Photovoltaic Generation Research Articles

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.

Based on Deep Learning Model and Flink Streaming Computing Short Term Photovoltaic Power Generation Prediction for Suburban Distribution Network

With the advancement of global energy internet construction, accurate prediction of new energy generation power such as photovoltaic is an important foundation for ensuring the safety and economic working of new power systems. A short-term photovoltaic power generation prediction method for suburban distribution networks based on deep learning model fusion and Flink flow calculation is proposed to address the challenges of complex power grids, diversified disturbance factors, and isolated monitoring points. This method uses Bi directional Long Short Term Memory(BiLSTM) to extract cross sequential nonlinear characteristic of photovoltaic power generation time series data. Compared with standard LSTM, BiLSTM can consider both historical and future information simultaneously, thus extracting richer extracted features from power generation time series data. This method also integrates attention mechanism to capture the importance distribution of historical temporal features for power generation prediction, effectively solving the problem of long-term temporal dependence in standard LSTM models. The Flink streaming computing framework embeds a trained BiLSTM-Attention photovoltaic power generation prediction model, enabling real-time prediction and monitoring analysis of photovoltaic power generation at various monitoring points in the suburban distribution network. This article uses a dataset of a suburban photovoltaic power station for validation, and trains the model with historical power generation data, meteorological factors, weather types, seasons, and other information as inputs. The BiLSTM-Attention fusion model studys the temporal characteristics of power generation, and has high accuracy in predicting short-term photovoltaic power generation in different scenarios. The Flink streaming computing platform can not only process high throughput predicted power data, but also has low time delay.

A Short-term PV Power Prediction and Uncertainty Analysis Model Based on CEEMDAN and AHA-BP

The stochastic and intermittent nature of photovoltaic (PV) generation brings a series of scheduling problems to the power system. An effective prediction of PV power is essential to minimize the impact of uncertainty. Therefore, this paper presents an integrated prediction model with complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), the artificial hummingbird algorithm (AHA), and the BP neural network (BPNN) for predicting power generation from PV power plants, and a methodology for uncertainty analysis by using the nonparametric kernel density estimation (NPKDE). First, one month of PV power is decomposed into an array of components using CEEMDAN. Then, the weights and thresholds of the BPNN are optimized by using AHA. These components are trained using the BPNN. Finally, the final prediction results are obtained by superimposing the components, and NPKDE is employed to compute the probability density and confidence interval of the prediction error. The proposed prediction method demonstrates superior predictive performance in comparison with other models. Also, the NPKDE approach better describes the accuracy of the probability density distribution.

Energy management and demand side management framework for nano-grid under various utility strategies and consumer’s preference

This research proposes a day-ahead scheduling utilizing both demand side management (DSM), and Energy Management (EM) in a grid-tied nanogrid comprises of photovoltaic, battery, and diesel generator for optimizing the generation cost and the energy not supplied (at grid-outage). Wider terminology is introduced to combine both load controllability (considered in traditional DSM), and interval capability to accommodate additional loads defined as flexible, non-flexible, and semi-flexible intervals. Moreover, the user selection for EM or combined operation of EM with DSM at different degrees of interval flexibility is defined as user preference. In addition, three utility’s operations are considered denoted as fixed rate pricing (FRP), time-of-use (ToU) pricing, and FRP with grid-outage. Hence, the suggested framework utilizes the opportunities of generation diversity, the electricity pricing strategy, and the load flexibility. The obtained result show that, DSM with flexible intervals reduces the cost by 21.02%, 25.23%, and 18.15% for FRP, ToU, and FRP with grid-outage scenarios respectively. And cost reduction by 20.41%, 22.42%, and 17.81% for DSM with semi-flexible intervals and 16.24%, 21.15%, and 13.8% for DSM with non-flexible intervals. This cost reduction is associated with full utilization of renewable energy generation and reduction of the energy from/to battery which enhances its lifetime or reduces the required battery size during design stage for cost and provisions saving in flexible and semi-flexible intervals. A hybrid optimization technique of Moth-flame optimization algorithm, and Lagrange’s multiplier is proposed and confirms its effectiveness with detailed comparison with other techniques.

Design of reliable standalone utility-scale pumped hydroelectric storage powered by PV/Wind hybrid renewable system

With a target of 35 % renewable energy in the country’s energy mix by 2030, the goal of this research is to support the Libyan government’s plan to maximize the use of environmentally friendly and sustainable energy sources. This will be accomplished by making effective use of the region’s plentiful natural resources. The feasibility of wind and solar energy has been established by local research, and the presence of highlands that can store pumped hydropower (PHS) makes hybrid renewable energy systems (HRES) even more feasible. These systems might offer a sizable edge over competitors in the regional energy market. In this study, PHS was utilized to stabilize electricity production in addition to storing energy. A hydropower turbine provides electricity to the load, and the PHS system is powered by a PV/wind supply. By lowering the volatility of wind and photovoltaic power generation, the suggested system could offer a more dependable renewable energy source without requiring complicated control mechanisms. This strategy could encourage a wider adoption of renewable energy, which could be especially advantageous for developing nations. Under particular load and climate conditions, the energy production of different solar PV array and wind turbine farm configurations was estimated using the System Advisor Model (SAM) software. The ideal HRES configuration consists of a 290 MW wind farm, a 154 MW solar PV field, and a 508 MW PHS system. This configuration will provide 100 % of the annual electrical demand of 513 GWh, plus a 20 % safety margin. The levelized cost of energy (LCOE), estimated at $211.65/MWh, is reduced by this configuration. It is anticipated that the $929.02 million initial investment will be recovered in 11 years, and the system will turn a profit in the following 9 years. Also, the planned HRES will stop 532.17 tons of CO2 emissions from being released each year.

Research and Case Application of Zero-Carbon Buildings Based on Multi-System Integration Function

This study focuses on developing and implementing zero-carbon buildings through the integration of multiple systems to meet China’s carbon neutrality goals. It emphasizes the significant role of the building sector in carbon emissions and highlights the challenge of increasing energy consumption conflicting with China’s “dual carbon” targets. To address this, the research proposes a comprehensive framework that combines multifunctional envelope structure (MES) systems, photovoltaic power generation, energy storage, direct current (DC) systems, flexible energy management (PEDF), and regional energy stations. This framework integrates different technologies such as phase change materials, radiation cooling, and carbon mineralized cement, aiming to reduce carbon emissions throughout the building’s lifecycle. The method has been successfully applied in the Yazhou Bay Zero Carbon Post Station project in Sanya, Hainan, with precise calculations of carbon emission reductions. The carbon emission calculations revealed a reduction of 44.13 tons of CO2 annually, totaling 1103.31 tons over 25 years, primarily due to the rooftop photovoltaic systems. It demonstrates that the multi-system integration can reduce carbon emissions and contribute to China’s broader carbon neutrality goals. This approach, if widely adopted, could accelerate the transition to carbon-neutral buildings in China.

Fuel Cell-Based Distributed Robust Optimal Scheduling for Combined Heat and Power Supply

At present, the safe operation of integrated energy systems is significantly affected by the considerable uncertainty inherent to wind and photovoltaic power generation. Based on this, this paper proposes an optimal scheduling model for integrated electricity, heat, and hydrogen-based energy systems on distributed robust optimization (DRO). Firstly, a combined heat and power microgrid system considering hydrogen energy systems was constructed based on the thermoelectric cogeneration characteristics of fuel cells and electrolyzers. Then, a data-driven two-stage distribution robust optimization scheduling model is built by combining typical historical data of wind power output, photovoltaic power output, and load. The results show that the distributed robust method reduces the running cost by 6% compared to the deterministic method. The proposed method and model are capable of meeting the demand for thermoelectric loads within the microgrid in a more cost-effective manner, thereby achieving stable and independent operation of the system.

