Forecasting Of Power Generation Research Articles

Solar Power Generation Forecasting in Smart Cities and Explanation Based on Explainable AI

Solar Power Generation Forecasting in Smart Cities and Explanation Based on Explainable AI

A Case Study on Deep Learning for Photovoltaic Power Forecasting Combining Satellite and Ground Data

The increasing demand for clean energy presents challenges in energy supply management, largely due to their intermittency. Photovoltaic power generation, in specific, is greatly affected by weather factors, which may render power grids susceptible to instability, quality and balance issues. In this context, photovoltaic power generation forecasting is crucial not only to enhance the management of diverse energy sources through generation planning, but also to ensure widespread adoption of photovoltaic energy. To address the predictability issue in generation, this study aims to investigate the combination of satellite data with meteorological data to predict the energy generation potential in photovoltaic panels within 30, 60, 120, and 180-minute horizons. For this purpose, images from the GOES-16 satellite are used in combination with data from a ground-based weather station, located at Florianópolis – Santa Catarina – Brazil. The data is fed to a convolutional neural network, where convolutions are employed to extract features from the satellite images, aiming to establish a relationship with solar irradiation. The output of the convolutional network serves as input for a multilayer perceptron network, which utilizes the data to predict the Global Horizontal Irradiance (GHI). Our results support that models incorporating satellite images provide forecasts approximately 41% better for the 30-minute horizon and 21% better for the 180-minute horizon, when compared to models without satellite images.

Development of a Power Generation Forecast Model that Reflects the Degradation Conditions of Solar Modules: For AI Technique Approach

Development of a Power Generation Forecast Model that Reflects the Degradation Conditions of Solar Modules: For AI Technique Approach

Wavelet CNN‐LSTM time series forecasting of electricity power generation considering biomass thermal systems

AbstractThe use of biomass as a renewable energy source for electricity generation has gained attention due to its sustainability and environmental benefits. However, the intermittent electricity demand poses challenges for optimizing electricity generation in thermal systems. Time series forecasting techniques are crucial in addressing these challenges by providing accurate predictions of biomass availability and electricity generation. Here, wavelet transform is applied for denoising, convolutional neural networks (CNN) are used to extract features of the time series, and long short‐term memory (LSTM) is applied to perform the predictions. The result of the mean absolute percentage error equal to 0.0148 shows that the wavelet CNN‐LSTM is a promising machine‐learning methodology for electricity generation forecasting. Additionally, this paper discusses the importance of model evaluation techniques and validation strategies to assess the performance of forecasting models in real‐world applications. The major contribution of this paper is related to improving forecasting using a hybrid method that outperforms other models based on deep learning. Finally, future research directions and potential advancements in time series forecasting for biomass thermal systems are outlined to foster continued innovation in sustainable energy generation.

Global Horizontal Irradiance in Brazil: A Comparative Study of Reanalysis Datasets with Ground-Based Data

Renewable energy sources are increasing globally, mainly due to efforts to achieve net zero emissions. In Brazil, solar photovoltaic electricity generation has grown substantially in recent years, with the installed capacity rising from 2455 MW in 2018 to 47,033 MW in August 2024. However, the intermittency of solar energy increases the challenges of forecasting solar generation, making it more difficult for decision-makers to plan flexible and efficient distribution systems. In addition, to forecast power generation to support grid expansion, it is essential to have adequate data sources, but measured climate data in Brazil is limited and does not cover the entire country. To address this problem, this study evaluates the global horizontal irradiance (GHI) of four global reanalysis datasets—MERRA-2, ERA5, ERA5-Land, and CFSv2—at 35 locations across Brazil. The GHI time series from reanalysis was compared with ground-based measurements to assess its ability to represent hourly GHI in Brazil. Results indicate that MERRA-2 performed best in 90% of the locations studied, considering the root mean squared error. These findings will help advance solar forecasting by offering an alternative in regions with limited observational time series measurements through the use of reanalysis datasets.

