Solar Power Generation Forecasting via Multimodal Feature Fusion (Student Abstract)

Multimodal ultra-short-term probabilistic solar power forecasting with generative AI and Transformer

Renewable energy sources such as PV solar or wind power are intermittent and non-dispatchable. Massive integration of these resources into the electric mix poses some challenges to meeting power generation with demand. Hence, improving power generation forecasting has raised much interest. This work assesses the market value of enhanced PV solar power generation forecasting. Then, we analyse the different agents present in the electricity system. We link the studied agents to the proposed market values based on both analyses. Improving the accuracy of RES forecasting has massive potential as the sector grows and new agents arise. It can have reactive values like reducing imbalances or proactive values such as participating in intraday markets or exercising energy arbitrage. However, accurate forecasting can also lead to opportunistic values that can be exploited by malicious agents if they are not adequately regulated.

Solar photovoltaic (PV) power generation has strong intermittency and volatility due to its high dependence on solar radiation and other meteorological factors. Therefore, the negative impact of grid-connected PV on power systems has become one of the constraints in the development of large scale PV systems. Accurate forecasting of solar power generation and flexible planning and operational measures are of great significance to ensure safe, stable, and economical operation of a system with high penetration of solar generation at transmission and distribution levels. In this paper, studies on the following aspects are reviewed: (1) this paper comprehensively expounds the research on forecasting techniques of PV power generation output. (2) In view of the new challenge brought by the integration of high proportion solar generation to the frequency stability of power grid, this paper analyzes the mechanisms of influence between them and introduces the current technical route of PV power generation participating in system frequency regulation. (3) This section reviews the feasible measures that facilitate the inter-regional and wide-area consumption of intermittent solar power generation. At the end of this paper, combined with the actual demand of the development of power grid and PV power generation, the problems that need further attention in the future are prospected.

Accurately predicting the power produced during solar power generation can greatly reduce the impact of the randomness and volatility of power generation on the stability of the power grid system, which is beneficial for its balanced operation and optimized dispatch and reduces operating costs. Solar PV power generation depends on the weather conditions, such as temperature, relative humidity, rainfall (precipitation), global solar radiation, wind speed, etc., and it is prone to large fluctuations under different weather conditions. Its power generation is characterized by randomness, volatility, and intermittency. Recently, the demand for further investigation into the uncertainty of short-term solar PV power generation prediction and its effective use in many applications in renewable energy sources has increased. In order to improve the predictive accuracy of the output power of solar PV power generation and develop a precise predictive model, the authors used predictive algorithms for the output power of a solar PV power generation system. Moreover, since short-term solar PV power forecasting is an important aspect of optimizing the operation and control of renewable energy systems and electricity markets, this review focuses on the predictive models of solar PV power generation, which can be verified in the daily planning and operation of a smart grid system. In addition, the predictive methods identified in the reviewed literature are classified according to the input data source, and the case studies and examples proposed are analyzed in detail. The contributions, advantages, and disadvantages of the predictive probabilistic methods are compared. Finally, future studies on short-term solar PV power forecasting are proposed.

With solar panels already installed, users can monitor and manage their electricity consumption via a smartphone application. The system allows for parameter settings under the Active Power Control Mode, which includes both Zero Export and non-Zero Export operation modes (No Limit). It is important for users to understand the details of each function. This article presents the application of a three-phase inverter for solar PV power generation and energy management. When the Zero Export function is enabled, a traditional three-phase inverter will generate power equal to the total load and distribute it evenly across all three phases. If any phase requires more power than what the inverter provides, the additional power will be drawn from the utility grid. Conversely, if any phase uses less power than the inverter output, the excess power will be exported back to the grid. On the other hand, for users who are allowed to sell electricity back to the grid, the Zero Export function is disabled. In this case, phases that consume more power than what the solar system provides will import a smaller amount from the grid, while phases that consume less than the inverter output will export more to the grid compared to when the Zero Export mode is enabled. This results in lower electricity bills and, if permitted to sell electricity back, allows for higher revenue from solar power generation. Newer inverter models are now capable of phase-independent operation, supporting unbalanced three-phase power output. Furthermore, integrating battery storage to store excess solar energy for use during peak demand periods can reduce dependence on the grid and improve the voltage quality of nearby transformers. When combined with TOU (Time-of-Use) metering, this setup leads to increased energy savings, lower electricity costs, and a shorter payback period for solar PV investments.

In the last few decades, Renewable energy has received remarkable attention. This is partially because fossil fuels are depleting and the necessity for energy is rising because of the increasing population of the world. Among renewable sources of energy, solar energy is one such type that is becoming increasingly popular because it is inexhaustible, clean, and reliable. Solar radiation is obtained as heat and light that can be converted by solar thermal power generation into valuable thermal energy or electricity generation. With regard to efficiency and financial viability, the availability of trusted data on solar radiation is crucial to forecast the performance of solar power plants at different places in the country. This paper describes a general integrated structure for assessing land suitability for ideal positioning of photovoltaic solar energy panels based on a variety of geographic information system (GIS), remote sensing methods. The Location Viability Assessment, i.e. the areas appropriate for harvesting Solar Energy, is measured based on Global, Diffuse, Direct Solar Radiation Data that estimates the potential of the Solar Power Generation sites. Two interrelated steps were implemented in this study. First, Remote Sensing was used, including LANDSAT 8 satellite data, to extract the study area’s land use/land cover map. Second, the Digital Elevation Model (DEM) was used to model the research zone map of aspect angles and slope maps. These results indicate the potential sites for Solar Power Generation.

Accurate solar power forecasting is essential to mitigate the variability and uncertainty of solar power generation and integrate renewable energy sources into power grids. A multi-step Long Short Term Memory (LSTM)-based model is proposed for solar power generation forecasting using online learning. To capture daily fluctuations in solar energy patterns, the model employs a dynamic sunrise–sunset data window operation, ensuring that the relevant transitions in solar irradiance are accurately represented in the training set. For seasonality analysis, the variance of the correlation of features with solar power output is determined across different months of the year. The simulation results show that the proposed LSTM-based online learning model achieves a mean absolute percentage error of less than 1%. The results demonstrate that incorporating solar transition period information significantly enhances the forecasting accuracy of the proposed model. Online learning exhibits higher performance than batch learning in terms of forecasting accuracy.

Volumetric Risk Hedging Strategies and Basis Risk Premium for Solar Power

Ensuring long term investment for large scale solar power stations: Hedging instruments for green power

Hydrogen production by wind and solar hybrid power generation is an important means to solve the strong randomness and high volatility of wind and solar power generation. In this paper, the permanent magnet direct-drive wind turbine, photovoltaic power generation unit, battery pack, and electrolyzer are assembled in the AC bus, and the mathematical model of the wind-solar hydrogen storage coupled power generation system and the simulation model in PSCAD/EMTDC are established. An energy coordination control strategy is designed. After simulation, the proposed control strategy can effectively reduce the rate of curtailment of wind and solar power, and stabilize the fluctuation of wind and solar power generation. It verifies that the established model is correct and the control strategy is effective and feasible.

To mitigate and adapt to the ongoing climate change, the decarbonization of the economy requires a radical change in our energy production and consumption patterns. A robust finding of existing studies is that renewable energy sources - and more specifically wind and solar power generation - are expected to represent a major share of the power mix in the future. Due to their higher dependency on meteorological variable a better understanding of the variability of VRE outputs across different temporal and geographical scales thus becomes critical. Of particular interest is the study of tight grid conditions with periods of coincidence between low wind and solar output because they will condition flexibility requirements. Our work addresses these research questions based on an analysis of the variability of solar PV and wind power generation capacity factors provided by the Copernicus service C3S energy. The Copernicus C3S energy service deals with the transformation of climate variables (reanalysis, seasonal forecast and climate projection) into energy variables (wind, PV, hydro and energy demand principally). To take into consideration the dependance between the solar and wind resource the combined variability has been evaluated for different wind to PV share. In addition, the coupling of different kind of storage technologies has been anticipated by evaluating the variability on different time scales ranging from hour to month. Finally, focusing on extreme conditions, the results of the variability analysis was synthesized in a couple of boundary conditions that capture the impact of the meteorological variability on estimated joint wind and solar power output. The added value of the proposed methodology will be illustrated for a simple case in France.

