scholarly journals Evaluation of Photovoltaic Power Generation by using Deep Learning in Solar Panels Installed in Buildings

Energies ◽  
2019 ◽  
Vol 12 (18) ◽  
pp. 3564 ◽  
Author(s):  
Wei
Keyword(s):  
Neural Network ◽  
Power Generation ◽  
Deep Learning ◽  
Power Output ◽  
Solar Panel ◽  
Second Phase ◽  
Solar Panels ◽  
Generation Efficiency ◽  
Southern Taiwan ◽  
Pv Power Generation

Southern Taiwan has excellent solar energy resources that remain largely unused. This study incorporated a measure that aids in providing simple and effective power generation efficiency assessments of solar panel brands in the planning stage of installing these panels on roofs. The proposed methodology can be applied to evaluate photovoltaic (PV) power generation panels installed on building rooftops in Southern Taiwan. In the first phase, this study selected panels of the BP3 series, including BP350, BP365, BP380, and BP3125, to assess their PV output efficiency. BP Solar is a manufacturer and installer of photovoltaic solar cells. This study first derived ideal PV power generation and then determined the suitable tilt angle for the PV panels leading to direct sunlight that could be acquired to increase power output by panels installed on building rooftops. The potential annual power outputs for these solar panels were calculated. Climate data of 2016 were used to estimate the annual solar power output of the BP3 series per unit area. The results indicated that BP380 was the most efficient model for power generation (183.5 KWh/m2-y), followed by BP3125 (182.2 KWh/m2-y); by contrast, BP350 was the least efficient (164.2 KWh/m2-y). In the second phase, to simulate meteorological uncertainty during hourly PV power generation, a surface solar radiation prediction model was developed. This study used a deep learning–based deep neural network (DNN) for predicting hourly irradiation. The simulation results of the DNN were compared with those of a backpropagation neural network (BPN) and a linear regression (LR) model. In the final phase, the panel of module BP3125 was used as an example and demonstrated the hourly PV power output prediction at different lead times on a solar panel. The results demonstrated that the proposed method is useful for evaluating the power generation efficiency of the solar panels.

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.

Investigation of Fresnel Lens Effect on Solar Panel Power Generation

2021 ◽  
Vol 80 (1) ◽  
pp. 37-49
Author(s):  
Abdul Hadi Mohaimin ◽  
Md. Rakib Uddin ◽  
Hasnul Hashim
Keyword(s):  
Power Generation ◽  
Power Output ◽  
Load Resistance ◽  
Fresnel Lens ◽  
Solar Panel ◽  
Heat Absorption ◽  
Solar Power Generation ◽  
Voltage Output ◽  
Long Run ◽  
Power Outputs

Solar panel power output can still be improved through various means. The aim of this paper is to investigate the effect on solar panel power generation due to Fresnel lens distance to the solar panel. The use of Fresnel lens is to magnify the light intensity from the sun to achieve higher solar collectability of solar panel which may increase power output. The Fresnel lens is to be positioned on top of the solar panel to concentrate the sunlight on to the solar panel. Voltages are measured by an electronic microcontroller with a 10-second interval while power output are determined by the product of voltage and load resistance connected to the solar panel. Immediate results were an instantaneous rise in voltage output but gradually decreasing with increase heat absorption in the solar panel. In the long run, voltage and power outputs were obtained at 0, 5, 10, 20, 30 and 40 cm Fresnel lens distance to the solar panel where all results saw the reduction in voltage and power generation from the solar panel incorporated with Fresnel lens compared to one without due to high ambient temperature. Because of this, it is deemed unfeasible to use Fresnel lens for solar power generation in hot areas such as those with equatorial or tropical climate.

scholarly journals Forecasting Day-Ahead Hourly Photovoltaic Power Generation Using Convolutional Self-Attention Based Long Short-Term Memory

Energies ◽  
2020 ◽  
Vol 13 (15) ◽  
pp. 4017 ◽  
Author(s):  
Dukhwan Yu ◽  
Wonik Choi ◽  
Myoungsoo Kim ◽  
Ling Liu
Keyword(s):  
Power Generation ◽  
Deep Learning ◽  
Prediction Accuracy ◽  
Short Term Memory ◽  
Local Context ◽  
Short Term ◽  
Term Memory ◽  
Proposed Model ◽  
Long Short Term Memory ◽  
Pv Power Generation