Scenario Generation Based on Ant Colony Optimization for Modelling Stochastic Variables in Power Systems

Uncertainty is an important subject in optimization problems due to the unpredictable nature of real variables in the power system area, which can condition the solution’s accuracy. The effective modelling of stochastic variables can contribute to the reduction in losses in the system under evaluation and facilitate the implementation of an effective response in advance. To model uncertainty variables, the most extended technique is the scenario generation (SG) method. This method evaluates possible combinations of complete curves. Classical scenario generation methods are founded on probability distributions or robust stochastic optimization. This paper proposes a novel approach for constructing scenarios using the Ant Colony Optimization (ACO) algorithm, referred to as ACO-SG. This methodology does not require a previous statistical study of uncertainty data to generate new scenarios. A historical dataset and the desired number of scenarios are the inputs inserted into the algorithm. In the case study, the algorithm used historical data from the Savona Campus Smart Polygeneration Microgrid of the University of Genoa. The approach was applied to generate scenarios of photovoltaic generation and building consumption. The low values of the Euclidean distance were used in order to check the validity of the scenarios. Moreover, the error deviation of the scenarios generated with the goal of daily power were 1.77% and 0.144% for the cases of PV generation and building consumption, respectively. The different results for both cases are explained by the characteristics of the specific cases. Despite these different results, both were significantly low, which indicates the capability of the algorithm to generate any kind of feature within curves and its adaptability to any case of SG.

An attention fused sequence -to-sequence convolutional neural network for accurate solar irradiance forecasting and prediction using sky images

The challenge of accurately forecasting ultra-short-term solar irradiance for photovoltaic systems is complicated by rapidly changing weather, and while ground-based sky images offer potential improvements, effectively extracting spatiotemporal data from these images remains a significant hurdle for current computer vision models. A new hybrid model, "An Attention Fused Sequence-to-Sequence Convolutional Neural Network," is being developed to address this challenge. The model predicts intra-hour GHI, DNI, and DHI with a 10-min lead time by combining a Convolutional Neural Network (for spatial feature extraction from sky images), an attention mechanism (to focus on relevant regions), and a sequence-to-sequence model (for temporal feature extraction from time-series data). The proposed Model is trained using the NREL Solar Radiation Research Laboratory Dataset while evaluating the model with the Mean Bias Error, Mean Absolute Error, Root Mean Squared Error, R Squared, and forecasting skill score. The 10-min and sequence length 2 interval is considered to be the best performing across most of the evaluation metrics with an MBE value is 2.321 W/m2, MAE value of 39.490 W/m2, RMSE value of 62.086 W/m2, R2 value is 0.909 W/m2, FSS value of 23.589 W/m2 and an MBE of 4.876 W/m2, MAE of 56.887 W/m2, RMSE of 85.346 W/m2, R2 of 0.834 and FSS of 24.881 W/m2 respectively. Furthermore, the sensitivity analysis reveals that the proposed model's performance is influenced by both the sequence length and the lead time. The proposed framework outperforms other techniques for ultra-short-term PV generation forecasting, demonstrating its potential for practical deployment in PV systems to improve grid reliability and energy management.

Optimal micro-pump-storage system for the average Greek hotel with PV generation

In this paper, a modern micro-scale pumped hydro storage system that is specifically designed to operate in coordination with photovoltaics installed at the roof of an average Greek hotel is presented. The fictitious hotel chosen as a case study, displays the energy profile of an average sea-side hotel around the Mediterranean Sea, while photovoltaics’ energy generation is assumed to follow the typical production profile of such sites. Pumped hydro storage and photovoltaic generation, size and cost have been appropriately modeled so that they realistically simulate their operational scheme, while also considering the spatial and technical characteristics and limitations of such projects. Results derived from the implementation of such a scheme into the Average Greek hotel demonstrated significant monetary benefits, accompanied with a substantial net annual profit and low payback period of the investment.

