Photovoltaic Output Research Articles

Learning Coupled Meteorological Characteristics Aids Short-Term Photovoltaic Interval Prediction Methods

In response to the challenges posed by renewable energy integration, this study introduces a hybrid Attention-TCN-LSTM model for short-term photovoltaic (PV) power forecasting. The LSTM captures the sequence characteristics of PV output, which are then combined with the meteorological sequence features extracted by the Attention-TCN module. The model leverages the strengths of the TCN, the LSTM, and the self-attention mechanism to enhance prediction accuracy and construct reliable prediction intervals. Aiming to optimize both performance and efficiency, the PSO algorithm is used for hyperparameter optimization. Ablation studies and comparisons with other models confirm the effectiveness, accuracy and robustness of the proposed model. This hybrid approach contributes to improved renewable energy integration, offering a more stable and reliable energy supply. Future work will focus on incorporating intelligent systems for autonomous risk management and real-time control of dynamic PV output fluctuations.

Exploring the landscape of deep learning for solar photovoltaic power output forecasting: A review

Exploring the landscape of deep learning for solar photovoltaic power output forecasting: A review

Advanced Automated Machine Learning Framework for Photovoltaic Power Output Prediction Using Environmental Parameters and SHAP Interpretability

Advanced Automated Machine Learning Framework for Photovoltaic Power Output Prediction Using Environmental Parameters and SHAP Interpretability

A Two-Stage Resilience Enhancement Strategy for Distribution Networks Considering Extreme Weather Conditions

Background: In the context of increasing extreme weather events and natural disasters, enhancing the resilience and rapid recovery capabilities of distribution networks has become a critical focus in power system research. Objective: Previous studies primarily focused on the post-disaster power restoration phase of distribution networks affected by extreme weather without fully addressing the critical role of mobile energy storage in pre-disaster prevention. To bridge this gap, this paper proposes a two-stage resilience enhancement strategy for distribution networks, incorporating multi-source coordination and network reconfiguration. Methods: This paper presents a two-stage resilience enhancement strategy for distribution networks under extreme weather conditions. This strategy combines the coordinated optimization of various DERs with network reconfiguration. In the pre-disaster stage, optimization is conducted to manage uncertainties in wind and photovoltaic output. A pre-deployment approach for energy storage is introduced, incorporating the coordination of the power grid and transportation network to maximize expected load power recovery and minimize node voltage deviation. In the post-disaster stage, the strategy integrates distributed resources such as photovoltaic systems, wind power, and mobile energy storage. It uses a multi-source coordinated dynamic scheduling method to optimize spatiotemporal energy distribution. Results: The results show that this approach significantly improves post-disaster recovery efficiency. It reduces load shedding and enhances the system's adaptability and disaster resistance. Conclusion: The proposed approach enhances the overall resilience and recovery capacity of the distribution network. This patented technology will be applied in the future.

Expression of concern: Short-time photovoltaic output prediction method based on depthwise separable convolution visual geometry group-deep gate recurrent neural network

Expression of concern: Short-time photovoltaic output prediction method based on depthwise separable convolution visual geometry group-deep gate recurrent neural network

A twenty-year dataset of hourly energy generation and consumption from district campus building energy systems

Distributed energy resources (DERs) would play a crucial role in the transition towards decentralized and decarbonized energy systems. However, due to the limited availability of long-term, high-resolution datasets, there has been little research on the descriptive analysis of distributed energy systems throughout the lifespan of distributed power generators and beyond. To address this challenge, this study has collected and described a twenty-year dataset (from 2002 to 2021) consisting of hourly energy generation and consumption profiles from a campus distributed energy system, covering the entire lifespan of on-site generators. The dataset includes supply-side data such as gas consumption from combined heating and power (CHP) units (fuel cell, gas engine), absorption chiller, gas boiler, solar photovoltaic generation, CHPs output, and grid electricity import. Additionally, real-life electricity, hot water, space heating, and cooling energy load profiles from individual buildings within the campus were also collected. This long-term dataset can be utilized in various scenarios, providing researchers and policymakers with comprehensive insights into the energy efficiency of distributed energy systems.

