 2017, 2017 IEEE PES Asia-Pacific Power and Energy Engineering Conference (APPEEC).

[11]  Mithulananthan Nadarajah,et al.  A multivariate ensemble framework for short term solar photovoltaic output power forecast , 2017, 2017 IEEE Power & Energy Society General Meeting.

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

[13]  B. Sivaneasan,et al.  Solar Forecasting using ANN with Fuzzy Logic Pre-processing , 2017 .

[14]  Badia Amrouche,et al.  Artificial neural network based daily local forecasting for global solar radiation , 2014 .

[15]  Youcef Messlem,et al.  Daily global solar radiation forecasting over a desert area using NAR neural networks comparison with conventional methods , 2015, 2015 International Conference on Renewable Energy Research and Applications (ICRERA).

[16]  Niranjan Nayak,et al.  Solar power forecasting using a hybrid EMD-ELM method , 2017, 2017 International Conference on Circuit ,Power and Computing Technologies (ICCPCT).

[17]  Chul-Hwan Kim,et al.  Determination Method of Insolation Prediction With Fuzzy and Applying Neural Network for Long-Term Ahead PV Power Output Correction , 2013, IEEE Transactions on Sustainable Energy.

[18]  Shiwen Mao,et al.  Adaptive Learning Hybrid Model for Solar Intensity Forecasting , 2018, IEEE Transactions on Industrial Informatics.

[19]  Yoshiaki Toyoda,et al.  An Improvement of Particle Swarm Optimization with A Neighborhood Search Algorithm , 2007 .

[20]  K. P. Moustris,et al.  One day-ahead forecasting of mean hourly global solar irradiation for energy management systems purposes using artificial neural network modeling , 2016 .

[21]  Eduardo F. Fernández,et al.  A methodology based on dynamic artificial neural network for short-term forecasting of the power output of a PV generator , 2014 .

[22]  Kok Soon Tey,et al.  Forecasting of photovoltaic power generation and model optimization: A review , 2018 .

[23]  Rohit Bhakar,et al.  Optimized Support Vector Regression models for short term solar radiation forecasting in smart environment , 2016, 2016 IEEE Region 10 Conference (TENCON).

[24]  N. D. Kaushika,et al.  Artificial neural network model based on interrelationship of direct, diffuse and global solar radiations , 2014 .

[25]  Jian Xiao,et al.  Short-Term Solar Power Forecasting Based on Weighted Gaussian Process Regression , 2018, IEEE Transactions on Industrial Electronics.

[26]  Niranjan Nayak,et al.  Solar photovoltaic power forecasting using optimized modified extreme learning machine technique , 2018, Engineering Science and Technology, an International Journal.

[27]  Anil Kumar Sao,et al.  Solar radiation forecasting with multiple parameters neural networks , 2015 .

[28]  Amelia Binti Abdul Razak,et al.  Investigation of the Effect Temperature on Photovoltaic (PV) Panel Output Performance , 2016 .

[29]  A. G. Bakirtzis,et al.  Application of time series and artificial neural network models in short-term forecasting of PV power generation , 2013, 2013 48th International Universities' Power Engineering Conference (UPEC).

[30]  Isabel Praça,et al.  Application of a Hybrid Neural Fuzzy Inference System to Forecast Solar Intensity , 2016, 2016 27th International Workshop on Database and Expert Systems Applications (DEXA).

[31]  Mojtaba Ahmadieh Khanesar,et al.  Hybrid multi-objective forecasting of solar photovoltaic output using Kalman filter based interval type-2 fuzzy logic system , 2017, 2017 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE).

[32]  Dazhi Yang,et al.  Satellite image analysis and a hybrid ESSS/ANN model to forecast solar irradiance in the tropics , 2014 .

[33]  A. Massi Pavan,et al.  A hybrid model (SARIMA-SVM) for short-term power forecasting of a small-scale grid-connected photovoltaic plant , 2013 .

[34]  Hoay Beng Gooi,et al.  Solar radiation forecast based on fuzzy logic and neural networks , 2013 .

[35]  Tek Tjing Lie,et al.  Hourly global solar irradiation forecasting for New Zealand , 2015 .

[36]  Mehdi Ferdowsi,et al.  Solar irradiance forecasting using deep recurrent neural networks , 2017, 2017 IEEE 6th International Conference on Renewable Energy Research and Applications (ICRERA).

[37]  Soteris A. Kalogirou,et al.  Artificial neural network-based model for estimating the produced power of a photovoltaic module , 2013 .

[38]  Miguel Brito,et al.  Impact of network layout and time resolution on spatio-temporal solar forecasting , 2018 .

[39]  Recep Çakmak,et al.  A day ahead hourly solar radiation forecasting by artificial neural networks: A case study for Trabzon province , 2017, 2017 International Artificial Intelligence and Data Processing Symposium (IDAP).

[40]  Mohamed Abuella,et al.  Solar power forecasting using artificial neural networks , 2015, 2015 North American Power Symposium (NAPS).

[41]  Francesco Grimaccia,et al.  Hybrid model analysis and validation for PV energy production forecasting , 2014, 2014 International Joint Conference on Neural Networks (IJCNN).

[42]  Vikas Arora,et al.  Data Analysis to Generate Models Based on Neural Network and Regression for Solar Power Generation Forecasting , 2016, 2016 7th International Conference on Intelligent Systems, Modelling and Simulation (ISMS).

[43]  S. Premrudeepreechacharn,et al.  Forecasting of solar irradiance for solar power plants by artificial neural network , 2015, 2015 IEEE Innovative Smart Grid Technologies - Asia (ISGT ASIA).

[44]  A. Mellit,et al.  A 24-h forecast of solar irradiance using artificial neural network: Application for performance prediction of a grid-connected PV plant at Trieste, Italy , 2010 .

[45]  Cristian Rodríguez Rivero,et al.  Very short term forecasting in global solar irradiance using linear and nonlinear models , 2017, 2017 IEEE Workshop on Power Electronics and Power Quality Applications (PEPQA).

[46]  L. D. Monache,et al.  An application of the ECMWF Ensemble Prediction System for short-term solar power forecasting , 2016 .

[47]  Gilles Notton,et al.  Estimation of 5-min time-step data of tilted solar global irradiation using ANN (Artificial Neural Network) model , 2014 .

[48]  E. Praynlin,et al.  Solar radiation forecasting using artificial neural network , 2017, 2017 Innovations in Power and Advanced Computing Technologies (i-PACT).

[49]  Truong Q. Nguyen,et al.  Forecasting of Solar Photovoltaic System Power Generation Using Wavelet Decomposition and Bias-Compensated Random Forest , 2017, 2017 Ninth Annual IEEE Green Technologies Conference (GreenTech).

[50]  Mohammad Aldeen,et al.  Residential Demand Forecasting With Solar-Battery Systems: A Survey-Less Approach , 2018, IEEE Transactions on Sustainable Energy.

[51]  Frederico G. Guimarães,et al.  Very short-term solar forecasting using fuzzy time series , 2017, 2017 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE).

[52]  Sue Ellen Haupt,et al.  Solar Forecasting: Methods, Challenges, and Performance , 2015, IEEE Power and Energy Magazine.

[53]  Gilles Notton,et al.  Neural network approach to estimate 10-min solar global irradiation values on tilted planes , 2013 .

[54]  Mohammad Bagher Menhaj,et al.  A novel clustering approach for short-term solar radiation forecasting , 2015 .

[55]  Saifur Rahman,et al.  Hour-ahead solar PV power forecasting using SVR based approach , 2017, 2017 IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT).