Recurrent Neural Network-Based Hourly Prediction of Photovoltaic Power Output Using Meteorological Information

Liu X., Liu Q., Feng S., Ge Y., Chen H., Chen C.

Gan J., Lin X., Chen T., Fan C., Wei P., Li Z., Huo Y., Zhang F., Liu J., He T.

Accurate photovoltaic (PV) power forecasting is crucial for effective smart grid management, given the intermittent nature of PV generation. To address these challenges, this paper proposes the Temporal Bottleneck-enhanced Bidirectional Temporal Convolutional Network with Multi-Head Attention and Autoregressive (TB-BTCGA) model. It introduces a temporal bottleneck structure and Deep Residual Shrinkage Network (DRSN) into the Temporal Convolutional Network (TCN), improving feature extraction and reducing redundancy. Additionally, the model transforms the traditional TCN into a bidirectional TCN (BiTCN), allowing it to capture both past and future dependencies while expanding the receptive field with fewer layers. The integration of an autoregressive (AR) model optimizes the linear extraction of features, while the inclusion of multi-head attention and the Bidirectional Gated Recurrent Unit (BiGRU) further strengthens the model’s ability to capture both short-term and long-term dependencies in the data. Experiments on complex datasets, including weather forecast data, station meteorological data, and power data, demonstrate that the proposed TB-BTCGA model outperforms several state-of-the-art deep learning models in prediction accuracy. Specifically, in single-step forecasting using data from three PV stations in Hebei, China, the model reduces Mean Absolute Error (MAE) by 38.53% and Root Mean Square Error (RMSE) by 33.12% and increases the coefficient of determination (R2) by 7.01% compared to the baseline TCN model. Additionally, in multi-step forecasting, the model achieves a reduction of 54.26% in the best MAE and 52.64% in the best RMSE across various time horizons. These results underscore the TB-BTCGA model’s effectiveness and its strong potential for real-time photovoltaic power forecasting in smart grids.

CHEN C., CHAI L., WANG Q.

Ali R., Sajjad H., Saha T.K., Rahaman M.H., Masroor M., Roshani, Sharma A.

This study examines the present and the future trend in rainfall and temperature in the Upper Jhelum Sub-catchment located in the northwestern Himalayas in India. We used gridded rainfall and temperature data obtained from the India Meteorological Department from 1972 to 2022. Mann–Kendall test and Sen’s slope estimator were utilized to evaluate the trend and quantify changes in the pattern of rainfall and temperature variables. The random forest model was utilized to forecast rainfall and temperature (2023–2047). The accuracy of the model was assessed using performance assessors. The results revealed an annual increasing trend in temperature at the rate of 0.0096 (°C/year) and decreasing trend in rainfall at the rate of − 2.2061 (mm/year) during the pre-monsoon and − 0.8676 (mm/year) during the post-monsoon seasons. A decreasing trend in maximum temperature was recorded during the monsoon and post-monsoon seasons at the rate of − 0.0056 and − 0.0134 (°C/year), respectively. The forecast analysis revealed decreasing trend in the rainfall at the rate of − 0.9256 and − 0.03961 (mm/year) during pre-monsoon and post-monsoon seasons, respectively, while increase in minimum temperature at the rate of 0.0714 , 0.0134 and 0.006 (°C/year) during the pre-monsoon, winter and monsoon seasons, respectively. The random forest model was found effective for forecast analysis of rainfall and temperature variables. The methodological framework utilized in this study may be replicated in other geographical regions for examining climate change.

Parczyk P., Puślecki T., Burduk R.

Hu J., Lim B., Tian X., Wang K., Xu D., Zhang F., Zhang Y.

