Comparison of Power Output Forecasting on the Photovoltaic System Using Adaptive Neuro-Fuzzy Inference Systems and Particle Swarm Optimization-Artificial Neural Network Model

Dawan, Promphak; Sriprapha, Kobsak; Kittisontirak, Songkiate; Boonraksa, Terapong; Junhuathon, Nitikorn; Titiroongruang, Wisut; Niemcharoen, Surasak

doi:10.3390/en13020351

Cited by 26 publications

(9 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, linear forecast methods may produce a large deviation when there are great changes in the external environment such as weather or temperature [27,28]. Nonlinear forecast methods are more suitable for PV power output prediction, which generally employ artificial neural network (ANN), Gaussian process regression (GPR), extreme learning machine (ELM), support vector machine (SVM), and more [29,30].…”

Section: Literature Reviewmentioning

confidence: 99%

Hybrid Improved Bird Swarm Algorithm with Extreme Learning Machine for Short‐Term Power Prediction in Photovoltaic Power Generation System

Kan

Lin

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

When a photovoltaic (PV) system is connected to the electric power grid, the power system reliability may be exposed to a threat due to its inherent randomness and volatility. Consequently, predicting PV power generation becomes necessary for reasonable power distribution scheduling. A hybrid model based on an improved bird swarm algorithm (IBSA) with extreme learning machine (ELM) algorithm, i.e., IBSAELM, was developed in this study for better prediction of the short-term PV output power. The IBSA model was initially used to optimize the hidden layer threshold and input weight of the ELM model. Further, the obtained optimal parameters were input into the ELM model for predicting short-term PV power. The results revealed that the IBSAELM model is superior in terms of the prediction accuracy compared to existing methods, such as support vector machine (SVM), back propagation neural network (BP), Gaussian process regression (GPR), and bird swarm algorithm with extreme learning machine (BSAELM) models. Accordingly, it achieved great benefits in terms of the utilization efficiency of whole power generation. Furthermore, the stability of the power grid was well maintained, resulting in balanced power generation, transmission, and electricity consumption.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Hybrid Improved Bird Swarm Algorithm with Extreme Learning Machine for Short‐Term Power Prediction in Photovoltaic Power Generation System

Kan

Lin

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…The conceptual diagram of the dynamic learning procedure can be understood from Figure 2. [10], Autoencoder [11], LSTM [10][11][12], ANFIS [13], ABP [14] GRNN [1], LR [2,7], persistent [2], LM [4,6], SVR, RT [5], BR, BFGSQN, RB etc. [6], M5PDT, GPR [7], BPNN, BPNN-GA, ENN, etc.…”

Section: Necessity Of Dynamic/online Learningmentioning

confidence: 99%

Novel Mode Adaptive Artificial Neural Network for Dynamic Learning: Application in Renewable Energy Sources Power Generation Prediction

Zamee

Won

2020

Energies

View full text Add to dashboard Cite

A reasonable dataset, which is an essential factor of renewable energy forecasting model development, sometimes is not directly available. Waiting for a substantial amount of training data creates a delay for a model to participate in the electricity market. Also, inappropriate selection of dataset size may lead to inaccurate modeling. Besides, in a multivariate environment, the impact of different variables on the output is often neglected or not adequately addressed. Therefore, in this work, a novel Mode Adaptive Artificial Neural Network (MAANN) algorithm has been proposed using Spearman’s rank-order correlation, Artificial Neural Network (ANN), and population-based algorithms for the dynamic learning of renewable energy sources power generation forecasting model. The proposed algorithm has been trained and compared with three population-based algorithms: Advanced Particle Swarm Optimization (APSO), Jaya Algorithm, and Fine-Tuning Metaheuristic Algorithm (FTMA). Also, the gradient descent algorithm is considered as a base case for comparing with the population-based algorithms. The proposed algorithm has been applied in predicting the power output of a Solar Photovoltaic (PV) and Wind Turbine Energy System (WTES). Using the proposed methodology with FTMA, the error was reduced by 71.261% and 80.514% compared to the conventional fixed-sized dataset gradient descent-based training approach for Solar PV and WTES, respectively.

show abstract

“…e nonuniformity of ambient irradiance and temperature levels throughout the year has made a PV system inefficient and requires prediction [51]. e neural network algorithm delivers accurate predictions from historical data of the system [52]. e procedure of the network is to acquire historical data containing patterns of input and target measurements.…”

Section: Implementation Of the Neural Network Algorithmmentioning

confidence: 99%

Power-Efficient Hybrid Energy Storage System for Seismic Nodes

Duncan

Zungeru

Mangwala

et al. 2020

Journal of Engineering

View full text Add to dashboard Cite

Recent surveys in the energy harvesting system for seismic nodes show that, most often, a single energy source energizes the seismic system and fails most frequently. The major concern is the limited lifecycle of battery and high routine cost. Simplicity and inexperience have caused intermittent undersizing or oversizing of the system. Optimizing solar cell constraints is required. The hybridization of the lead-acid battery and supercapacitor enables the stress on the battery to lessen and increases the lifetime. An artificial neural network model is implemented to resolve the rapid input variations across the photovoltaic module. The best performance was attained at the epoch of 117 and the mean square error of 1.1176e-6 with regression values of training, test, and validation at 0.99647, 0.99724, and 0.99534, respectively. The paper presents simulations of Nsukka seismic node as a case study and to deepen the understanding of the system. The significant contributions of the study are (1) identification of the considerations of the PV system at a typical remote seismic node through energy transducer and storage modelling, (2) optimal sizing of PV module and lead-acid battery, and, lastly, (3) hybridization of the energy storage systems (the battery and supercapacitor) to enable the energy harvesting system to maximize the available ambient irradiance. The results show the neural network model delivered efficient power with duty cycles across the converter and relatively less complexities, while the supercapacitor complemented the lead-acid battery and delivered an overall efficiency of about 75 % .

show abstract

Comparison of Power Output Forecasting on the Photovoltaic System Using Adaptive Neuro-Fuzzy Inference Systems and Particle Swarm Optimization-Artificial Neural Network Model

Cited by 26 publications

References 22 publications

Hybrid Improved Bird Swarm Algorithm with Extreme Learning Machine for Short‐Term Power Prediction in Photovoltaic Power Generation System

Hybrid Improved Bird Swarm Algorithm with Extreme Learning Machine for Short‐Term Power Prediction in Photovoltaic Power Generation System

Novel Mode Adaptive Artificial Neural Network for Dynamic Learning: Application in Renewable Energy Sources Power Generation Prediction

Power-Efficient Hybrid Energy Storage System for Seismic Nodes

Contact Info

Product

Resources

About