Estimation of power outputs of two different photovoltaic solar panels with different heuristic algorithms

Abstract

The estimation of the power values obtained from photovoltaic (PV) systems is of critical importance for the reliable and economical use of solar energy panels. This estimation affects many processes, starting from the installation phase of solar panels to guiding electricity companies, energy management, and distribution. At the same time, it is necessary to detect the adaptations of solar panels in a timely manner and reach the optimal production capacity to provide the most efficient energy production. In this context, Artificial Neural Networks (ANN) were used to estimate the power values obtained from PV panels. In this study, heuristic algorithms such as Particle Swarm Optimization (PSO), Genetic Algorithm (GA), Clonal Selection Algorithm (CSA), Ant Colony Optimization, and Artificial Bee Colony (ABC) were used to estimate the power values obtained from monocrystalline and polycrystalline photovoltaic panels. In the verification of the estimation results, the most common statistical evaluation criteria, Mean Absolute Percentage Error (MAPE), Root Mean Square Error (RMSE), and Variance (R2) equations were used. The estimation values made with the PSO algorithm were the closest to the real values. 98.95% estimation was achieved in monocrystalline photovoltaic solar panels and 93.94% in polycrystalline photovoltaic solar panels.

Keywords

• Solar panel
• Artificial neural network
• Prediction
• Particle swarm optimization
• Panel types

İki farklı fotovoltaik güneş panelin güç çıkışlarının farklı sezgisel algoritmalar ile tahmini

Abstract

Fotovoltaik (FV) sistemlerden elde edilen güç değerlerinin tahmini, güneş enerjisi panellerinin güvenilir ve ekonomik bir şekilde kullanılabilmesi için kritik öneme sahiptir. Bu tahmin, güneş panellerinin kurulum aşamasından başlayarak elektrik şirketlerine rehberlik edilmesine, enerji yönetimi ve dağıtımına kadar birçok süreci etkiler. Aynı zamanda, en verimli enerji üretimi sağlamak için güneş panellerinin adaptasyonlarının zamanında tespiti ve optimal üretim kapa-sitesine ulaşılması için de gereklidir. Bu bağlamda, FV panellerinden elde edilen güç değerleri-nin tahmin edilmesi amacıyla Yapay Sinir Ağları (YSA) kullanılmıştır. Bu çalışmada, monokris-tal ve polikristal forovoktaik panellerinden elde edilen güç değerlerinin tahmini için sezgisel algoritmalardan Parçacık Sürü Optimizasyonu(PSO), Genetik Algoritma (GA), Klonal Seçim Algoritması(KSA), Karınca Kolonisi Optimizasyonu ve Yapay Arı Kolonisi (YAK) kullanılmış-tır. Tahmin sonuçlarının doğrulanmasında en yaygın istatiksel değerlendirme kriteri olan Orta-lama Mutlak Yüzde Hata (MAPE), Ortalama Karesel Hataların Karekökü (RMSE) ve Varyans (R2) eşitliklerinden yararlanılmıştır. PSO algoritması ile yapılan tahmin değerleri gerçek de-ğerlere en yakın sonuçlar olmuştur. Monokristal fotovoltaik güneş panelinde %98,95, polikristal fotovoltaik güneş panelinden ise %93,94 oranında tahmin işlemi gerçekleşmiştir.

Keywords

• güneş paneli
• yapay sinir ağları
• tahmin
• Parçacık Sürü Optimizasyonu

References

1. Gan L, Xiong Q, Chen X, Lin Z, Wen J (2025) Optimal dispatch schedule for the coordinated hydro-wind-photovoltaic system with non-priority output utilizing combined meta-heuristic. Omega 103198. https://doi.org/10.1016/j.omega.2024.103198
2. Beşkirli A, Dağ İ, Kiran MS (2024) A tree seed algorithm with multi-strategy for parameter estimation of solar photovoltaic models. Applied Soft Computing 167:112220. https://doi.org/10.1016/j.asoc.2024.112220
3. Duman S, Kahraman HT, Sonmez Y, Guvenc U, Kati M, Aras S (2022) A powerful meta-heuristic search algorithm for solving global optimization and real-world solar photovoltaic parameter estimation problems. Engineering Applications of Artificial Intelligence 111:104763, https://doi.org/10.1016/j.engappai.2022.104763
4. Yu Y, Wang K, Zhang T, Wang Y, Peng C, Gao S (2022) A population diversity-controlled differential evolution for parameter estimation of solar photovoltaic models. Sustainable Energy Technologies and Assessments 51:101938. https://doi.org/10.1016/j.seta.2021.101938
5. Liang Z, Wang Z, Mohamed AW (2024) A novel hybrid algorithm based on improved marine predators’ algorithm and equilibrium optimizer for parameter extraction of solar photovoltaic models. Heliyon 10:19. https://doi.org/10.1016/j.heliyon.2024.e38412
6. Gani A, Sekkeli M (2022) Experimental evaluation of type-2 fuzzy logic controller adapted to real environmental conditions for maximum power point tracking of solar energy systems. International Journal of Circuit Theory and Applications 50:4131-4145. https://doi.org/10.1002/cta.3374
7. Mojallizadeh MR, Badamchizadeh M, Khanmohammadi S, Sabahi M (2016) Designing a new robust sliding mode controller for maximum power point tracking of photovoltaic cells. Solar Energy 132:538-546. https://doi.org/10.1016/j.solener.2016.03.038
8. Lorenz E, Hurka J (2009) Irradiance forecasting for the power prediction of grid-connected photovoltaic systems. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 5:2-10.

