Energy Shortage Failure Prediction in Photovoltaic Standalone Installations by Using Machine Learning Techniques

Guillen-Asensio, A.; Sanz-Gorrachategui, Iván; Bono-Nuez, Antonio; Bernal, Carlos; Sanz-Alcaine, José Miguel; Pérez-Cebolla, Francisco Jose

doi:10.1109/access.2021.3129930

Cited by 6 publications

(2 citation statements)

References 33 publications

(39 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A large number of representative papers in the literature [41][42][43][44][45][46][47][48][49][50][51][52][53][54] show that the NARX neural network notably outperformed the other persistence models, and it is better than linear regression models. Accordingly, comparative test results analysis with other predicting methods in terms of similar statistical error measurements (i.e., mean bias error, mean absolute error, mean square error, root mean square error, normalized root mean squared error, and/or mean absolute percentage error) confirms NARX-based model prediction performances when it is used for renewable energy forecasting, as follows: (1) wind speed prediction [48,50,55,56], (2) solar irradiance prediction [45,51], (3) energy storage systems in photovoltaic installations [52], (4) output power prediction of the PV panels [53], electric power prediction [1], and (5) electrical load forecasting for buildings [47,48,57,58]. All these indicate that the NARX-based model has been implemented since the last decade for energy prediction issues and particularly it was widely adopted for forecasting the PV power output in relevant literature [41][42][43]47,49,53,57,58].…”

Section: Narx-based Model For Pv Power Predictionmentioning

confidence: 99%

Prediction of Electric Power Production and Consumption for the CETATEA Building Using Neural Networks

Turcu

Lazar

Rednic

et al. 2022

Sensors

View full text Add to dashboard Cite

Economic and social development is hardly influenced by electric power production and consumption. In this context of the energy supply pressure, energy production and consumption must be monitored and controlled in an intelligent way. Due to the availability of large data measurements, prediction algorithms based on neural networks are widely used in accurate power prediction. Firstly, the particularity of our work is represented by the size of the dataset consisting of 4 years of continuous real-time data measurements collected from the CETATEA photovoltaic power plant, a research site for renewable energies located in Cluj-Napoca, Romania. Secondly, the high granularity of the dataset with more than 4.2 million unified production and consumption power values recorded every 30 s guarantees the overall prediction accuracy of the system. Performance metrics used to evaluate the prediction accuracy are the mean bias error, the mean square error, the convergence time of the prediction system, the test performance, and the train mean performance. Test results indicate that the predicted unified electric power production and consumption closely resembles the unified electric power measured values.

show abstract

Section: Narx-based Model For Pv Power Predictionmentioning

confidence: 99%

Prediction of Electric Power Production and Consumption for the CETATEA Building Using Neural Networks

Turcu

Lazar

Rednic

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…However, their installation costs are relatively high. In contrast, the standalone solar power system market has witnessed a significant growth in recent years [6,7]. Several factors can be attributed to this growth: Firstly, the efforts of governments across the globe to reduce carbon emissions and mitigate employed for the inverter to improve power harmonic content and reduce the size of the low-pass filter (LPF).…”

Section: Introductionmentioning

confidence: 99%

Novel Control Technology for Reducing Output Power Harmonics of Standalone Solar Power Generation Systems

Liu,

Lin,

Lin

et al. 2023

Processes

View full text Add to dashboard Cite

This study presents a standalone solar power system that incorporates a photovoltaic (PV) module, a boost converter, an H-bridge inverter, a low-pass filter (LPF), and a microcontroller unit (MCU). A novel cake sweetness maximum power point tracking (CS MPPT) algorithm and adjustable frequency and duty cycle (AFDC) control strategy has been proposed and efficiently applied to the solar power system for optimizing the system efficiency and output power quality. The experimental results show that the proposed CS MPPT algorithm achieves an efficiency of 99% under both the uniform irradiance conditions (UIC) and partial shading conditions (PSC). Subsequently, the AFDC control strategy is applied to the H-bridge inverter which improves the output AC voltage and AC current and thereby improving the power quality. The system ensures a stable 110 Vrms/60 Hz AC output voltage with only 2% total voltage harmonic distortion of voltage (THDv), and produces a high-quality output voltage with reduced LPF volume and better economic benefits. The comparative analysis demonstrates that the characteristics and the performances of the CS MPPT algorithm in combination with the AFDC control strategy is better than the existing several maximum power point tracking (MPPT) techniques and inverter control strategies. The research output affirms the potential of the proposed solar power system to fulfill the actual daily needs of electricity by harnessing the maximum power from PV modules.

show abstract

Enhancing and Optimising Solar Power Forecasting in Dhar District of India using Machine Learning

Sharma,

Mishra,

Bhola

et al. 2024

Smart Grids and Energy

View full text Add to dashboard Cite

Energy Shortage Failure Prediction in Photovoltaic Standalone Installations by Using Machine Learning Techniques

Cited by 6 publications

References 33 publications

Prediction of Electric Power Production and Consumption for the CETATEA Building Using Neural Networks

Prediction of Electric Power Production and Consumption for the CETATEA Building Using Neural Networks

Novel Control Technology for Reducing Output Power Harmonics of Standalone Solar Power Generation Systems

Enhancing and Optimising Solar Power Forecasting in Dhar District of India using Machine Learning

Contact Info

Product

Resources

About