Forecasting Wholesale Electricity Market Prices Considering Bidding Conditions Using Price Sensitivity

This article proposes a sophisticated forecasting model to predict significant price volatility on the Japan Electric Power Exchange (JEPX) due to the growing influence of solar photovoltaics (PV) in the energy mix. As solar power generation continues to grow, it significantly impacts the daily and seasonal price trends in the market. This method employs a neural network that integrates daily prices, net electricity demand (total demand minus PV output), and underlying time‐series data to determine the objective variable, defined as the deviation from the average price over the past week. Incorporating price sensitivity data from JEPX increases the accuracy of the model. These data reflect how prices respond to market‐specified bid adjustments, including a variety of bidding, providing a nuanced understanding of market responses. The results demonstrate that adding multiple price sensitivities significantly improves the model's ability to detect price spikes and provides a robust tool for transmission and distribution system operators to manage risk and optimize their market strategies in an increasingly renewable energy‐dominated landscape. This approach not only addresses daily and seasonal price fluctuations but also aligns with broader sustainability goals as the share of solar PV generation continues to grow.

A Janus Spectrally Selective Glazing Toward All-Season Energy-Efficient Windows.

Windows offer the most promising avenue for mitigating energy consumption and reducing greenhouse gas emissions. However, the balance between comfortable natural lighting and all-season energy savings is often neglected in extensive explorations of energy-efficient windows. Herein, a Janus glazing is proposed that enables the switch of passive radiative cooling and heating under the precondition of conveying sufficient natural light. Measurement results indicate that the Janus window maintains a visible transmittance of 0.47, while possesses a near-infrared (NIR) reflectivity/absorptivity of 0.75/0.71 and a mid-infrared (MIR) emissivity of 0.94/0.13 for the cooling and heating modes, respectively. As demonstrated by the outdoor test, the Janus window realizes a reduction of 7.1°C for room cooling and an increase of 0.4°C for room heating compared with commercial low-e window, potentially conserving 13%-53% of the total building energy consumption across China. Meanwhile, attributed to the photothermal effect, the Janus window can elevate the surface temperature by 6.1°C compared with the low-e window, which can effectively reduce fogging occurrences on the window surface for ensuring sunlight entrance in the cold-weather conditions. This strategy offers novel prospects for enhancing energy efficiency in diverse applications, including architectural windows, greenhouse cultivation, photovoltaic generation, etc.

Smart Grid Forecasting with MIMO Models: A Comparative Study of Machine Learning Techniques for Day-Ahead Residual Load Prediction

With the fast expansion of intermittent renewable energy sources in the upcoming smart grids, simple and accurate day-ahead systems for residual load forecasts are urgently needed. Machine learning strategies can facilitate towards drastic cost minimizations in terms of operating-reserves avoidance to compensate the mismatches between the actual and forecasted values. In this study, a multi-input/multi-output model is developed based on artificial neural networks to map the relationship between different predictor inputs, including time indices, weather variables, human activity parameters, and energy price indicators, and target outputs such as wind and photovoltaic generation. While the information flows in only one direction (from the predictor nodes through the hidden layers to the target node), benchmark training algorithms are employed and assessed under different case studies. The model is evaluated under both parametric and non-parametric formulations, namely neural networks and Gaussian process regression. Essential improvements are achieved by enhancing the number of embedded predictors, while superior performance is observed by using Bayesian regularization mechanisms. In terms of mean-error indices and determination coefficient, this opens the pathway towards minimization via Bayesian inference-based approaches in the presence of increased and highly stochastic renewable inputs.

Economic and Social Benefits of Aquavoltaics: A Case Study from Jiangsu, China

Aquavoltaics is an innovative and beneficial solution that makes dual use of water area for photovoltaic (PV) power generation and aquaculture. Currently, China has made remarkable developments in aquavoltaics. This paper first analyzes the current development status of aquavoltaics in China, then takes the TW “fishery–PV integration” base project in Nanjing, Jiangsu Province, as a case study to analyze its economic and social benefits, and finally puts forward countermeasure suggestions for the development of aquavoltaics in China. It is found that Jiangsu Province is one of the clustering areas for the development of aquavoltaics in China, and the development of aquavoltaics in this province has a high level of specialization. The payback period (PP) of the TW “fishery–PV integration” base project is 10.44 years, the net present value (NPV) is USD 18.5334 million (the discount rate is 5%), and the internal rate of return (IRR) is 8.06%. The social benefits of this project are mainly reflected in the promotion of energy conservation and emission reduction, the alleviation of energy shortages, the optimization of land use, and the development of culture, tourism, science, and education. The development of aquavoltaics should be promoted by strengthening scientific research, paying attention to the impact of PV panel erection on the ecological environment of the waters, emphasizing the fishery farming part of the aquavoltaic project, and improving the commercial operation mode of the aquavoltaic project.