9. Kudo M, Nozaki Y, Endo H (2009) Forecasting electric power generation in a photovoltaic power system for an energy network. Electrical Engineering in Japan 16-23.
10. Feng Y, Hao WP, Li HR, Cui NB, Gong DZ, Gao LL (2024) Machine learning models to quantify and map daily global solar radiation and photovoltaic power. Renewable & Sustainable Energy Reviews 118: 109393.
11. Yang M, Zhao M, Liu D, Ma M, Su X (2022) Improved Random Forest Method for Ultra-short-term Prediction of the Output Power of a Photovoltaic Cluster. Improved RFM for PV Prediction. https://doi.org/10.3389/fenrg.2021.749367
12. Jailani NLM, Dhanasegaran JK, Alkawsi G, Alkahtani AA, Phing CC, Baashar Y, Capretz LF, Al-Shetwi AQ, Tiong SK (2023) Investigating the Power of LSTM-Based Models in Solar Energy Forecasting. Processe 11:1382. https://doi.org/10.3390/pr11051382
13. Alizamir M, Othman Ahmed K, Shiri J, Fakheri Fard A, Kim S, Heddam S, Kisi O (2023) A New Insight for Daily Solar Radiation Prediction by Meteorological Data Using an Advanced Artificial Intelligence Algorithm: Deep Extreme Learning Machine Integrated with Variational Mode Decomposition Technique. Sustainabilit 15:11275. https://doi.org/10.3390/su151411275
14. Dan ARJ, Paras M, Miguel V, Shantanu C, Tomonobu S (2019) Data Fusion Based Hybrid Deep Neural Network Method for Solar PV Power Forecasting. 2019 North American Power Symposium (NAPS) https://doi.org/10.1109/NAPS46351.2019.9000331
15. Al-Ali EM, Hajji Y, Said Y, Hleili M, Alanzi AM, Laatar AH, Atri M (2023) Solar Energy Production Forecasting Based on a Hybrid CNN-LSTM-Transformer Model. Mathematics 11:676. https://doi.org/10.3390/math11030676
16. Khandakar AEH, Chowdhury M, Khoda Kazi M, Benhmed K, Touati F, Al-Hitmi M, Gonzales A (2019) Machine Learning Based Photovoltaics (PV) Power Prediction Using Different Environmental Parameters of Qatar. Energies 12:2782. https://doi.org/10.3390/en12142782
17. Rajib BR, Nowshad A, Mahmuda KM, Sanath A, Saifur R (2023) A Comparative Performance Analysis of ANN Algorithms for MPPT Energy Harvesting in Solar PV System. IEEE Access. https://doi.org/10.1109/ACCESS.2021.3096864
18. Gani A (2021) Improving dynamic efficiency of photovoltaic generation systems using adaptive type 2 fuzzy-neural network via EN 50530 test procedure. International Journal of Circuit Theory and Applications 49:3288-3940. https://doi.org/10.1002/cta.3126
19. Kececioglu OF, Gani A, Sekkeli M (2020) Design and hardware implementation based on hybrid structure for MPPT of PV system using an interval type-2 TSK fuzzy logic controller. Energies 13(7):1842. https://doi.org/10.3390/en13071842
20. Wang F, Mi Z, Su S, Zhang C (2011) A practical model for single-step power prediction of grid-connected PV plant using artificial neural network. Innovative Smart Grid Technologies Asia (ISGT) 1:1-4.
21. Qasrawi I, Awad M (2022) Prediction of the Power Output of Solar Cells Using Neural Networks: Solar Cells Energy Sector in Palestine. International Journal of Computer Science and Security (IJCSS) 1:35-42.
22. Zhu H, Li X (2016) A Power Prediction Method for Photovoltaic Power Plant Based on Wavelet Decomposition and Artificial Neural Networks. Energies 9(11). https://doi.org/10.3390/en9010011
23. Wang B, Zheng W, Yujing S, Fei W, Zhao Z, Mi Z (2016) Research on influence between photovoltaic power and module temperature and ambient temperature. 2016 IEEE International Conference on Power System Technology (POWERCON). https://doi.org/10.1109/POWERCON35682.2016
24. Chu DI, Ebunle RA (2023) Control and optimization of a hybrid solar PV–Hydro power system for off-grid applications using particle swarm optimization (PSO) and differential evolution (DE). Energy Reports 10:4253-4270. https://doi.org/10.1016/j.egyr.2023.10.080
25. Weixing L, Yunjie B, Chun Z, Zijing W, Aimin Y, Mingyu W (2024) PSO-DFNN:A particle swarm optimization enabled deep fuzzy neural network for predicting the pellet strength. Alexandria Engineering Journal 106:505-516. https://doi.org/10.1016/j.aej.2024.08.069
