scholarly journals Construction of Forecast Model for Power Demand and PV Power Generation Using Tensor Product Spline Function

2021 ◽  
Vol 812 (1) ◽  
pp. 012001
Author(s):  
T Matsumoto ◽  
Y Yamada
Keyword(s):  
Power Generation ◽  
Tensor Product ◽  
Spline Function ◽  
Forecast Model ◽  
Power Demand ◽  
Pv Power Generation

scholarly journals Quasi Z-Source Inverter for Pv Power Generation Systems

2019 ◽  
Vol 9 (2) ◽  
pp. 1191-1199
Keyword(s):  
Power Generation ◽  
Renewable Energy ◽  
Fossil Fuels ◽  
Renewable Energy Sources ◽  
Energy Sources ◽  
Modern World ◽  
Power Demand ◽  
Point Tracking ◽  
Power Point ◽  
Pv Power Generation

For the enormously increased power demand in the modern world, the existing fossil fuel sources seem to be inadequate to meet the demands. Hence, it is necessary to switch over to use Renewable Energy Sources (RES). Besides the demand concerns, the power generation from fossil fuels causes environmental pollution prominently. As a result, the utilization of RES has been encouraged. When RES is interconnected with the grid, this system becomes an excellent solution to fulfill the power demand of the present scenario. The energy generated from renewable energy sources varies according to seasonal variations. The power generated from RES can be delivered to the load by interconnecting it with the grid. When a small size RES system is connected with the distribution network, it can deliver energy to the isolated zones where the energy cannot be drawn from the conventional network. In this work, the Artificial Neural Network based Maximum Power Point Tracking scheme has been introduced with Photovoltaic (PV) power generation. Also, a bi-directional charger is introduced to overcome the battery issues. The model is evaluated in the MATLAB/SIMULINK package. The performance of the system is analyzed by applying different voltage levels to qZSI. The voltage gain, effectiveness of the scheme, MPPT and the regulation of the voltages are observed

scholarly journals Deep RNN-Based Photovoltaic Power Short-Term Forecast Using Power IoT Sensors

Energies ◽  
2021 ◽  
Vol 14 (2) ◽  
pp. 436
Author(s):  
Hyung Keun Ahn ◽  
Neungsoo Park
Keyword(s):  
Power Generation ◽  
Forecast Model ◽  
Experimental Results ◽  
Short Term ◽  
Time Step ◽  
Short Term Forecast ◽  
Term Forecast ◽  
Weather Changes ◽  
The Impact ◽  
Pv Power Generation

Photovoltaic (PV) power fluctuations caused by weather changes can lead to short-term mismatches in power demand and supply. Therefore, to operate the power grid efficiently and reliably, short-term PV power forecasts are required against these fluctuations. In this paper, we propose a deep RNN-based PV power short-term forecast. To reflect the impact of weather changes, the proposed model utilizes the on-site weather IoT dataset and power data, collected in real-time. We investigated various parameters of the proposed deep RNN-based forecast model and the combination of weather parameters to find an accurate prediction model. Experimental results showed that accuracies of 5 and 15 min ahead PV power generation forecast, using 3 RNN layers with 12 time-step, were 98.0% and 96.6% based on the normalized RMSE, respectively. Their R2-scores were 0.988 and 0.949. In experiments for 1 and 3 h ahead of PV power generation forecasts, their accuracies were 94.8% and 92.9%, respectively. Also, their R2-scores were 0.963 and 0.927. These experimental results showed that the proposed deep RNN-based short-term forecast algorithm achieved higher prediction accuracy.

scholarly journals Swarm Decomposition Technique Based Hybrid Model for Very Short-Term Solar PV Power Generation Forecast

2020 ◽  
Vol 26 (3) ◽  
pp. 79-83 ◽  
Author(s):  
Emrah Dokur
Keyword(s):  
Power Generation ◽  
Power Plant ◽  
Hybrid Model ◽  
Forecast Model ◽  
Decomposition Technique ◽  
Solar Pv ◽  
Short Term ◽  
Energy Management Systems ◽  
Novel Approach ◽  
Pv Power Generation

Accurate predictions of solar photovoltaic (PV) power generation at different time horizons are essential for reliable operation of energy management systems. The output power of a PV power plant is dependent on non-linear and intermittent environmental factors, such as solar irradiance, wind speed, relative humidity, etc. Intermittency and randomness of solar PV power effect precision of estimation. To address the challenge, this paper presents a Swarm Decomposition Technique (SWD) based hybrid model as a novel approach for very short-term (15 min) solar PV power generation forecast. The original contribution of the study is to investigate use of SWD for solar data forecast. The solar PV power generation data with hourly resolution obtained from the field (grid connected, 857.08 kWp Akgul Solar PV Power Plant in Turkey) are used to develop and validate the forecast model. Specifically, the analysis showed that the hybrid model with SWD technique provides highly accurate predictions in cloudy periods.

scholarly journals Ultra-Short-Term Forecasting of Photo-Voltaic Power via RBF Neural Network

Electronics ◽  
2020 ◽  
Vol 9 (10) ◽  
pp. 1717
Author(s):  
Wanxing Ma ◽  
Zhimin Chen ◽  
Qing Zhu
Keyword(s):  
Neural Network ◽  
Power Generation ◽  
Smart Grids ◽  
Percentage Error ◽  
Solar Pv ◽  
Short Term ◽  
Forecasting Method ◽  
Photo Voltaic ◽  
Short Term Forecasting ◽  
Pv Power Generation