Analysis of Inverter Efficiency Using Photovoltaic Power Generation Element Parameters

Photovoltaic power generation is influenced not only by variable environmental factors, such as solar radiation, temperature, and humidity, but also by the condition of equipment, including solar modules and inverters. In order to preserve energy production, it is essential to maintain and operate the equipment in optimal condition, which makes it crucial to determine the condition of the equipment in advance. This paper proposes a method of determining a degradation of efficiency by focusing on photovoltaic equipment, especially inverters, using LSTM (Long Short-Term Memory) for maintenance. The deterioration in the efficiency of the inverter is set based on the power generation predicted through the LSTM model. To this end, a correlation analysis and a linear analysis were performed between the power generation data collected at the power plant to learn the power generation prediction model and the data collected by the environmental sensor. With this analysis, a model was trained using solar radiation data and power data that are highly correlated with power generation. The results of the evaluation of the model’s performance show that it achieves a MAPE of 7.36, an RMSE of 27.91, a MAE of 18.43, and an R2 of 0.97. The verified model is applied to the power generation data of the selected inverters for the years 2020, 2021, and 2022. Through statistical analysis, it was determined that the error rate in 2022, the third year of its operation, increased by 159.55W on average from the error rate of the power generation forecast in 2020, the first year of operation. This indicates a 0.75% decrease in the inverter’s efficiency compared to the inverter’s power generation capacity. Therefore, it is judged that it can be applied effectively to analyses of inverter efficiency in the operation of photovoltaic plants.

Explainable AI and optimized solar power generation forecasting model based on environmental conditions.

This paper proposes a model called X-LSTM-EO, which integrates explainable artificial intelligence (XAI), long short-term memory (LSTM), and equilibrium optimizer (EO) to reliably forecast solar power generation. The LSTM component forecasts power generation rates based on environmental conditions, while the EO component optimizes the LSTM model's hyper-parameters through training. The XAI-based Local Interpretable and Model-independent Explanation (LIME) is adapted to identify the critical factors that influence the accuracy of the power generation forecasts model in smart solar systems. The effectiveness of the proposed X-LSTM-EO model is evaluated through the use of five metrics; R-squared (R2), root mean square error (RMSE), coefficient of variation (COV), mean absolute error (MAE), and efficiency coefficient (EC). The proposed model gains values 0.99, 0.46, 0.35, 0.229, and 0.95, for R2, RMSE, COV, MAE, and EC respectively. The results of this paper improve the performance of the original model's conventional LSTM, where the improvement rate is; 148%, 21%, 27%, 20%, 134% for R2, RMSE, COV, MAE, and EC respectively. The performance of LSTM is compared with other machine learning algorithm such as Decision tree (DT), Linear regression (LR) and Gradient Boosting. It was shown that the LSTM model worked better than DT and LR when the results were compared. Additionally, the PSO optimizer was employed instead of the EO optimizer to validate the outcomes, which further demonstrated the efficacy of the EO optimizer. The experimental results and simulations demonstrate that the proposed model can accurately estimate PV power generation in response to abrupt changes in power generation patterns. Moreover, the proposed model might assist in optimizing the operations of photovoltaic power units. The proposed model is implemented utilizing TensorFlow and Keras within the Google Collab environment.

The Comparison of GRU and LSTM in Solar Power Generation Forecasting Application

Precise forecasting of solar power generation is essential for optimizing the incorporation of renewable energy into the electrical grid and maintaining the stability of energy systems. This paper offers a thorough comparative examination of Long Short-Term Memory (LSTM) networks and Gated Recurrent Unit (GRU) networks in forecasting solar power generation. Both models were assessed for predicted accuracy and computational efficiency, employing essential performance indicators including Mean Absolute Error (MAE) and R-squared (R²). The efficacy of LSTM and GRU in forecasting is assessed using a real-world dataset. Comprehensive experimental data demonstrate that the GRU model surpasses the LSTM model.

