Modified Auto Regressive Technique for Univariate Time Series Prediction of Solar Irradiance.

The integration of renewable resources has increased in power generation as a means to reduce the fossil fuel usage and mitigate its adverse effects on the environment. However, renewables like solar energy are stochastic in nature due to its high dependency on weather patterns. This uncertainty vastly diminishes the benefit of solar panel integration and increases the operating costs due to larger energy reserve requirement. To address this issue, a Modified Auto Regressive model, a Convolutional Neural Network and a Long Short Term Memory neural network that can accurately predict the solar irradiance are proposed. The proposed techniques are compared against each other by means of multiple error metrics of validation. The Modified Auto Regressive model has a mean absolute percentage error of 14.2%, 19.9% and 22.4% for 10 minute, 30 minute and 1 hour prediction horizons. Therefore, the Modified Auto Regressive model is proposed as the most robust method, assimilating the state of the art neural networks for the solar forecasting problem.

[1]  Yang Du,et al.  Short-Term Photovoltaic Power Forecasting Based on Long Short Term Memory Neural Network and Attention Mechanism , 2019, IEEE Access.

[2]  M. Cervantes,et al.  Utilization of Low Cost, Sky-Imaging Technology for Irradiance Forecasting of Distributed Solar Generation , 2016, 2016 IEEE Green Technologies Conference (GreenTech).

[3]  Muhammad Rafi,et al.  ATM Cash Prediction Using Time Series Approach , 2020, 2020 3rd International Conference on Computing, Mathematics and Engineering Technologies (iCoMET).

[4]  A. Moreno-Munoz,et al.  Very short term forecasting of solar radiation , 2008, 2008 33rd IEEE Photovoltaic Specialists Conference.

[5]  H. Pedro,et al.  Benefits of solar forecasting for energy imbalance markets , 2016 .

[6]  Shiwen Mao,et al.  LASSO and LSTM Integrated Temporal Model for Short-Term Solar Intensity Forecasting , 2019, IEEE Internet of Things Journal.

[7]  D. M. L. H. Dissawa,et al.  Cross-correlation based cloud motion estimation for short-term solar irradiation predictions , 2017, International Conference on Industrial and Information Systems.

[8]  Younghoon Kim,et al.  Forecasting Solar Power Using Long-Short Term Memory and Convolutional Neural Networks , 2018, IEEE Access.

[9]  Wang Jie-sheng,et al.  Auto regressive moving average (ARMA) prediction method of bank cash flow time series , 2015, 2015 34th Chinese Control Conference (CCC).

[10]  Pitshou Bokoro,et al.  Load Forecasting Using Statistical Time Series Model in a Medium Voltage Distribution Network , 2018, IECON 2018 - 44th Annual Conference of the IEEE Industrial Electronics Society.

[11]  H. R. Pota,et al.  Univariate time series prediction of solar power using a hybrid wavelet-ARMA-NARX prediction method , 2016, 2016 IEEE/PES Transmission and Distribution Conference and Exposition (T&D).

[12]  Derek Abbott,et al.  Keeping the Energy Debate Clean: How Do We Supply the World's Energy Needs? , 2010, Proceedings of the IEEE.

[13]  Wu Ji,et al.  Solar radiation prediction using statistical approaches , 2009, 2009 7th International Conference on Information, Communications and Signal Processing (ICICS).

[14]  Shanlin Yang,et al.  Optimal load dispatch of community microgrid with deep learning based solar power and load forecasting , 2019, Energy.

[15]  Na Dong,et al.  A novel convolutional neural network framework based solar irradiance prediction method , 2020 .

[16]  Oliver Kramer,et al.  Input quality aware convolutional LSTM networks for virtual marine sensors , 2018, Neurocomputing.

[17]  国際連合プロジェクトサービス機関,et al.  United Nations Office for Project Services , 1999 .

[18]  Qian Huang,et al.  Improved quantile convolutional neural network with two-stage training for daily-ahead probabilistic forecasting of photovoltaic power , 2020 .