Photovoltaic Short-Term Output Power Forecast Model Based on Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise–Kernel Principal Component Analysis–Long Short-Term Memory

To solve the problem of photovoltaic power prediction in areas with large climate changes, this article proposes a hybrid Long Short-Term Memory method to improve the prediction accuracy and noise resistance. It combines the improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) and kernel principal component analysis (KPCA) algorithm. The ICEEMDAN algorithm reduces the instability of the environmental factor sequence. The KPCA algorithm reduces the input dimensions of the model. LSTM performs dynamic time modeling of the multivariate feature sequences to predict the output PV power. The adaptability of the ICEEMDAN-KPCA-LSTM model is assessed with datasets from a PV plant in west China and evaluated by root mean squared error (RMSE), mean absolute percentage error (MAPE), and R-squared metrics. Using 70% of the datasets for output PV power estimation, the results show a good performance, with an RMSE of 4.3715, MAPE of 8.9264%, and R-squared value of 89.973%. By comparing with other prediction models, the ICEEMDAN-KPCA-LSTM photovoltaic output power model outperforms other models.

A Robust Salp Swarm Algorithm for Photovoltaic Maximum Power Point Tracking Under Partial Shading Conditions

Currently, numerous intelligent maximum power point tracking (MPPT) algorithms are capable of tackling the global optimization challenge of multi-peak photovoltaic output power under partial shading conditions, yet they often face issues such as slow convergence, low tracking precision, and substantial power fluctuations. To address these challenges, this paper introduces a hybrid algorithm that integrates an improved salp swarm algorithm (SSA) with the perturb and observe (P&O) method. Initially, the SSA is augmented with a dynamic spiral evolution mechanism and a Lévy flight strategy, expanding the search space and bolstering global search capabilities, which in turn enhances the tracking precision. Subsequently, the application of a Gaussian operator for distribution calculations allows for the adaptive adjustment of step sizes in each iteration, quickening convergence and diminishing power oscillations. Finally, the integration with P&O facilitates a meticulous search with a small step size, ensuring swift convergence and further mitigating post-convergence power oscillations. Both the simulations and the experimental results indicate that the proposed algorithm outperforms particle swarm optimization (PSO) and grey wolf optimization (GWO) in terms of convergence velocity, tracking precision, and the reduction in iteration power oscillation magnitude.

Fine-grained simulation model for PV power output interval based on two-stage scenario clustering and dual-ensemble compatible learning

Photovoltaic (PV) power simulation is indispensable for the planning and operation of renewable-rich power systems. Among various simulation methods, data-driven indirect simulation methods are the most efficient, primarily involving scenario extraction and power output generation. Typical scenario extraction methods often feature coarse characterizations, which also cannot be expressed by traditional power output generation models lacking the ability of quantifying the uncertainty of the output results. This paper proposes a fine-grained simulation model for PV power output interval, i.e., upper bound and lower bound, based on two-stage clustering of multiple typical scenarios and dual-ensemble compatible learning. The first stage of scenario extraction, considering the impact of total daily irradiance on PV output, employs a line distance index for preliminary scenario division of daily PV output. These scenarios are further divided into five characteristic scenarios with an angular distance index considering the impact of intra-day irradiance variations on power output. PV power output interval is generated from dual-ensemble compatible learning including Stacking and Bagging, which are adaptively selected with a Bias-Variance Selection Index (BS) calculated using the value of scenario characteristics. Stacking and Bagging are driven by three neural network base learners with Bayesian layers, which can output the lower bound and upper bound with confidence at a certain level, thus quantifying the uncertainty of the result accurately. The actual data of Daxing and Gangjialing power stations are used in case study. Results form case study show that compared with the existing methods, the proposed method can improve the Power Coverage Rate (PCR) and Average Power Simulation Accuracy (APA) of uncertainty simulation results by 27.44% and 5.39%, respectively. Meanwhile, the Average Daily Maximum Power Simulation Accuracy (AMPA) is similar to that of existing methods.

Slashing the surplus – how prosumers with smart metering respond to regulatory restrictions on self-consumption in Croatia

With the diffusion of prosumerism, where households act both as producers and consumers of energy, policy makers must strike a balance between encouraging microgeneration and regulating this new prosumer segment on the energy market. However, effective policy implementation depends on prosumers’ behavioural reactions. This paper provides evidence on the interplay between digital real-time information and regulation of self-consumption for rooftop photovoltaics (PV) in Croatia. Croatian households that produce more annual electricity than they consume are automatically re-classified as renewable traders, which means additional administrative duties and less favorable tax treatment. This creates perverse incentives to reduce PV generation or increase energy consumption by year-end. We document the behavioural reactions to this policy design, indicating that energy production and consumption are highly elastic regarding regulatory incentives, but only if these incentives are made transparent and accessible with timely information. We collected two survey waves (n = 54 and n = 80) and smart meter data (n = 39), which illustrate the behavioural reaction before and after year-end. According to the survey wave before year-end, almost half of the participants considered curtailing their PV output. According to the smart meter data, a sizable share did indeed take action by shutting down PV production or by powering additional devices to reduce the surplus near year-end. In a second survey wave in the new year, prosumers provide ex-post insights on the specific measures taken to reduce surplus. We discuss research insights regarding the transparency and control offered by metering feedback, and how this can influence household behaviour within regulatory frameworks.