A method for configuring hybrid electrolyzers based on joint wind and photovoltaic power generation modeling using copula functions

Considering the specific wind and photovoltaic power characteristics of a certain region, this study investigates the optimal ratio of Alkaline Electrolysis Cells (AEL) to Proton Exchange Membrane (PEM) electrolyzers in a hybrid electrolysis system for hydrogen production. A flexible model for configuring the hybrid electrolysis system is proposed, based on a copula function for joint wind and solar power modeling. This model generates wind and photovoltaic power generation scenarios using the copula function, incorporating a selection mechanism to ensure that the output scenarios are more representative of the actual data characteristics of wind and photovoltaic power output. Consequently, considering both the fluctuation and amplitude, the wind and photovoltaic power data are decomposed using the Ensemble empirical mode decomposition method. The decomposed components are then allocated to the two types of electrolyzers. Furthermore, the optimal configuration of the hybrid electrolysis system is determined by minimizing the costs associated with wasted power, electricity purchases, and other expenses. Finally, a case study of a 100 MW wind farm and a 50 MW photovoltaic power station in Northwest China is presented, concluding that the optimal configuration ratio of AEL to PEM electrolyzers is 2:1. In a Matlab/Simulink platform, the performance metrics of the hybrid electrolysis system were validated. It was found that the hydrogen production rate of the hybrid electrolyzer is comparable to that of the PEM electrolyzer, but with a lower required cost. Additionally, the hydrogen production rate and volume of the optimal configuration for the hybrid electrolyzer determined by the model proposed in this paper are higher than those obtained through the optimization algorithm's optimal configuration.

Design Guidelines for Building and Infrastructure Integrated Photovoltaic Modules

The demand for renewable energy is increasing as efforts to decarbonize energy sources continue. Photovoltaic (PV) generation systems are the main contributor to the growth of renewable energy, but limited land availability in countries such as Belgium and Netherlands poses a challenge to their deployment. Integrated PV (IPV) can be a promising solution, but requires special consideration regarding electrical and fire safety, efficiency, durability, cost, and environmental impact in the design process. This study seeks to assist designers of IPV products by guiding the selection of materials, technologies, mechanical designs, and production methods for PV semifabricates (SF). It provides a comprehensive list of general design criteria, each offering various options in terms of bill of materials and production technologies. These options come with their own set of advantages and disadvantages, which are enumerated and quantified wherever feasible. The general design guidelines are validated based on the building‐integrated PV and infrastructure‐integrated PV demonstrators (in this case a noise barrier) being developed in the Solar Energy Made Regional (SolarEMR) project.

The use of photobioreactors in façades for decarbonization process

The paper deals with the application of microalgae in building’s façade, regard to the broader project comprising the aspects of the environmental comfort of academic spaces and the energy consumption with on-grid photovoltaic generation, as well as the investigation of alternatives for the improvement of the performance of the building envelopes. Thus, its main objective is the application of interdisciplinary concepts involving Architecture and Biotechnology, as known by Black Ecologies, referring to an investigative interest to explore a new approach of nature, not only related to architectural space, but an emergent environmental focus. This relationship is performed by using photobioreactors with microalgae, installed on the façades of buildings for educational use. The present work presents the methodological outline of the research, based on literature review and case studies; complementary experimental methodologies are also presented to contextualize the subject and its application and feasibility. The current state of art showed an emergent approach in terms of international level, but in the Brazilian context any further research was identified yet. In addition to thermal and energy performance, the strategies will allow the process of sequestration of carbon dioxide and other GHG (greenhouse gases) that impacts on the process of climate change and can contribute to reach the sustainable development. This subject coincides with the discussions of the 2050 scenarios and emission reduction, which were faced at the recent COP-27 and its connections with an integrative way to contribute to the United Nations Sustainable Development Goals.