Unfixed Seasonal Partition Based on Symbolic Aggregate Approximation for Forecasting Solar Power Generation Using Deep Learning

Solar energy is an important alternative energy source, and it is essential to forecast solar power generation for efficient power management. Due to the seasonal characteristics of weather features, seasonal data partition strategies help develop prediction models that perform better in extreme weather-related situations. Most existing studies rely on fixed season partitions, such as meteorological and astronomical, where the start and end dates are specific. However, even if the countries are in the same Northern or Southern Hemisphere, seasonal changes can occur due to abnormal climates such as global warming. Therefore, we propose a novel unfixed seasonal data partition based on Symbolic Aggregate Approximation (SAX) to forecast solar power generation. Here, symbolic representations generated by SAX are used to select seasonal features and obtain seasonal criteria. We then employ two-layer stacked LSTM and combine predictions from various seasonal features and partitions through ensemble methods. The datasets used in the experiments are from real-world solar panel plants such as in Gyeongju, South Korea; and in California, USA. The results of the experiments show that the proposed methods perform better than non-partitioned or fixed-partitioned solar power generation forecasts. They outperform them by 2.2% to 3.5%; and 1.6% to 6.5% in the Gyeongju and California datasets, respectively.

Wind power forecasting with metaheuristic-based feature selection and neural networks

Accurate forecasting of wind power generation is crucial for ensuring a stable and efficient energy supply, reducing the environmental impact of energy production, and promoting a cleaner and more sustainable energy supply. Inaccurate forecasts can lead to a mismatch between wind power generation and energy demand, resulting in wasted energy, increased emissions, and reduced grid stability. Therefore, improving the accuracy of wind power generation forecasting is essential for optimizing energy storage and grid management, reducing the reliance on fossil fuels, decreasing greenhouse gas emissions, and promoting a more sustainable energy future. This study proposes an innovative approach to enhance wind power generation forecasting accuracy by leveraging the strengths of metaheuristic algorithms for feature selection and integrating them with Neural Networks (NN). Specifically, five distinct algorithms - Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Ant Colony Optimization (ACO), Teaching-Learning-Based Optimization (TLBO), and Evolutionary Mating Algorithm (EMA) - are integrated with NN model to identify optimal feature subsets from a comprehensive dataset of 18 diverse features. The results show that the GA consistently outperforms other algorithms in selecting the most influential features, leading to improved precision in wind power predictions. Notably, the GA achieves the best root mean square error (RMSE) of 37.1837 and the best mean absolute error (MAE) of 18.6313, outperforming the other algorithms and demonstrating the importance of feature selection in improving the accuracy of wind power forecasting. This innovative framework advances the field of renewable energy forecasting and provides valuable insights into optimizing feature sets for improved predictions across diverse domains.

Predictive Modeling and Forecasting of Solar Power Generation Using Machine Learning Techniques

The purpose of this research study is to investigate the predictive modelling and forecasting of solar power generation by utilising a variety of machine learning approaches. The paper addresses the significant obstacle that is presented by the variable production of solar energy, which is a barrier to the effective incorporation of solar power into the network of electrical power distribution systems. This research investigates the application of machine learning models such as Bayesian Ridge Regression, Gradient Boosting, and Linear Regression. The research makes use of historical meteorological data and solar power output to investigate the application of these models. The effectiveness of these models in estimating the amount of solar energy that will be produced under a variety of different weather situations is being investigated. Based on the findings, it is evident that the application of machine learning techniques has the potential to considerably improve the accuracy of solar power projections. This, in turn, will facilitate better grid integration and promote wider adoption of solar energy products. Through the demonstration of the potential of advanced machine learning approaches in enhancing the reliability and efficiency of solar power generation, this study makes a contribution to the expanding body of literature on the forecasting of renewable energy sources.