Integrating artificial intelligence (AI) into photovoltaic (PV) systems has become a revolutionary approach to improving the efficiency, reliability, and predictability of solar power generation. In this paper, we explore the impact of AI technology on PV power generation systems and its applications from a global perspective. Central to the discussion are the pivotal applications of AI in maximum power point tracking (MPPT), power forecasting, and fault detection within the PV system. On the one hand, the integration with AI technology enables the optimization and improvement of the operational efficiency of PV systems. On the other hand, new challenges have been observed, mainly in the areas of data processing and model management. Moreover, advances in AI technology and hardware upgrades will lead to the rapid global popularization of new energy sources such as solar energy, which is expected to replace traditional energy sources. Finally, we describe forward-looking solutions including transfer learning, few-shot learning, and edge computing, as well as the state of the art.

Chaaban A.K., Alfadl N.

Jannah N., Gunawan T.S., Yusoff S.H., Hanifah M.S., Sapihie S.N.

Sankara kumar S., Karthick A., Shankar R., Dharmaraj G.

Tang C., Todo Y., Kodera S., Sun R., Shimada A., Hirata A.

A novel coronavirus discovered in late 2019 (COVID-19) quickly spread into a global epidemic and, thankfully, was brought under control by 2022. Because of the virus's unknown mutations and the vaccine's waning potency, forecasting is still essential for resurgence prevention and medical resource management. Computational efficiency and long-term accuracy are two bottlenecks for national-level forecasting. This study develops a novel multivariate time series forecasting model, the densely connected highly flexible dendritic neuron model (DFDNM) to predict daily and weekly positive COVID-19 cases. DFDNM's high flexibility mechanism improves its capacity to deal with nonlinear challenges. The dense introduction of shortcut connections alleviates the vanishing and exploding gradient problems, encourages feature reuse, and improves feature extraction. To deal with the rapidly growing parameters, an improved variation of the adaptive moment estimation (AdamW) algorithm is employed as the learning algorithm for the DFDNM because of its strong optimization ability. The experimental results and statistical analysis conducted across three Japanese prefectures confirm the efficacy and feasibility of the DFDNM while outperforming various state-of-the-art machine learning models. To the best of our knowledge, the proposed DFDNM is the first to restructure the dendritic neuron model's neural architecture, demonstrating promising use in multivariate time series prediction. Because of its optimal performance, the DFDNM may serve as an important reference for national and regional government decision-makers aiming to optimize pandemic prevention and medical resource management. We also verify that DFDMN is efficiently applicable not only to COVID-19 transmission prediction, but also to more general multivariate prediction tasks. It leads us to believe that it might be applied as a promising prediction model in other fields.

El-Shahat D., Tolba A., Abouhawwash M., Abdel-Basset M.

AbstractIn late 2023, the United Nations conference on climate change (COP28), which was held in Dubai, encouraged a quick move from fossil fuels to renewable energy. Solar energy is one of the most promising forms of energy that is both sustainable and renewable. Generally, photovoltaic systems transform solar irradiance into electricity. Unfortunately, instability and intermittency in solar radiation can lead to interruptions in electricity production. The accurate forecasting of solar irradiance guarantees sustainable power production even when solar irradiance is not present. Batteries can store solar energy to be used during periods of solar absence. Additionally, deterministic models take into account the specification of technical PV systems and may be not accurate for low solar irradiance. This paper presents a comparative study for the most common Deep Learning (DL) and Machine Learning (ML) algorithms employed for short-term solar irradiance forecasting. The dataset was gathered in Islamabad during a five-year period, from 2015 to 2019, at hourly intervals with accurate meteorological sensors. Furthermore, the Grid Search Cross Validation (GSCV) with five folds is introduced to ML and DL models for optimizing the hyperparameters of these models. Several performance metrics are used to assess the algorithms, such as the Adjusted R2 score, Normalized Root Mean Square Error (NRMSE), Mean Absolute Deviation (MAD), Mean Absolute Error (MAE) and Mean Square Error (MSE). The statistical analysis shows that CNN-LSTM outperforms its counterparts of nine well-known DL models with Adjusted R2 score value of 0.984. For ML algorithms, gradient boosting regression is an effective forecasting method with Adjusted R2 score value of 0.962, beating its rivals of six ML models. Furthermore, SHAP and LIME are examples of explainable Artificial Intelligence (XAI) utilized for understanding the reasons behind the obtained results.

