Solar Photovoltaic Power Forecasting in Jordan using Artificial Neural Networks

Abstract

In this paper, Artificial Neural Networks (ANNs) are used to study the correlations between solar irradiance and solar photovoltaic (PV) output power which can be used for the development of a real-time prediction model to predict the next day produced power. Solar irradiance records were measured by ASU weather station located on the campus of Applied Science Private University (ASU), Amman, Jordan and the solar PV power outputs were extracted from the installed 264KWp power plant at the university. Intensive training experiments were carried out on 19249 records of data to find the optimum NN configurations and the testing results show excellent overall performance in the prediction of next 24 hours output power in KW reaching a Root Mean Square Error (RMSE) value of 0.0721. This research shows that machine learning algorithms hold some promise for the prediction of power production based on various weather conditions and measures which help in the management of energy flows and the optimisation of integrating PV plants into power systems.

A Predictive Model for Solar Photovoltaic Power using the Levenberg-Marquardt and Bayesian Regularization Algorithms and Real-Time Weather Data

“…Two years of hourly data were processed to associate the available www.ijacsa.thesai.org One day ahead ANN MAE 0.122 [12] One day ahead APVF RMSE, MAE 0.121, 0.0597 [12] One day ahead MPVF RMSE, MAE 0.1195, 0.0646 [13] One day ahead PHANN NMAE, WMAE 50% error reduction [14] One day ahead SVM R 2 correlation coefficients 90% [15] One temperature and global radiation records to the generated PV power. The associated datasets were used as a source of learning for a neural network model that use real-time weather data to provide PV power forecasts for the next 24 hours.…”

“…In our previous work [15], we proposed an initial real-time forecasting model for the PV power production using ANNs based on the available solar irradiation records for the last few days. In this research work, ANNs were optimized comparing the Levenberg-Marquardt (LM) and Bayesian Regularization (BR) algorithms to analyze and correlate the available data of temperature, solar irradiance, timing, and the generated solar PV power.…”

PVPF tool: an automatedWeb application for real-time photovoltaic power forecasting

“…PV power production data is available from the local web-boxes and from online sunnyportal system that can be accessed at www.sunnyportal.com providing hourly records as shown in Figure 1. A wide range of measurement equipments for weather conditions are installed at ASU weather station as described in [20]. More information about these equipments is available at the REC website [22] (see Figure 2).…”

“…In [18] reviewed forecasting methods up to 2017, and they introduced an important information for researchers and engineers who are modeling and planning PV systems. Our first forecasting model was proposed in [19] for the solar PV power production using neural networks and solar radiation records. Later in [20], the model has been improved by adding more weather inputs such as the temperature and time and two backpropagation algorithms were applied to neural networks: the Levenberg-Marquardt (LM) and the Bayesian Regularization (BR) algorithms.…”

“…Our first forecasting model was proposed in [19] for the solar PV power production using neural networks and solar radiation records. Later in [20], the model has been improved by adding more weather inputs such as the temperature and time and two backpropagation algorithms were applied to neural networks: the Levenberg-Marquardt (LM) and the Bayesian Regularization (BR) algorithms. In this paper, we are presenting ISSN: 2088-8708 a novel web application that implements our previous research into a real-time prediction system providing power production forecasts for the next 24 hours.…”