Research and application of a novel graph convolutional RVFL and evolutionary equilibrium optimizer algorithm considering spatial factors in ultra-short-term solar power prediction

With the increasing proportion of photovoltaic power generation, solar power prediction systems have become more important. Accurate photovoltaic power prediction can assist the grid dispatch department in formulating effective power scheduling plans, improving grid stability and the capacity to accommodate solar energy. To address the challenges in solar power generation forecasting, the paper proposes a new neural network model called Graph Convolutional Random Vector Functional Link (GCRVFL). The output layer of this model includes both nonlinear transformed features from the hidden layer and the original input features, while also considering the spatial characteristics among photovoltaic sites. Furthermore, Singular Spectrum Analysis (SSA) is utilized to decompose the original solar power time series, extracting different component sequences from the photovoltaic power time series. Opposite based learning and cross-mutation are employed to improve the original Equilibrium Optimizer (EO) algorithm, resulting in an Evolutionary Equilibrium Optimizer (EEO) algorithm. The EEO algorithm is employed to optimize the weight threshold of GCRVFL, leading to a novel photovoltaic power prediction model called SSA-EEO-GCRVFL. Through four datasets and eight control experiments, it can be observed that the proposed model achieves the best predictive performance and is capable of fulfilling the task of photovoltaic power prediction.

Machine learning-based energy management and power forecasting in grid-connected microgrids with multiple distributed energy sources

The growing integration of renewable energy sources into grid-connected microgrids has created new challenges in power generation forecasting and energy management. This paper explores the use of advanced machine learning algorithms, specifically Support Vector Regression (SVR), to enhance the efficiency and reliability of these systems. The proposed SVR algorithm leverages comprehensive historical energy production data, detailed weather patterns, and dynamic grid conditions to accurately forecast power generation. Our model demonstrated significantly lower error metrics compared to traditional linear regression models, achieving a Mean Squared Error of 2.002 for solar PV and 3.059 for wind power forecasting. The Mean Absolute Error was reduced to 0.547 for solar PV and 0.825 for wind scenarios, and the Root Mean Squared Error (RMSE) was 1.415 for solar PV and 1.749 for wind power, showcasing the model’s superior accuracy. Enhanced predictive accuracy directly contributes to optimized resource allocation, enabling more precise control of energy generation schedules and reducing the reliance on external power sources. The application of our SVR model resulted in an 8.4% reduction in overall operating costs, highlighting its effectiveness in improving energy management efficiency. Furthermore, the system’s ability to predict fluctuations in energy output allowed for adaptive real-time energy management, reducing grid stress and enhancing system stability. This approach led to a 10% improvement in the balance between supply and demand, a 15% reduction in peak load demand, and a 12% increase in the utilization of renewable energy sources. Our approach enhances grid stability by better balancing supply and demand, mitigating the variability and intermittency of renewable energy sources. These advancements promote a more sustainable integration of renewable energy into the microgrid, contributing to a cleaner, more resilient, and efficient energy infrastructure. The findings of this research provide valuable insights into the development of intelligent energy systems capable of adapting to changing conditions, paving the way for future innovations in energy management. Additionally, this work underscores the potential of machine learning to revolutionize energy management practices by providing more accurate, reliable, and cost-effective solutions for integrating renewable energy into existing grid infrastructures.

Predicting power and solar energy using neural networks and PCA with meteorological parameters from Diass and Taïba Ndiaye

The excessive reliance on conventional fossil fuel-based resources poses a significant threat to our environment. To mitigate this impact, it has become increasingly crucial to increase the integration of intermittent and non-polluting energy sources into our electrical grids. However, while this higher penetration rate brings benefits such as improved producer satisfaction and reduced fossil fuel consumption, it also presents challenges for traditional non-smart electrical networks. To promote intermittent energy sources effectively and maintain a balance between consumption and production, accurate forecasting of these energy outputs plays a vital role. This research paper focuses on studying the application of artificial neural networks for predicting the power and energy output of the Diass solar power plant in the short and medium term. The proposed approach utilizes not only the meteorological data from the city where the power plant is located but also data from a nearby city with a data acquisition station. Principal component analysis (PCA) is employed to select the relevant variables for the prediction model. Furthermore, the results obtained from our approach are compared to existing literature that solely uses meteorological data from the power plant's location. The comparison shows that our method achieves more satisfactory results, with mean absolute errors and root mean square errors of 0.0223 KWh and 0.003 KWh, respectively, and a prediction accuracy of 94.57% in terms of energy and power. It is worth noting that the computational resource requirements for our approach are higher, with simulation times ranging between 1788 seconds and 2201 seconds. By utilizing a broader range of data sources and employing advanced techniques like artificial neural networks, this research contributes to improving the accuracy of solar power generation forecasts. The findings highlight the potential of incorporating additional data inputs and advanced modeling techniques to enhance the performance of renewable energy systems, paving the way for a more sustainable and efficient energy future.