Febriansyah Y.I., Barus D.H., Indradjaja Marcus Brunner I.M.

Tiwari S.

With forecasting models growing more common, energy forecasting will be utilized to enhance the energy infrastructure’s layout, management, and application. Energy is one of the most significant accelerators for social and environmental improvement and improving economies. To consistently and successfully fulfill consumer electrical requirements, it is necessary to use efficient methods, make cost-effective deliveries, and adhere to a timeframe. Estimating the generation of electricity, particularly from providers of clean energy, and consumer load is essential because power plants are so reliant on the unpredictable behavior of the environment. The reliability of predictions must be increased if we are to speed up the judging process. Although big data can handle huge-scale details and detect relationships provided to deep learning methods which decrease mistakes over traditional approaches, big data had only recently started to be employed in energy forecasting. The initial phase in enhancing the dependability of clean energy production and modernizing the overall grid is to investigate artificial intelligence and machine learning technologies in this endeavor and to determine their benefits and drawbacks. A forecasting model was developed using each of the data separation approaches studied in this study. There are now technical problems with energy forecasting algorithms that need to be rectified. The current moment and forthcoming years are the timeframes for forecasting in the short term. The medium-term projection window includes the upcoming days to weeks. Long-term predictions are made in terms of either months or years. These problems were noted, and solutions were also suggested. In our view, big data is crucial for forecasts’ accuracy.

Bui Duy L., Nguyen Quang N., Doan Van B., Riva Sanseverino E., Tran Thi Tu Q., Le Thi Thuy H., Le Quang S., Le Cong T., Cu Thi Thanh H.

This article presents a research approach to enhancing the quality of short-term power output forecasting models for photovoltaic plants using a Long Short-Term Memory (LSTM) recurrent neural network. Typically, time-related indicators are used as inputs for forecasting models of PV generators. However, this study proposes replacing the time-related inputs with clear sky solar irradiance at the specific location of the power plant. This feature represents the maximum potential solar radiation that can be received at that particular location on Earth. The Ineichen/Perez model is then employed to calculate the solar irradiance. To evaluate the effectiveness of this approach, the forecasting model incorporating this new input was trained and the results were compared with those obtained from previously published models. The results show a reduction in the Mean Absolute Percentage Error (MAPE) from 3.491% to 2.766%, indicating a 24% improvement. Additionally, the Root Mean Square Error (RMSE) decreased by approximately 0.991 MW, resulting in a 45% improvement. These results demonstrate that this approach is an effective solution for enhancing the accuracy of solar power output forecasting while reducing the number of input variables.

Karakan A.

It is very important to analyze and forecast energy production for investments in renewable energy resources. In this study, the energy production of wind and solar power plants, which are among the leading renewable energy sources, was estimated using deep learning. For a solar power plant, three different solar power plants with 1MW installed power were examined. Three-year energy production data of power plants were taken. These data were used with the deep learning method long short-term memory (LSTM) and seasonal autoregressive moving average (SARIMA). Results were obtained for each dataset; they were subjected to five different (MSE, RMSE, NMSE, MAE, and MAPE) error performance measurement systems. In the LSTM model, the highest accuracy rate was 81% and the lowest accuracy rate was 59%. In the SARIMA model, the highest accuracy rate was 66% and the lowest accuracy rate was 41%. As for wind energy, wind speeds in two different places were estimated. Wind speed data were taken from meteorological stations. Datasets were tested with MAPE, R2, and RMSE error performance measurement systems. LSTM, GRU, CNN-LSTM, CNN-RNN, LSTM-GRU, and CNN-GRU deep learning methods were used in this study. The CNN-GRU model achieved a maximum accuracy of 99.81% in wind energy forecasting.