The problem of Photovoltaic (PV) power generation forecasting is becoming crucial as the penetration level of Distributed Energy Resources (DERs) increases in microgrids and Virtual Power Plants (VPPs). In order to improve the stability of power systems, a fair amount of research has been proposed for increasing prediction performance in practical environments through statistical, machine learning, deep learning, and hybrid approaches. Despite these efforts, the problem of forecasting PV power generation remains to be challenging in power system operations since existing methods show limited accuracy and thus are not sufficiently practical enough to be widely deployed. Many existing methods using long historical data suffer from the long-term dependency problem and are not able to produce high prediction accuracy due to their failure to fully utilize all features of long sequence inputs. To address this problem, we propose a deep learning-based PV power generation forecasting model called Convolutional Self-Attention based Long Short-Term Memory (LSTM). By using the convolutional self-attention mechanism, we can significantly improve prediction accuracy by capturing the local context of the data and generating keys and queries that fit the local context. To validate the applicability of the proposed model, we conduct extensive experiments on both PV power generation forecasting using a real world dataset and power consumption forecasting. The experimental results of power generation forecasting using the real world datasets show that the MAPEs of the proposed model are much lower, in fact by 7.7%, 6%, 3.9% compared to the Deep Neural Network (DNN), LSTM and LSTM with the canonical self-attention, respectively. As for power consumption forecasting, the proposed model exhibits 32%, 17% and 44% lower Mean Absolute Percentage Error (MAPE) than the DNN, LSTM and LSTM with the canonical self-attention, respectively.

scholarly journals Designing and Modeling of Solar Panel with Dish Reflector for Productive Improvement by Optimum Utilisation of Plant Area

2019 ◽  
Vol 8 (3) ◽  
pp. 3955-3957
Keyword(s):  
Power Generation ◽  
Power Plant ◽  
Light Intensity ◽  
Solar Panel ◽  
Solar Power Plant ◽  
Solar Panels ◽  
Factors Associated ◽  
Plant Area ◽  
Parabolic Dish ◽  
Solar Rays

In this paper, we propose a conceptual design to reduce the solar power plant area by using dish reflector and solar panel arrangement by placing the solar panel at 90° angle. The solar rays get redirected into the box with the help of parabolic dish reflectors which results reduced size requirement for the panel installation. The reflective surface increases both light intensity as well as power generation by the solar panel. Also, the usual factors associated with general installation method like dust or snow formation and bird dropping over the panels that affect the efficiency of solar panels are avoided in this light box concept.

scholarly journals Efficiency Measurement and Factor Analysis of China’s Solar Photovoltaic Power Generation Considering Regional Differences Based on a FAHP–DEA Model

Energies ◽  
2020 ◽  
Vol 13 (8) ◽  
pp. 1936
Author(s):  
Jing Yang ◽  
Changhui Yang ◽  
Xiaojia Wang ◽  
Manli Cheng ◽  
Jingjing Shang
Keyword(s):  
Power Generation ◽  
Energy Structure ◽  
Data Envelopment ◽  
Tobit Regression ◽  
Process Data ◽  
Generation Efficiency ◽  
Analytic Hierarchy ◽  
Dea Model ◽  
Hierarchy Process ◽  
Pv Power Generation

Driven by the transformation of the energy structure, China’s photovoltaic (PV) power generation industry has made remarkable achievements in recent years. However, there are more than 30 regions (cities/provinces) in China, and the economic, policy, technological, and the environmental conditions of each region are significantly different, which leads to a huge discrepancy in PV power generation efficiency. To address the imbalance in the development of PV industry, first, this paper employed the integrated fuzzy analytic hierarchy process–data envelopment analysis (FAHP–DEA) model to evaluate the PV power generation efficiency of 30 regions in China. Second, Tobit regression model was used to examine the effects of 9 potential influencing factors. Third, a concrete analysis was conducted, and discussion based on the efficiency rankings and regression results was made. Additionally, the FAHP–DEA model proposed in this study can also be applied to the efficiency evaluation issues of other types of renewable energy.

scholarly journals An Experimental Investigation of Wake Characteristics and Power Generation Efficiency of a Small Wind Turbine under Different Tip Speed Ratios

Energies ◽  
2020 ◽  
Vol 13 (8) ◽  
pp. 2113 ◽  
Author(s):  
Yu-Ting Wu ◽  
Chang-Yu Lin ◽  
Che-Ming Hsu
Keyword(s):  
Power Generation ◽  
Wind Turbine ◽  
Power Output ◽  
Estimation Method ◽  
Mechanical Power ◽  
Power Coefficient ◽  
Regulation System ◽  
Generation Efficiency ◽  
Blade Rotation ◽  
Wake Characteristics

We carried out a wind tunnel experiment to examine the power generation efficiency of a stand-alone miniature wind turbine and its wake characteristics at different tip speed ratios (TSRs) under the same mean inflow velocity. Resistors in the electrical circuit were adjusted to control the TSRs to 0.9, 1.5, 3.0, 4.1, 5.2, and 5.9. The currents were measured to estimate the turbine power outputs versus the TSRs and then establish the actual power generation coefficient Cp distribution. To calculate the mechanical power coefficient, a new estimation method of the mechanical torque constant is proposed. A reverse calibration on the blade rotation speed was performed with given electrical voltages and currents that are used to estimate the mechanical power coefficient Cp, mech. In the experiment, the maximum Cp,mech was approximately 0.358 (corresponding to the maximum Cp of 0.212) at the TSR of 4.1. Significant findings indicate that the turbine at the TSR of 5.2 produces a smaller torque but a larger power output compared with that at the TSR of 3.0. This comparison further displays that the turbine at the TSR of 5.2, even with larger power output, still produces a turbine wake that has smaller velocity deficits and smaller turbulence intensity than that at the TSR of 3.0. This behavior demonstrates the significance of the blade-rotation control (i.e., pitch regulation) system to the turbine operation in a large wind farm for raising the overall farm power productivity.