Dispatchable generation analysis and prediction by using machine learning: A case study of South Africa

South African power sector has a total installed capacity of about 58,095 MW. However, in the past five years, the nation's energy sector has been struggling to generate a daily average power of about 23,526 MW. Therefore, the use of machine learning technique is crucial to observing the short-term forecast of South African dispatchable power generation and its effects on the nation's economic growth. The choice of SARIMAX as the forecasting tool in this study is due to its flexibility, simplicity, accuracy, and robustness. This study has carried out time series modeling of the South African dispatchable power generation between the period: 2019 and 2023 by using the seasonal auto-regressive moving average with exogenous variables (SARIMAX). The accuracy of the model was measured by the root mean square error (RMSE), mean absolute error (MAE), coefficient of determination (R2), mean bias error (MBE), and mean absolute percentage error (MAPE). When subjected to ARIMA analysis, the predictive model produced the following metrics: RMSE of 669.05 MW, MAE of 575.07 MW, R2 value of 0.937, MBE of -2.45, and MAPE of 0.023. However, upon employing the SARIMAX method, notable improvements were observed, with the metrics indicating RMSE of 469.92 MW, MAE of 330.80 MW, R2 of 0.969, MBE of -0.09 MW, and MAPE of 0.015. The improved accuracy provided by the SARIMAX predictive method confirms the importance of considering seasonal effects in dispatchable generation prediction models. Dispatchable power generation prediction is an important route to achieving sustainable energy for a nation's development, social well-being, and security of life and properties.

Machine Learning Models for Solar Power Generation Forecasting in Microgrid Application Implications for Smart Cities

In the context of escalating concerns about environmental sustainability in smart cities, solar power and other renewable energy sources have emerged as pivotal players in the global effort to curtail greenhouse gas emissions and combat climate change. The precise prediction of solar power generation holds a critical role in the seamless integration and effective management of renewable energy systems within microgrids. This research delves into a comparative analysis of two machine learning models, specifically the Light Gradient Boosting Machine (LGBM) and K Nearest Neighbors (KNN), with the objective of forecasting solar power generation in microgrid applications. The study meticulously evaluates these models’ accuracy, reliability, training times, and memory usage, providing detailed experimental insights into optimizing solar energy utilization and driving environmental sustainability forward. The comparison between the LGBM and KNN models reveals significant performance differences. The LGBM model demonstrates superior accuracy with an R-squared of 0.84 compared to KNN’s 0.77, along with lower Root Mean Squared Error (RMSE: 5.77 vs. 6.93) and Mean Absolute Error (MAE: 3.93 vs. 4.34). However, the LGBM model requires longer training times (120 s vs. 90 s) and higher memory usage (500 MB vs. 300 MB). Despite these computational differences, the LGBM model exhibits stability across diverse time frames and seasons, showing robustness in handling outliers. These findings underscore its suitability for microgrid applications, offering enhanced energy management strategies crucial for advancing environmental sustainability. This research provides essential insights into sustainable practices and lays the foundation for a cleaner energy future, emphasizing the importance of accurate solar power forecasting in microgrid planning and operation.

Harnessing open data for hourly power generation forecasting in newly commissioned photovoltaic power plants

This paper introduces a novel approach for forecasting hourly outputs in photovoltaic power plants. The approach was tailored to the needs of energy cooperatives by focusing on availability/cost, ease of use, reliability, and replicability. Following the cooperative values, the proposed methodology relies entirely on open data; primarily on the data from the Photovoltaic Geographical Information System (PVGIS). Additionally, the approach was developed to perform short-term (next-day), hourly power-generation forecasts for power plants without or with limited on-site historical records. Seven predictive algorithms were utilized to model the power outputs. The algorithm that performed best (CatBoost) was optimized by using the Sequential Feature Selection and Optuna (automatic hyperparameter optimization software framework). The validation of the developed model was conducted on the actual data from three photovoltaic plants. On these samples, the model performed with a coefficient of determination ranging from 0.83 to 0.9 with only 5 input parameters. Even though the approach was designed to meet the needs of energy cooperatives, it is not limited to such purposes.

