China 
Africa 
Explore chapters and articles related to this topic
Short-Term Uncertainty of Renewable Energy Generation
Published in Ning Zhang, Chongqing Kang, Ershun Du, Yi Wang, Analytics and Optimization for Renewable Energy Integration, 2019
Ning Zhang, Chongqing Kang, Ershun Du, Yi Wang
To analyze the difference in the PV output forecast error for different weather conditions, an artificial neural network model (widely used in PV forecasting) is adopted to conduct virtual forecasting and PV output verification. The verification data is taken from the Solar Power Forecasting section in the Second Global Energy Forecasting Competition in 2014 held by the Institute of Electrical and Electronics Engineers (IEEE) Working Group on Energy Forecasting [21]-[22]. The forecasted target PV power plant is located somewhere in the southern hemisphere, and the PV panels are fixed. The given data includes the hourly historical output data for the PV panels and the historical output values correspond to 12 weather-related factors. When forecasting, it is necessary to estimate the hourly PV output on the basis of the given forecast values of various relevant factors.
Integration of Distributed Renewable Energy Generation with Customer-End Energy Management System for Effective Smart Distribution Grid Operation
Published in I. M. Mujtaba, R. Srinivasan, N. O. Elbashir, The Water–Food–Energy Nexus, 2017
Rajasekhar Batchu, Kalpesh Joshi, Naran M. Pindoriya
A solar PV module output depends upon solar irradiation and module temperature and the module material. The PV power forecast model is developed based on manufacturer specifications, system location, and orientation and forecasted insolation and temperature models. First regression-based solar power forecasting model based on American Society of Heating, Refrigerating and Air-Conditioning Engineers (ASHRAE) models for insolation and temperature was by Bakirci (2009), which was developed by considering historical data from weather sensors and local weather station is considered as shown in Equation 11.1:
Expert Systems for Microgrids
Published in KTM Udayanga Hemapala, MK Perera, Smart Microgrid Systems, 2023
KTM Udayanga Hemapala, MK Perera
Considering the objective of solar power forecasting, an MLP network is selected. As the input to the MLP network, relevant weather data for the location of interest are used. The solar PV prediction using the MLP network generalizes the RL model by allowing further advancement of the system to a deep learning network. In addition, this is suitable for solar power generation prediction for a day or a year ahead for simulation purposes.
Modeling of solar photovoltaic power using a two-stage forecasting system with operation and weather parameters
Published in Energy Sources, Part A: Recovery, Utilization, and Environmental Effects, 2022
Damodhara Venkata Siva Krishna Rao Kasagani, Premalatha Manickam
The PV power can be predicted using physical prediction approach based on solar irradiance on a surface. Irradiance models will play a major role in the prediction of SPV power (Cui et al. 2019). A regional SPV power forecasting model can be better modeled using historical power data, irradiance, earth declination angle, temperature, and solar time (Zhang et al. 2019). Aerosol index data can also be better used in the development of SPV power forecasting models with great accuracy (Liu et al. 2015). Solar power forecasting model can be developed based on weather-type classifications using the ANN approach, and the accuracy of the forecast model can be enhanced further by incorporating suitable modeling parameters (Chen et al. 2011).
An Empirical Analysis of Machine Learning Algorithms for Solar Power Forecasting in a High Dimensional Uncertain Environment
Published in IETE Technical Review, 2023
Amit Rai, Ashish Shrivastava, K. C. Jana
The selection of an accurate machine learning model for solar power forecasting is a challenging issue, and numerous approaches are investigated in different works involving different ML models. So, this work provides an in-depth review and empirical analysis of solar power forecasting techniques, which includes ARIMA-based classical time-series methods to 16 different ML models. ARIMA-based solar power prediction models require comparatively fewer data points. However, their inability in long-term predictions and parameter estimation for accurate prediction limits their capability.
PV power forecasting based on data-driven models: a review
Published in International Journal of Sustainable Engineering, 2021
The integration of renewable energy sources with the electrical grid has been gaining more importance and is also creating more challenges for electrical engineers and researchers. The intermittent and uncontrollable nature of solar energy increases the complexity of grid management and adds to the difficulty in balancing the generation and consumption of electrical energy (Lara-Fanego et al. 2012; Raza et al. 2016). A balance between generation and consumption has become a great challenge for electrical operators. Voltage fluctuations, low power quality, and low stability issues are some other problems that arise due to the uncontrollable nature of solar energy. Variability, uncertainty and asynchronous operations are the main technical challenges electrical operators have to deal in integrating renewable energy sources with the power grid (Kroposki 2017). So, for optimal management of the electrical grid, accurate forecasting of solar PV power is required (Paulescu et al. 2013). Solar power forecasting is also required for scheduling, approximating the reserves, dealing generated electrical power, better operation of the power grid, reducing the cost of produced electrical energy and congestion management. As the penetration of solar PV in the grid increases, the prediction of solar power also becomes more critical due to the above-mentioned problems in the power system. Researchers also suggest using storage systems with renewable energy prediction to control electricity variation. Storage systems absorb excess power, dampen the fluctuations and maintain a continuous flow of electricity. This paper aims to discuss and compare different forecasting techniques to estimate the PV power output in two different ways, i.e. (i) direct forecasting that predicts the power directly by using historical data of PV power and (ii) indirect forecasting, which uses solar irradiation forecasting, along with other meteorological variables that directly affect solar PV power production (Rana, Koprinska, and Agelidis 2016).