Optimization of distributed energy resources planning and battery energy storage management via large-scale multi-objective evolutionary algorithm

This paper investigates the synergistic integration of renewable energy sources and battery energy storage systems to enhance the sustainability, reliability, and flexibility of modern power systems. Addressing a critical gap in distribution networks, particularly regarding the variability of renewable energy, the study aims to minimize energy costs, emission rates, and reliability indices by optimizing the placement and sizing of wind and solar photovoltaic generators alongside battery energy storage systems. An improved large-scale multi-objective evolutionary algorithm with a bi-directional sampling strategy is employed.Two scenarios are considered. In the first scenario, six study cases are analyzed to determine the optimal number, location, and size of distributed generators at peak load demand. The proposed algorithm outperforms existing state-of-the-art methods for small-scale distributed resource allocation. In the second scenario, a multi-period load demand across various seasons is evaluated, introducing new opportunities for battery energy storage systems. The problem is modeled with intertemporal constraints, creating a large-scale optimization challenge. Results demonstrate significant improvements: cost savings of up to 51.67 %, power reductions of up to 76.78 %, and a 99.9 % improvement in voltage deviation. Emission rates decreased by 99.92 % in case 1, 95.19 % in case 2, and 97.38 % in case 3, compared to the base case. The proposed algorithm shows superior convergence and performance in solving both small- and large-scale optimization problems, outperforming recent multi-objective evolutionary algorithms.This study provides a robust framework for optimizing renewable energy integration and battery energy storage, offering a scalable solution to modern power system challenges.

An optimal approach for active power reserve of a de-loaded PV generator operating in coordination with synchronous generators

The de-loading operation of PVs, where PVs are operated with an active power reserve has picked up the interest of the researchers in the last few years. However, in an integrated system, where the PV generators are operated in coordination with the synchronous generators, the estimation of the amount of the active power reserve of the PV generator is crucial. A very high reserve will cause an excessive economical loss and a very low reserve will deteriorate the frequency regulation capability. Therefore, in this paper, the cost function of an integrated system is minimised using the particle swarm optimisation algorithm, and the amount of power reserve of the PV generator and operating power values of synchronous generators are obtained as a result of the minimisation. Further, the frequency response of the system for the obtained power reserve value is investigated by suddenly adding the load in the system. The lowest and highest system costs of 2521.87 and 4474.98 $/h are obtained for the irradiance 1000 and 400 W/m2 respectively, and upon a significant load change, the frequency deviation limits to 0.4513 for a reserve value of 29.0712 MW. System modelling and validation have been carried out in the SIMULINK toolbox of the MATLAB software.

Short-Term Irradiance Prediction Based on Transformer with Inverted Functional Area Structure

Solar irradiance prediction is a crucial component in the application of photovoltaic power generation, playing a vital role in optimizing energy production, managing energy storage, and maintaining grid stability. This paper proposes an irradiance prediction method based on a functionally structured inverted transformer network, which maintains the channel independence of each feature in the model input and extracts the correlations between different features through an Attention mechanism, enabling the model to effectively capture the relevant information between various features. After the channel mixing of different features is completed through the Attention mechanism, a linear network is used to predict the irradiance sequence. A data processing method tailored to the prediction model used in this paper is designed, which employs a comprehensive data preprocessing approach combining mutual information, multiple imputation, and median filtering to optimize the raw dataset, enhancing the overall stability and accuracy of the prediction project. Additionally, a Dingo optimization algorithm suitable for the self-tuning of deep learning model hyperparameters is designed, improving the model’s generalization capability and reducing deployment costs. The artificial intelligence (AI) model proposed in this paper demonstrates superior prediction performance compared to existing common prediction models in irradiance data forecasting and can facilitate further applications of photovoltaic power generation in power systems.