О влиянии неопределенностей на прогнозы ветрового ресурса и выработки электроэнергии

The annual power generation of a wind farm is one of the most important indicators determining the profitability of a wind power project. The methods used to estimate the annual power generation of a wind farm have to consider uncertainties at all stages of the project life cycle. When developing a financial model of a wind power project, it is required to consider information about uncertainties to reduce the error and increase the reliability of the project. Specialists of various countries are improving the efficiency of wind power plants, studying wind energy resources, as well as assessing the efficiency of their use. However, special studies do not pay due attention to the problem of assessing the impact of various uncertainties on the forecasts of wind resource and power generation. Two methods are proposed to calculate uncertainties. They are a deterministic method based on the assumption of independence of various uncertainties, and a Monte Carlo method that simulates the behavior of a physical system many times. The paper considers the uncertainties to be considered during the design of a wind farm and presents the variation ranges. The authors have presented the plots of power generation with various levels of probability of being reached or exceeded the total uncertainty for three variants. It is shown that considering the various uncertainties allows a power generation forecast to be made with increased accuracy. The results obtained are necessary to develop a wind measurement data processing model that allows us to forecast electricity generation by existing wind power plants with increased accuracy.

Power generation forecasting for solar plants based on Dynamic Bayesian networks by fusing multi-source information

A Dynamic Bayesian network (DBN) model for solar power generation forecasting in photovoltaic (PV) solar plants is proposed in this paper. The key idea is to fuse sensor data, operational indicators, meteorological data, lagged output power information, and model errors for more accurate short-term (e.g., hours) and mid-term (e.g., days to weeks) power generation forecasting. The proposed DBN augments automated data-driven structure learning with expert knowledge encoding using continuous and categorical data given constraints to represent causal relationships within a solar inverter system. In addition, an error compensation mechanism that uses an error node to capture the temporal fluctuation caused by system degradation or failures is proposed to capture temporal fluctuation. The effectiveness of the DBN on solar power generation forecasting was evaluated by rolling window analysis with one-year testing data collected from a local solar plant. The proposed DBN is compared with four state-of-art methods including support-vector regression (SVR), k-nearest neighbors (kNN), artificial neural network (ANN), and long short-term memory (LSTM) models. The results show that the proposed DBN achieves better accuracy in general, and it is not as data-hungry as some neural network-based models. The proposed DBN is also shown to have robust and consistent forecasting power with different forecasting horizons. The accuracy is 92 %–95 % from 1 h to one week ahead forecasting.

Hybrid machine learning model combining of CNN-LSTM-RF for time series forecasting of Solar Power Generation

Forecasting solar power generation (SPG) is vital for the development and planning of power systems, offering significant benefits in terms of technical performance and financial efficiency. It enhances system reliability, safety, stability and it reduces the operational costs. This paper's primary goal is to develop models that can precisely forecast solar power generation by analyzing real first-hand dataset of solar power. The value of these forecasting models lies in their ability to anticipate future solar power generation, thus optimizing resource use and minimizing expenses. To achieve this, the study utilizes various classical machine learning, deep learning, and hybrid machine learning techniques, including Long Short-Term Memory (LSTM), Gated Recurrent Units (GRU), Recurrent Neural Networks (RNN), Random Forest (RF), Support Vector Regression (SVR), Bi-directional LSTM (Bi-LSTM), and Convolutional Neural Network (CNN). Among these, the hybrid model combining CNN-LSTM-RF demonstrated superior accuracy with R-squared of 92 %, a Root Mean Square Error (RMSE) of 0.07 kW, and a Mean Absolute Error (MAE) of 0.05 kW. This indicates that the hybrid machine learning model combining of CNN-LSTM-RF is effective in forecasting solar power generation.