- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Photovoltaic power forecasting based LSTM-Convolutional Network
摘要： The volatile and intermittent nature of solar energy itself presents a significant challenge in integrating it into existing energy systems. Accurate photovoltaic power prediction plays an important role in solving this problem. With the development of deep learning, more and more scholars have applied the deep learning model to time series prediction and achieved very good results. In this paper, a hybrid deep learning model (LSTM-Convolutional Network) is proposed and applied to photovoltaic power prediction. In the proposed hybrid prediction model, the temporal features of the data are extracted first by the long-short term memory network, and then the spatial features of the data are extracted by the convolutional neural network model. In order to show the superior performance of the proposed hybrid prediction model, the prediction results of the hybrid model are compared with those of the single model (long-short term memory network, convolutional neural network) and the hybrid network (Convolutional-LSTM Network) model, and the results of eight error evaluation indexes are given. The results show that the hybrid prediction model has better prediction effect than the single prediction model, and the proposed hybrid model (extract the temporal characteristics of data first, and then extract the spatial characteristics of data) is better than Convolutional-LSTM Network (extract the spatial characteristics of data first, and then extract the temporal characteristics of data).
关键词： Convolutional-LSTM network,LSTM-Convolutional network,Photovoltaic power forecasting,Convolutional neural network,Deep learning,Long-short term memory
更新于2025-09-16 10:30:52
-
[IEEE 2019 AEIT International Annual Conference (AEIT) - Florence, Italy (2019.9.18-2019.9.20)] 2019 AEIT International Annual Conference (AEIT) - Multi-Layer RNN-based Short-term Photovoltaic Power Forecasting using IoT Dataset
摘要： Photovoltaic power ?uctuation in daytime is one of critical problems for the ef?cient and stable operation of the smart grid. To respond the PV power ?uctuation resulting from weather change, the short-term PV power forecasting algorithm using multi-layer RNN is proposed in this paper. It consists of multiple RNN layers using power and meteorological data which are collected by on-site IoT (Internet of Things) sensors. Experimental results showed that the accuracies of the short-term PV power prediction of 5 minutes and 1 hour later using 3 RNN layers with 12 time-step were 98.02% and 96.58% based on the normalized RMSE, respectively. These experimental results con?rmed that the proposed short-term prediction algorithm using multi-layer RNN model was applicable to respond the short-term PV power ?uctuation.
关键词： IoT (Internet of Things),multi-layer RNN,PV forecasting algorithm,photovoltaic power
更新于2025-09-16 10:30:52
-
[IEEE 2019 International Conference on Information and Communications Technology (ICOIACT) - Yogyakarta, Indonesia (2019.7.24-2019.7.25)] 2019 International Conference on Information and Communications Technology (ICOIACT) - The Effect of Irradiance on Distribution Power System Stability in Large-Scale Grid-Connected Photovoltaic
摘要： The purpose of this study was to analyze the effect of solar irradiance in the integration of photovoltaic plants (PV) on the stability of the electric power distribution system. The stability aspects assessed were the stability of the distribution network and the stability response of the synchronous generator which work in parallel with the PV generator. Distribution grid stability includes voltage and frequency stability. The stability response of synchronous generators includes power angle stability, active power stability, and reactive power stability. All aspects of stability were simulated based on four different cases of irradiance, namely 550 W/m2, 650 W/m2, 850 W/m2, and 1000 W/m2. PV generators were connected to a distribution grid using an inverter with MPPT and PV systems without batteries. This study was applied to a case of electrical distribution system in Gorontalo province, Indonesia. One distribution feeder in Gorontalo Province was connected a photovoltaic system of 2000 kWp and synchronous generators that work in parallel. The distribution system was modelled in a single-line diagram of 13-buses. The measurement of every solar radiation intensity change was conducted in every electrical distribution power system change. This study showed that high irradiation in PV plants affects the voltage and frequency stability on the grid by increasing proportionately. However, the high irradiation has an effect on increasing power oscillation at synchronous generators.