With the fast expansion of renewable energy systems during recent years, the stability and quality of smart grids using solar energy have been challenged because of the intermittency and fluctuations. Hence, forecasting photo-voltaic (PV) power generation is essential in facilitating planning and managing electricity generation and distribution. In this paper, the ultra-short-term forecasting method for solar PV power generation is investigated. Subsequently, we proposed a radial basis function (RBF)-based neural network. Additionally, to improve the network generalization ability and reduce the training time, the numbers of hidden layer neurons are limited. The input of neural network is selected as the one with higher Spearman correlation among the predicted power features. The data are normalized and the expansion parameter of RBF neurons are adjusted continuously in order to reduce the calculation errors and improve the forecasting accuracy. Numerous simulations are carried out to evaluate the performance of the proposed forecasting method. The mean absolute percentage error (MAPE) of the testing set is within 10%, which show that the power values of the following 15 min. can be predicted accurately. The simulation results verify that our method shows better performance than other existing works.

scholarly journals A Study on the Improvement of Efficiency by Detection Solar Module Faults in Deteriorated Photovoltaic Power Plants

2021 ◽  
Vol 11 (2) ◽  
pp. 727 ◽  
Author(s):  
Myeong-Hwan Hwang ◽  
Young-Gon Kim ◽  
Hae-Sol Lee ◽  
Young-Dae Kim ◽  
Hyun-Rok Cha
Keyword(s):  
Power Generation ◽  
Power Plants ◽  
Detection System ◽  
Failure Detection ◽  
Solar Module ◽  
Thermal Images ◽  
Power Stations ◽  
Photovoltaic Power ◽  
Manufacturing Technologies ◽  
Pv Power Generation

In recent years, photovoltaic (PV) power generation has attracted considerable attention as a new eco-friendly and renewable energy generation technology. With the recent development of semiconductor manufacturing technologies, PV power generation is gradually increasing. In this paper, we analyze the types of defects that form in PV power generation panels and propose a method for enhancing the productivity and efficiency of PV power stations by determining the defects of aging PV modules based on their temperature, power output, and panel images. The method proposed in the paper allows the replacement of individual panels that are experiencing a malfunction, thereby reducing the output loss of solar power generation plants. The aim is to develop a method that enables users to immediately check the type of failures among the six failure types that frequently occur in aging PV panels—namely, hotspot, panel breakage, connector breakage, busbar breakage, panel cell overheating, and diode failure—based on thermal images by using the failure detection system. By comparing the data acquired in the study with the thermal images of a PV power station, efficiency is increased by detecting solar module faults in deteriorated photovoltaic power plants.

Operation of a Micro Off-Shore Island Considering PV Power Generation Ramp-Rates

2018 ◽  
Author(s):  
Cheng-Ting Hsu ◽  
Hung-Ming Huang ◽  
Tsun-Jen Cheng ◽  
Yih-Der Lee ◽  
Yung-Ruei Chang ◽  
...  
Keyword(s):  
Power Generation ◽  
Pv Power Generation

Potential Impacts of Net-Zero Energy Buildings With Distributed Photovoltaic (PV) Power Generation on the Electrical Grid

2018 ◽  
Author(s):  
Dongsu Kim ◽  
Heejin Cho ◽  
Rogelio Luck
Keyword(s):  
Power Generation ◽  
Electricity Demand ◽  
Office Buildings ◽  
Office Building ◽  
Electrical Grid ◽  
Net Zero ◽  
Demand Profile ◽  
The Impact ◽  
Pv Power Generation ◽  
The U.S

This study evaluates potential aggregate effects of net-zero energy building (NZEB) implementations on the electrical grid in simulation-based analysis. Many studies have been conducted on how effective NZEB designs can be achieved, however the potential impact of NZEBs have not been explored sufficiently. As significant penetration of NZEBs occurs, the aggregated electricity demand profile of the buildings on the electrical grid would experience dramatic changes. To estimate the impact of NZEBs on the electrical grid, a simulation-based study of an office building with a grid-tied PV power generation system is conducted. This study assumes that net-metering is available for NZEBs such that the excess on-site PV generation can be fed to the electrical grid. The impact of electrical energy storage (EES) within NZEBs on the electrical grid is also considered in this study. Finally, construction weighting factors of the office building type in U.S. climate zones are used to estimate the number of national office buildings. In order to consider the adoption of NZEBs in the future, this study examines scenarios with 20%, 50%, and 100% of the U.S. office building stock are composed of NZEBs. Results show that annual electricity consumption of simulated office buildings in U.S. climate locations includes the range of around 85 kWh/m2-year to 118 kWh/m2-year. Each simulated office building employs around 242 kWp to 387 kWp of maximum power outputs in the installation of on-site PV power systems to enable NZEB balances. On a national scale, the daily on-site PV power generation within NZEBs can cover around 50% to 110% of total daily electricity used in office buildings depending on weather conditions. The peak difference of U.S. electricity demand typically occurs when solar radiation is at its highest. The peak differences from the actual U.S. electricity demand on the representative summer day show 9.8%, 4.9%, and 2.0% at 12 p.m. for 100%, 50%, and 20% of the U.S. NZEB stocks, respectively. Using EES within NZEBs, the peak differences are reduced and shifted from noon to the beginning of the day, including 7.7%, 3.9%, and 1.5% for each percentage U.S. NZEB stock. NZEBs tend to create the significant curtailment of the U.S. electricity demand profile, typically during the middle of the winter day. The percentage differences at a peak point (12 p.m.) are 8.3%, 4.2%, and 1.7% for 100%, 50%, and 20% of the U.S. NZEB stocks, respectively. However, using EES on the representative winter day can flatten curtailed electricity demand curves by shifting the peak difference point to the beginning and the late afternoon of the day. The shifted peak differences show 7.4%, 3.7%, and 1.5% at 9 a.m. for three U.S. NZEB stock scenarios, respectively.

Sign in / Sign up

Export Citation Format

Share Document