26. Shuai L, Ying G, Wei S, Shuhan Z, Chengcheng Z, Lisha Q, Aoxiang Y, Monan S (2024) An indicator of relative distribution probability of field-scale permafrost in Northeast China: Using a particle swarm optimization (PSO)-based indicator composition algorithm. Cold Regions Science and Technology 228:104311. https://doi.org/10.1016/j.coldregions.2024.104311
27. Elkholy MH, Tomonobu S, Mahmoud MG, Mohammed EL, Dongran S, Gul AL (2024) Implementation of a multistage predictive energy management strategy considering electric vehicles using a novel hybrid optimization technique. Journal of Cleaner Production 476: 143765. https://doi.org/10.1016/j.jclepro.2024.143765
28. Hassan MHF, Abdullrahman AA, Fahad A, Hammed OO, Walied A, Mohamed AM (2024) Optimization and uncertainty analysis of hybrid energy systems using Monte Carlo simulation integrated with genetic algorithm. Computers and Electrical Engineering 120:109833. https://doi.org/10.1016/j.compeleceng.2024.109833
29. Dareen D, Daniel F, Cédric T, Meire ERD, Cyrille P, Joao CS, Michel L, François M (2024) ROSMOSE: A web-based decision support tool for the design and optimization of industrial and urban energy systems. Energy 304:132182. https://doi.org/10.1016/j.energy.2024.132182
30. Eman A, Kabeel AE, Yehia E, Sayed AW, Warda MS (2023) Predicting solar distiller productivity using an AI Approach: Modified genetic algorithm with Multi-Layer Perceptron. Solar Energy 263:111964. https://doi.org/10.1016/j.solener.2023.111964
31. Hisham A, Chika M, Aminu Y, Sameer A, Sedat B, Abdullah A, Ahmed A, Mohammed A, Emad M, Mohamad A (2024) Semiconductors for enhanced solar photovoltaic-thermoelectric 4E performance optimization: Multi-objective genetic algorithm and machine learning approach. Results in Engineering 23:102573. https://doi.org/10.1016/j.rineng.2024.102573
32. Hangyue Z, Yanqiu C, Hongbin C, Zhengshu C (2024) Optimization and prediction of office building shading devices for energy, daylight, and view consideration using genetic and BO-LGBM algorithms. Energy and Buildings 324:114939. https://doi.org/10.1016/j.enbuild.2024.114939
33. Ramendra P, Mumtaz A, Paul K, Huma K (2019) Designing a multi-stage multivariate empirical mode decomposition coupled with ant colony optimization and random forest model to forecast monthly solar radiation. Applied Energy 236:778-792. https://doi.org/10.1016/j.apenergy.2018.12.034
34. Rama R, Venkateshwarlu S, Shaik AS, Sairaj A, Srinu R (2024) Optimizing solar panel maximum power point tracking and parasitic parameter extraction in partial shading with Enhanced Slime Mold optimization. Measurement: Sensors 33:101163. https://doi.org/10.1016/j.measen.2024.101163
35. Mohammad KK, Mustafa I, Fuat E, Babak S (2023) Feature selection by ant colony optimization and experimental assessment analysis of PV panel by reflection of mirrors perpendicularly. Renewable Energy 218:119238. https://doi.org/10.1016/j.renene.2023.119238
36. Dekun T, Xuhui L, Ruchun Z, Xuefeng F, Zhenzhen L (2025) A novel multi-objective artificial bee colony algorithm for solving the two-echelon load-dependent location-routing problem with pick-up and delivery. Engineering Applications of Artificial Intelligence 139:109636. https://doi.org/10.1016/j.engappai.2024.109636
37. Min L, Yundong Y, Aobo X, Tianhu D, Ling J (2025) A learning-based artificial bee colony algorithm for operation optimization in gas pipelines. Information Sciences 690:121593, https://doi.org/10.1016/j.ins.2024.121593
38. Alexandros Z, Christina I, Ioannis T, Grigorios B (2024) Solving large-scale instances of the urban transit routing problem with a parallel artificial bee colony-hill climbing optimization algorithm. Applied Soft Computing 167:112335. https://doi.org/10.1016/j.asoc.2024.112335
39. Deepthi P, Kanthalakshmi S (2019) An improved P&O algorithm integrated with artificial bee colony for photovoltaic systems under partial shading conditions. Solar Energy 178:37-47. https://doi.org/10.1016/j.solener.2018.12.008