关键词： Distribution System,Synchronous Generator,Photovoltaic,Power System Stability,Grid-Connected
更新于2025-09-16 10:30:52
-
Charging Strategy of Supercapacitor in Photovoltaic Power Generation System
摘要： The charging efficiency of supercapacitor under different charging methods is analyzed by using the improved RC model of supercapacitor. A photovoltaic cell charging system for supercapacitor based on Boost cascade Buck converter (BOCBB) is proposed. The former Boost converter is connected to the photovoltaic power generation system, and the conductance increment method is used to track the maximum power point of the photovoltaic cell. The latter Buck converter uses a segmented charging strategy to charge the supercapacitor. Based on this circuit, a complete control method for the supercapacitor charging system is proposed. Finally, the charging efficiency of supercapacitor by photovoltaic cells under different lighting conditions is simulated and analyzed.
关键词： Boost cascade Buck converter,charging strategy,conductance increment method,supercapacitor,photovoltaic power generation
更新于2025-09-16 10:30:52
-
Key Parameter Identification and Optimization of Photovoltaic Power Plants Based on Genetic Algorithm
摘要： As the penetration rate of the photovoltaic power continues to grow, its impact on the stability of the power system becomes more considerable ever than before. However, due to the relatively low accuracy of the parameters, the traditional electromagnetic transient simulation used to assess the impact is biased. Therefore, it is of great importance to perform key parameter identification and optimization on a solar power plant containing many photovoltaic panels, which can avoid the problem of combination explosion. In this paper, a scheme of key parameter identification is proposed. Then, an optimization method based on genetic algorithm is also established to improve the accuracy. Simulation tests validate the effectiveness of the proposed method.
关键词： genetic algorithm,parameter identification,photovoltaic power plants,optimization
更新于2025-09-16 10:30:52
-
Research on Valuation of Photovoltaic Power Stationa??s Earning Right Backed Securitization
摘要： The high cost of financing has always been a problem that hinders the construction of grid-connected PV power station. As a new type of structural financing, asset securitization can help PV power station achieve low-cost financing and effectively solve the problem of financing difficulties. This paper takes the BOC-Shenneng Nankong Assets Special Plan as an example to design a photovoltaic power station’s earning right backed securitization product. It uses data comprised of the income from the on-grid electricity charges of six ground-based photovoltaic power stations, issued by Shenneng Nankong during the years between 2016 to 2021, as the underlying asset of ABS. Taken the characteristics of PV into account, Monte Carlo model is used to predict the distribution of future cash flow of the asset pool, and the NS model is used to fit the term structure of the interest rate, thereby determining the overall issuance amount of ABS products; then the underlying asset, according to the stability of the cash flow of the asset pool, is divided into three tranches with different credit ratings; finally, the issuance scale and coupon rate of different grades of bonds are determined.
关键词： Photovoltaic Power Station,Asset Securitization,Earning Right,NS Model,Monte Carlo Model
更新于2025-09-16 10:30:52
-
Study on Three-Phase Reclosing Strategy Applicable to Tie Line of Photovoltaic Power Station
摘要： When a fault occurring in the tie line of photovoltaic power station is cleared by the protection three-phase trip, photovoltaic power source (PVS) will form an unplanned island with the local load. However, since the voltage regulation and frequency control capability of PVS is generally poor, it is very difficult to satisfy the synchronous reclosing conditions, eventually resulting in an automatic reclosing failure. According to the islanding control strategy of PVS and the principle of phase-locked loop (PLL), a vector relationship model of PVS port actual voltage, port calculation voltage, grid-connected point voltage and so on before and after reclosing is established. Based on this, the influences of reclosing phase difference, amplitude difference and frequency difference on reclosing impulse voltage and current are analyzed, and a synchronous check reclosing strategy applicable to the tie line of PVS is proposed, which can effectively improve the success rate of the three-phase reclosing in tie line. Digital simulation results verify the correctness of the proposed reclosing strategy.