Day-ahead photovoltaic power generation forecasting with the HWGC-WPD-LSTM hybrid model assisted by wavelet packet decomposition and improved similar day method

Precisely forecasting output of solar photovoltaics is crucial for (i) effective solar power management, (ii) integration into the electrical grid, (iii) flexible allocation of power resources. While deep learning algorithms have shown promise in energy applications, single algorithms often struggle with unstable predictions and limited generalizability for predicting photovoltaic (PV) output. This study introduces an innovative hybrid model (HWGC-WPD-LSTM) that integrates an improved similar day algorithm (WGC: weighted grey correlation analysis and cosine similarity), Wavelet Packet Decomposition (WPD), and Long Short-Term Memory neural network (LSTM) for predicting day-ahead power output. The model suggests an approach to identifying similar days by integrating weighted GRA with cosine similarity. It then decomposes power sequences employing WPD to capture various frequency characteristics. Four independent LSTM networks are then applied to these sub-sequences to forecast output, which are then reconstructed to derive the ultimate forecast outcome for solar photovoltaics. The evaluation of the hybrid model is conducted based on data gathered from actual generating station in Shandong Province, China. Then it is compared against other models utilizing similar day selection methods and other hybrid HWGC-BP, HWGC-Elman, HWGC-SVM, HWGC-RF, and HWGC-LSTM models. This comparison is based on four performance metrics: Mean Absolute Error (MAE), Root Mean Square Error (RMSE), normalized Root Mean Square Error (NRMSE), and Mean Absolute Deviation (MAD). Results demonstrate that the HWGC-WPD-LSTM model offers enhanced precision and stability (MAE = 0.2168 MW, RMSE = 0.2996 MW, NRMSE = 6.78 %, MAD = 2.18 %) in day-ahead power generation predictions. This highlights the potency of the hybrid model in enhancing the forecasting capabilities for solar photovoltaics, which is crucial for the strategic enhancement of renewable energy resource exploitation in the context of modern power systems.

A K-means cluster division of regional photovoltaic power stations considering the consistency of photovoltaic output

The uncertainty and volatility of photovoltaics seriously impact the grid's power quality. Short-term photovoltaic(PV) forecasts have a positive effect on the stable operation of the power system. The accuracy of cluster division is a key factor in the output prediction of regional PV power stations. This paper proposes a cluster division method, including a novel feature selection technique and an optimized cluster algorithm based on K-means. The proposed method performs feature analysis and parameter optimization of the division of regional photovoltaic plant clusters, analyzes the clustering dimension of photovoltaic output consistency, and establishes a K-means clustering model of photovoltaic power plants that considers time, space, and inherent characteristics of power plants first. Then, a prediction model based on Long Short-Term Memory (LSTM) is established for each cluster to realize the prediction of regional cluster photovoltaic output. The simulation results demonstrate that the Mean Absolute Percentage Error (MAPE) of the proposed method is 18.27 % and Root Mean Square Error (RMSE) is 45.79 %, which verifies the superiority of the proposed method over comparison models. It shows that the proposed method can effectively solve the problem of low prediction accuracy caused by weak output consistency of power stations in regional photovoltaic clusters.

Aggregation Modeling for Integrated Energy Systems Based on Chance-Constrained Optimization

Integrated energy systems (IESs) strengthen electricity–gas–heat multi-energy coupling and reduce wind and light abandonment. For grids with superior distribution, IESs are similar to virtual energy storage systems and are able to realize efficient interaction with the grid by synergizing the operating status of the internal equipment and improving the security, economy, and flexibility of the grid’s operation. However, the internal equipment coupling of an IES is complex, and determining how to evaluate its adjustable capacity range (that is, the upper and lower boundaries of its external energy demand) considering the uncertainty and volatility of wind power and photovoltaic output is a problem to be solved. To solve this problem, this paper presents a chance-constrained evaluation method for the adjustable capacity of IESs. Firstly, mathematical models and operational constraints of each device within the IES are established. Secondly, based on the mathematical model of chance-constrained planning, an adjustable capacity range assessment model considering the uncertainty of wind and photovoltaic output is established. Finally, the MATLAB/Yalmip/Gurobi solver is used for the optimization solution, and the adjustable capacity range interval of the constructed IES model is solved using an arithmetic example to analyze and verify the correctness and validity of the method and to study the influencing factors of its adjustable range.

