article · Results in Engineering
Integrating photovoltaic power into electricity grids helps meet growing energy needs while cutting emissions, but the intermittent nature of solar energy poses challenges for grid stability. To address this, a hybrid deep learning model combines gated recurrent units and temporal convolutional networks to forecast global horizontal irradiance over ultra-short time horizons. The architecture extracts temporal characteristics from historical solar data using recurrent units and captures spatial correlations across meteorological variables from target and neighbouring locations using convolutional networks. Both univariate and multivariate implementations were evaluated against standard models, including standalone recurrent and convolutional networks. The univariate model, relying solely on historical solar irradiance measurements, achieved the best performance with a mean absolute error of 23.02 watts per square metre, outperforming multivariate configurations and baseline techniques to deliver accurate short-term irradiance predictions.
As solar power adoption expands worldwide, sudden variations in sunlight can disrupt electrical grid stability. Reliable ultra-short-term solar irradiance forecasts allow grid operators to anticipate fluctuations in electricity generation. By delivering more accurate near-term predictions using readily available historical solar data, this modelling approach supports smoother integration of renewable energy and helps maintain stable power network operations.
This forecasting technique could be integrated into software tools used by solar plant operators and electrical grid management utilities to optimise real-time power dispatch and grid stability. Because the method relies successfully on univariate historical irradiance data, it reduces the complexity of sourcing broader meteorological feeds. The work represents applied research validated against numerical datasets, placing it at an early computational stage prior to live grid deployment.
AI-generated from the published abstract. Always read the original work before citing.
The need for energy is increasing globally due to a several factors, including population growth and economic development. Achieving this energy demand in the face of global warming and the depletion of fossil fuels requires the use of renewable energy. Photovoltaic energy is one of the renewable energy sources that is widely used in many nations across the world. Photovoltaic (PV) energy integration into the grid has significant benefits for the environment and economy, but at high penetration levels, its intermittent nature makes system stability difficult to maintain. Accurate ultra-short-term global horizontal irradiance forecasting is necessary in order to guarantee the most optimal use of photovoltaic power production sources. For GHI forecasting, a novel GRU-TCN-based model is proposed in this paper. It is composed of two neural networks: a temporal convolutional network and a gated recurrent unit. After extracting the temporal features from time-series solar irradiance data using GRU, the spatial features are obtained from the correlation matrix of different meteorological variables of the target and its neighbor position using TCN. Univariate and multivariate GRU-TCN models have been used for GHI ultra short-term forecasting. This paper compares the univariate and multivariate GRU-TCN models with TCN, LSTM, and GRU models based on three evaluation metrics in order to investigate how different combinations of variables affect the accuracy of the GRU-TCN models for one-step forecasting. The findings indicate the adoption of a univariate model using historical data of GHI is suitable to obtain reliable forecasting with 23.02 (W/m2) in MAE as opposed to the best multivariate model that achieved 25.67 (W/m2) in MAE. According to the results, the proposed model outperforms the other models assessed and offers a practical alternative for ultra-short-term GHI forecasting.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1016/j.rineng.2024.102817
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