关键词： reclosing impulse,three-phase reclosing,Photovoltaic power,synchronous check reclosing strategy,analysis of influencing factors
更新于2025-09-16 10:30:52
-
[IEEE 2019 IEEE 10th International Symposium on Power Electronics for Distributed Generation Systems (PEDG) - Xi'an, China (2019.6.3-2019.6.6)] 2019 IEEE 10th International Symposium on Power Electronics for Distributed Generation Systems (PEDG) - Reliability Evaluation of Photovoltaic Power Generation System Based on Fuzzy Layering Method
摘要： The analysis process of the overall reliability evaluation model of the traditional photovoltaic power generation system is complicated, and the shortcomings of the system weak link cannot be analyzed. This paper proposes a fuzzy hierarchical evaluation method based on sensitivity analysis to evaluate the reliability of photovoltaic power generation systems. The method judges the whole system failure factor by introducing the fault frequency, the degree of fault impact, and the second evaluation criterion of the fault detection difficulty. In particular, the Monte Carlo-based component sensitivity analysis method is used to calculate the degree of fault impact. Finally, the method of this paper is used to analyze a photovoltaic power generation system. The effectiveness of the proposed method is verified by the overall reliability analysis and the evaluation of fault factors. It is proved that the method is of great significance for analyzing the reliability of the photovoltaic system and the weak link of the system.
关键词： photovoltaic power generation system,sensitivity analysis,Monte Carlo,fuzzy layering evaluation method
更新于2025-09-16 10:30:52
-
Photovoltaic Hot-Spots Fault Detection Algorithm using Fuzzy Systems
摘要： Faults in photovoltaic (PV) modules, which might result in energy loss and reliability problems are often difficult to avoid, and certainty need to be detected. One of the major reliability problems affecting PV modules is hot-spotting, where a cell or group of cells heats up significantly compared to adjacent solar cells, hence decreasing the optimum power generated. In this article, we propose a fault detection of PV hot-spots based on the analysis of 2580 PV modules affected by different types of hot-spots, where these PV modules are operated under various environmental conditions, distributed across the UK. The fault detection model comprises a fuzzy inference system (FIS) using Mamdani-type fuzzy controller including three input parameters, namely, percentage of power loss (PPL), short circuit current (Isc), and open circuit voltage (Voc). In order to test the effectiveness of the proposed algorithm, extensive simulation and experimental-based tests have been carried out; while the average obtained accuracy is equal to 96.7%.
关键词： Fault Detection,Hot-Spots,Photovoltaic,Power Loss,I-V curve,Fuzzy Logic
更新于2025-09-16 10:30:52
-
Daily Photovoltaic Power Prediction Enhanced by Hybrid GWO-MLP, ALO-MLP and WOA-MLP Models Using Meteorological Information
摘要： Solar energy is a safe, clean, environmentally-friendly and renewable energy source without any carbon emissions to the atmosphere. Therefore, there are many studies in the field of solar energy in order to obtain the maximum solar radiation during the day time, to estimate the amount of solar energy to be produced, and to increase the efficiency of solar energy systems. In this study, it was aimed to predict the daily photovoltaic power production using air temperature, relative humidity, total horizontal solar radiation and diffuse horizontal solar radiation parameters as multi-tupled inputs. For this purpose, grey wolf, ant lion and whale optimization algorithms were integrated to the multilayer perceptron. In addition, the effects of sigmoid, sinus and hyperbolic tangent activation functions on the prediction performance were analyzed in detail. As a result of overall accuracy indictors achieved, the grey wolf optimization algorithm-based multilayer perceptron model was found to be more successful and competitive for the daily photovoltaic power prediction. Furthermore, many meaningful patterns were revealed about the constructed models, input tuples and activation functions.
关键词： prediction,photovoltaic power,meteorological input,artificial neural networks,metaheuristic optimization
更新于2025-09-16 10:30:52