Photovoltaic output prediction based on VMD disturbance feature extraction and WaveNet

Traditional photovoltaic (PV) forecasting methods often overlook the impact of the correlation between different power fluctuations and weather factors on short-term forecasting accuracy. To address this, this paper proposes a PV output forecasting method based on Variational Mode Decomposition (VMD) disturbance feature extraction and the WaveNet model. First, to extract different feature variations of the output and enhance the model’s ability to capture PV power fluctuation details, VMD is used to decompose the PV output time series, obtaining IMFs modes representing output disturbances and quasi-clear sky IMF modes. Then, to reveal power changes, especially the underlying patterns of disturbances and their relationship with weather factors, K-means clustering is applied to the IMF modes representing output disturbances, clustering the disturbance IMFs into different power change feature clusters. This is combined with Spearman correlation analysis of weather factors and the construction of an experimental dataset. Finally, to enhance the model’s learning ability and improve short-term output forecasting accuracy, the WaveNet model is employed during the forecasting phase. Separate WaveNet models are constructed and trained with the corresponding datasets, and the total PV output forecast is obtained by superimposing the predictions of different IMF modes. Experimental results are compared with traditional methods, demonstrating a significant improvement in forecasting accuracy, with a Mean Absolute Percentage Error (MAPE) error of 6.94%, highlighting the effectiveness of our method and providing strong technical support for the refined management and intelligent forecasting of PV energy.

Enhanced operation of PVWPS based on advanced soft computing optimization techniques

This study introduces three soft computing (SC) optimization algorithms aimed at enhancing the efficiency of photovoltaic water pumping systems (PVWPS). These algorithms include the Gorilla Troop Algorithm (GTO), Honey Badger Algorithm (HBA), and Snake Algorithm (SAO). The goal of the SC optimizers is to maximize the output power of the PV array (PPV) and enhance the efficiency of the DC motor (η), thereby optimizing the water flow rate (Q) of the pumping system. The analytical modeling approach proposed in this study involves forecasting the optimal duty cycle (Dop) for a buck-boost converter, taking into account variables such as solar radiation (G) and ambient temperature (T). A comparative analysis is conducted between the suggested SC optimizers and analytical modeling. MATLAB simulation is employed to explore an adaptive neuro-fuzzy inference system (ANFIS) trained for the proposed system. The objective is to assess system performance and accuracy. Findings indicate a strong convergence between the analytical model and the simulation model utilizing SC optimizers. Moreover, the neuro-fuzzy system trained offline, coupled with the proposed SC optimizers, demonstrates superior performance compared to traditional control methods like perturb and observe (P&O) and incremental conductance (IC). This superiority is evident across various metrics including motor efficiency (η), photovoltaic (PV) output power (PPV), water flow rate (Q), and time response.

Distributed Dispatch of Distribution Network Operators, Distributed Energy Resource Aggregators, and Distributed Energy Resources: A Three-Level Conditional Value-at-Risk Optimization Model

To enhance the participation enthusiasm of distributed energy resources (DERs) and DER aggregators in their demand response, this paper develops a three-level distributed scheduling model for the distribution network operators (DNO), DER aggregators, and DERs based on the conditional value-at-risk (CVaR) theory. First, a demand response model is established for the DNO, DER aggregators, and DERs. Next, we employ the analytical target cascading (ATC) method to construct a three-level distributed scheduling model, where incentive and compensation prices are shared as consensus variables across the model levels to amplify the influence of DER aggregators on incentive prices and DERs on compensation prices. Then, the photovoltaic output model is restructured using the CVaR theory to effectively measure the risk associated with photovoltaic output uncertainty. Finally, an analysis is conducted using the IEEE 33-node distribution network to validate the effectiveness of the proposed model.