Due to rapidly changing sky conditions, the available solar irradiance for energy generation is subject to wide swings in amplitude. As the market penetration of solar energy continues to increase rapidly, these variations in solar power generation are beginning to have an impact on grid stability and increased wear on power switches. Solar power forecasting plays a critical role in operations for Independent System Operators (ISOs) and utilities. Accurate forecasts help maintain grid reliability, optimize generation from renewables, and reduce operating costs. Of particular interest to the ISOs and utilities are sudden changes in solar irradiance, termed “ramp events,” due to the movement of clouds. One significant impact of ramp events on the grid is additional ancillary service requirements necessary to manage such variability. Ramp events can also cause voltage fluctuations in the distribution grids and trigger actions of automated line equipment (e.g., tap changers), leading to additional maintenance costs. In high penetration solar regions, forecasts must be made for both transmission-connected and distribution-connected resources – either behind the meter or in front of it. Particularly for distributed solar energy resources, forecasting can be a challenge due to the lack of visibility of the energy resource. Brookhaven National Laboratory (BNL) has been working towards nowcasting Global Horizontal Irradiance (GHI) using low-cost technologies for several years now. The Solar NowCasting technology being developed by BNL is a 0 – 30 min solar “nowcasting” technology applicable to a scale covering both large generating facilities and residential, distributed solar installations that relies on a network of ground-based high-definition (HD) cameras and surface pyranometers. GHI forecasts are being produced for both regions using 8 ground-based HD cameras and at least 2 surface pyranometers. When stitched together, the camera images can be used to forecast the impact of clouds on available solar irradiance over a domain of ~50 km². Phase I of the project was the engineering scale up conceptual design stage. Phase II was the initial field test and demonstration, in which the technology was scaled up by a factor of 20 times and successfully demonstrated in eastern Long Island. In Phase III, an additional forecasting network was added in upstate NY and both networks are currently being operated until at least a full year of data is gathered by the Albany network to allow for the collection of sufficient data to evaluate performance against the persistence and smart persistence models using the Solar Arbiter.

Renewable energies, carbon neutrality, and sustainable practices have become an important aim for many countries. Solar power generation has drawn much consideration where maintenance of solar panels is an essential task due to the natural and other mechanical circumstances. In this paper, we have proposed a deep learning (DL) approach for the detection of faults in solar panels. The proposed system uses an unmanned aerial vehicle (UAV) equipped with a thermal camera and GPS for acquiring thermal images and localization of the fault in solar panels. An improved version of You only look once (YOLOv3-tiny) is employed as a DL model for the detection of the fault and then transmitted that information using Long-Term Evolution (LTE) to a remote server for visualization. The performance of the proposed model is compared with the current default YOLOv3-tiny, where high performance was achieved by the proposed DL model.

In the solar energy application system, in order to improve the efficiency of solar cells and the utilization of light energy, the paper studies the solar tracking system with concentrating device and using germanium solar cells. This paper compares the differences between germanium cells and silicon cells in terms of photoelectric conversion efficiency and output characteristics, and demonstrates the superiority of germanium solar cells. Several common types of concen-trating devices such as Fresnel lenses, trough concentrators, tower concentrators and disc con-centrators were listed, and the disc concentrator was finally selected considering the concen-trating performance and cost. The paper also analyzes the solar operation law and the charac-teristics of various tracking devices, and on the basis of comprehensive analysis of the ad-vantages and disadvantages of various tracking devices, a hybrid tracking scheme is proposed. After completing the design of the system structure, the efficiency and cost of the traditional fixed solar system and the concentrated germanium solar power generation sunny system are compared and analyzed by SIMULINK modeling, and the results show that the solar energy utilization rate and power generation efficiency of the system designed in this paper are greatly improved, which verifies the effectiveness and economy of the system. The concentrating germanium solar power generation system not only adopts germanium cells with better photo-electric characteristics, but also adds a concentrating device and a sun tracking device, which greatly improves the efficiency of solar power generation. And the volume of the device is not large, which can realize the promotion of small home solar energy systems.

Solar power generation is highly uncertain and intermittent due to its strong dependence on climate and meteorological factors. In this study, we have proposed a bagging ensemble of artificial neural network (BagANN) model with weighted averaging optimized using grey wolf optimization (GWO) and investigate the impact of climatic and meteorological factors on the output power prediction of the solar power plant. Initially, we have preprocessed the data by applying feature engineering, normalization techniques, and appropriate features are selected for power prediction. The hyperparameters of the BagANN model are tuned and optimized using the GWO technique to improve the models predictive accuracy. Experiments are conducted to evaluate the generalization performance of the developed model using five-fold and 10-fold cross-validation techniques. The performance results are assessed using RMSE, coefficient of determination ( R 2 ), adjusted ( R 2 ), and the MAPE. Results show that the BagANN with weighted averaging has a higher level of precision with R 2 of 98.5% predictive accuracy, has less prediction errors with 0.1263 MSE and 0.0267 MAPE than the other developed models. From the result, it is evident that the BagANN model has significant improvements compared to other models available in the literature in terms of robustness of the prediction and predictive accuracy.