Solar Panel Automatic Positioning and Maximum Light Flux Direction Tracking

2021 ◽  
pp. 115-132
Author(s):  
K.V. Selivanov
Keyword(s):  
Power Generation ◽  
Alternative Energy ◽  
Power Plants ◽  
Light Flux ◽  
Solar Panel ◽  
Solar Panels ◽  
Moving Vehicle ◽  
New Device ◽  
Maximum Light ◽  
Automatic Positioning

The paper analyzes the state and possible ways of development of alternative energy, describes the prospects for the development of solar power plants, their classification and areas of application. Within the research, we revealed the problems that arise when installing and operating solar panels and identified the reasons that reduce their efficiency. Consequently, we analyzed the ways to increase the efficiency of power generation by solar panels and suggested solar panel automatic positioning and maximum light flux direction tracking as a possible solution to the problem. The study introduces a new device for positioning solar panels, which is distinguished by the automatic deployment and positioning of solar panels according to the actual direction of the maximum light flux. The device provides possible automation of the installation and greater efficiency of solar panels. The novelty of the device is protected by a utility model patent no. 180765 RF. To confirm the efficiency and to obtain a quantitative value of the increase in power generation by solar panels due to the use of the developed device, we present the comparison methodology and a description of the experiment. The schematic diagram and external view of the developed device are also shown. The experimental results are processed and shown in a graph. The possibility of increasing power generation by solar panels by tracking the maximum light flux and reorienting the solar panel towards it during the day has been confirmed, and a quantitative value of the increase in power generation has been obtained. Based on the positive results of the experiment, the possibility of using the developed device for automating the process of deploying solar panels in an autonomous way and excluding human participation in this process is described. The operation of the developed device on a moving vehicle and other methods of its application are considered. The results are summed up, conclusions are drawn and possible further directions for the development and use of the proposed method for increasing the efficiency of solar panels and the developed device for improving the performance of solar panels are identified

scholarly journals Deep Learning to Forecast Solar Irradiance Using a Six-Month UTSA SkyImager Dataset

Energies ◽  
2018 ◽  
Vol 11 (8) ◽  
pp. 1988 ◽  
Author(s):  
Ariana Moncada ◽  
Walter Richardson ◽  
Rolando Vega-Avila
Keyword(s):  
Deep Learning ◽  
Solar Irradiance ◽  
Imaging System ◽  
San Antonio ◽  
Raspberry Pi ◽  
Solar Panels ◽  
Original Design ◽  
Error Metrics ◽  
Ill Posed ◽  
Pv Power Generation

Distributed PV power generation necessitates both intra-hour and day-ahead forecasting of solar irradiance. The UTSA SkyImager is an inexpensive all-sky imaging system built using a Raspberry Pi computer with camera. Reconfigurable for different operational environments, it has been deployed at the National Renewable Energy Laboratory (NREL), Joint Base San Antonio, and two locations in the Canary Islands. The original design used optical flow to extrapolate cloud positions, followed by ray-tracing to predict shadow locations on solar panels. The latter problem is mathematically ill-posed. This paper details an alternative strategy that uses artificial intelligence (AI) to forecast irradiance directly from an extracted subimage surrounding the sun. Several different AI models are compared including Deep Learning and Gradient Boosted Trees. Results and error metrics are presented for a total of 147 days of NREL data collected during the period from October 2015 to May 2016.

Study of the Energy Consumption Characteristic of a 1000MW Ultra-Supercritical Unit

2013 ◽  
Vol 860-863 ◽  
pp. 629-633
Author(s):  
Feng Ping Pan ◽  
Shi He Chen ◽  
Ya Qing Zhu ◽  
Zhi Qiang Pang ◽  
Shu Mei Wu ◽  
...  
Keyword(s):  
Power Generation ◽  
High Pressure ◽  
Energy Consumption ◽  
Temperature Control ◽  
Power Output ◽  
Superheated Steam ◽  
Unit Operation ◽  
Steam Temperature ◽  
Generation Efficiency ◽  
Superheated Steam Temperature

A 1000MW ultra-supercritical unit was studied to gain the energy consumption characteristics by means of thermodynamic analysis. Comparing with the designed conditions, the power generation efficiency under real operation is much less; especially under 50% and 100% rated loads. The higher superheated steam temperature and lower reheat temperature were found to explain that. At the real running, the higher superheated steam temperature induced more attemperation water, while reheat temperature lower than the designed point would decrease the power output. Aiming at solving issues about temperature control in unit operation, several details could be paid extra attention to. For instance, attemperating water comes from outlet of the high-pressure heaters would have a much slighter influence on generating efficiency.

Sign in / Sign up

Export Citation Format

Share Document