Two-Stage, Three-Layer Stochastic Robust Model and Solution for Multi-Energy Access System Based on Hybrid Game Theory

This paper proposes a two-stage, three-layer stochastic robust model and its solution method for a multi-energy access system (MEAS) considering different weather scenarios which are described through scenario probabilities and output uncertainties. In the first stage, based on the principle of the master–slave game, the master–slave relationship between the grid dispatch department (GDD) and the MEAS is constructed and the master–slave game transaction mechanism is analyzed. The GDD establishes a stochastic pricing model that takes into account the uncertainty of wind power scenario probabilities. In the second stage, considering the impacts of wind power and photovoltaic scenario probability uncertainties and output uncertainties, a max–max–min three-layer structured stochastic robust model for the MEAS is established and its cooperation model is constructed based on the Nash bargaining principle. A variable alternating iteration algorithm combining Karush–Kuhn–Tucker conditions (KKT) is proposed to solve the stochastic robust model of the MEAS. The alternating direction method of multipliers (ADMM) is used to solve the cooperation model of the MEAS and a particle swarm algorithm (PSO) is employed to solve the non-convex two-stage model. Finally, the effectiveness of the proposed model and method is verified through case studies.

Assessment of Solar Energy Generation Toward Net-Zero Energy Buildings

With the continuous rise in the energy consumption of buildings, the study and integration of net-zero energy buildings (NZEBs) are essential for mitigating the harmful effects associated with this trend. However, developing an energy management system for such buildings is challenging due to uncertainties surrounding NZEBs. This paper introduces an optimization framework comprising two major stages: (i) renewable energy prediction and (ii) multi-objective optimization. A prediction model is developed to accurately forecast photovoltaic (PV) system output, while a multi-objective optimization model is designed to identify the most efficient ways to produce cooling, heating, and electricity at minimal operational costs. These two stages not only help mitigate uncertainties in NZEBs but also reduce dependence on imported power from the utility grid. Finally, to facilitate the deployment of the proposed framework, a graphical user interface (GUI) has been developed, providing a user-friendly environment for building operators to determine optimal scheduling and oversee the entire system.

Research on stacking ensemble method for day-ahead ultra-short-term prediction of photovoltaic power

The intermittency and uncertainty of photovoltaic power output make it difficult to match real-time electricity demand, and accurate prediction of photovoltaic power is the basis for improving photovoltaic energy consumption. This article proposes a new stacking ensemble forecast model based on the time series generative adversarial network (TimeGAN-SEFM), to improve the accuracy of ultra-short-term forecasting of photovoltaic power. Firstly, a dual layer feature weighted clustering weighted fuzzy C-means clustering algorithm is proposed to accurately partition the original dataset according to weather types. Secondly, in the proposed TimeGAN-SEFM, a Particle Swarm Optimization based BP neural network is used as a meta learner to integrate three types of base learners, thereby improving the structural diversity of the model. The dataset for each type of weather is proportionally divided into multiple sub-datasets for training base learners. In response to the limitation that the amount of data used for training a single base learner is relatively small after multiple splitting of the original data, a TimeGAN augmentation network is introduced to perform multi-dimensional data augmentation on the sub-training sets, which improves the size and diversity of the dataset used for training base learners, thereby improving the predictive performance of the model. Finally, the predictive performance of the proposed TimeGAN-SEFM was evaluated using measurement data from a 20 MW photovoltaic power station in North China. The results show that TimeGAN-SEFM effectively improves the accuracy of photovoltaic prediction and helps promote real-time matching of photovoltaic energy and power demand, thereby improving the utilization of photovoltaic energy.

Optimal capacity configuration of joint system considering uncertainty of wind and photovoltaic power and demand response

AbstractTo reduce phenomenon of abandoning wind and photovoltaic power, improve the limitations of traditional methods in dealing with uncertainty of wind and photovoltaic power and system planning, and improve the optimal configuration of resources, an optimal capacity configuration of joint system considering uncertainty of wind and photovoltaic power and demand response is proposed. Firstly, using probability distribution information of wind and photovoltaic power output, the distance between actual probability distribution and forecast probability distribution is constrained based on the 1‐norm and ∞‐norm. A fuzzy set considering uncertainty probability distribution is constructed, and a two‐stage distributed robust planning model is established. The first stage involves optimizing joint system capacity for scenarios with the lowest probability of wind and photovoltaic power; the second stage builds on capacity optimization scheme from the first stage and aims to minimize operating costs through simulation optimization. Secondly, column and constraint generation is used to solve the model. Finally, constructing an example based on actual data from a power grid in Northeast China for simulation and analysis, the results show that the method achieves a balanced optimization of robustness and economy, effectively reduces carbon emissions and improves ability of the system to consume wind and photovoltaic power.