Energies · 2024 · 13 citations · 36 references
ComputingComputer ScienceMachine LearningRenewable Energy SystemsWeather ForecastingDeep LearningRenewable EnergySolar Energy SystemsSolar IrradianceSolar RadiationTime Series PredictionAttentionConvolutional Neural NetworksEvaluation MetricsGlobal Horizontal IrradianceMean Absolute ErrorMultilayer PerceptronSolar Energy Resource AssessmentSolar Resource Assessment
The global horizontal irradiance (GHI) is the most important metric for evaluating solar resources. The accurate prediction of GHI is of great significance for effectively assessing solar energy resources and selecting photovoltaic power stations. Considering the time series nature of the GHI and monitoring sites dispersed over different latitudes, longitudes, and altitudes, this study proposes a model combining deep neural networks and deep convolutional neural networks for the multi-step prediction of GHI. The model utilizes parallel temporal convolutional networks and gate recurrent unit attention for the prediction, and the final prediction result is obtained by multilayer perceptron. The results show that, compared to the second-ranked algorithm, the proposed model improves the evaluation metrics of mean absolute error, mean absolute percentage error, and root mean square error by 24.4%, 33.33%, and 24.3%, respectively.
36
Takuya Akiba, Shotaro Sano, Toshihiko Yanase et al. · 2019 · 7.4K citations
Electrical load-temperature CNN for residential load forecasting
Maryam Imani · Energy · 2021 · 207 citations
Machine learning for site-adaptation and solar radiation forecasting
Gabriel Narváez, Luis Felipe Giraldo, Michaël Bressan et al. · Renewable Energy · 2020 · 191 citations
A TCN-Based Hybrid Forecasting Framework for Hours-Ahead Utility-Scale PV Forecasting
Yiyan Li, Lidong Song, Si Zhang et al. · IEEE Transactions on Smart Grid · 2023 · 153 citations · Full text
Computing, Data Science, Forecasting +14