Solar energy is one of the most important forms of renewable energy for generating electricity. The efficiency of Photovoltaic (PV) panels that produce electricity depends on the continuously changing weather paramete...
详细信息
ISBN:
(数字)9798331528171
ISBN:
(纸本)9798331528188
Solar energy is one of the most important forms of renewable energy for generating electricity. The efficiency of Photovoltaic (PV) panels that produce electricity depends on the continuously changing weather parameters like dust, wind speed, wind direction, ambient temperature, module temperature, relative humidity and most importantly the solar irradiation. The dust particles in the atmosphere, like the other weather parameters, is also changing continuously and plays a major role in reducing the sunlight on the PV panels by scattering, absorbing or reflecting the incoming sunlight. This leads to reduced efficiency in the production of electricity and consequently the DC power generated from the PV panels will be less. This paper aims to build a model using machine learning algorithms to predict the output DC power due to the dust (PM 2.5 and PM 10 concentrations are considered in the dataset), wind speed, wind direction, the ambient temperature of the region where the PV panels are placed, the module temperature, the relative humidity. Using this dataset, a random forest model (by implementing a machine learning algorithm known as the Random Forest Algorithm) was developed and implemented. This model achieved a mean absolute error (MAE) of 482.02 Watts and an R-squared score of 0.873 and can be used to achieve optimized performance and efficient energy conversion of PV systems.
Microgrids have become a promising decentralized and effective energy distribution alternative in modern power systems. Energy storage systems (ESS) management is a crucial component of microgrid operation to maintain...
详细信息
Low voltage next-generation unified multi-input multi-output (U-MIMO) system-based AC-DC microgrids (MGs), equipped with distributed renewable resources (DERs), significantly contribute to sustainable development by o...
详细信息
ISBN:
(数字)9798350364866
ISBN:
(纸本)9798350364873
Low voltage next-generation unified multi-input multi-output (U-MIMO) system-based AC-DC microgrids (MGs), equipped with distributed renewable resources (DERs), significantly contribute to sustainable development by offering reliable, decentralized and scalable electricity. It alleviates the burden on the main grid and promotes socio-economic development. However, challenges persist in power management, power quality and the high installation costs of battery management systems (BMS). To address these issues, this study introduces a modified hybrid U-MIMO system to optimize MGs. This system provides an all-weather synchronized solution, integrating multi-located PV nanoarrays and single-phase grid supply as multi-input sources for AC-DC multi-output loads with a bi-directional BMS. Grid interaction reduces the required battery capacity and thus lowers installation costs. The modified U-MIMO system enhances power management by accounting for BMS state of charge (SOC) and power generation from DERs. This study uses a single-phase induction motor and a rectifier with inductive load as non-linear AC loads, while an EV battery serves as the DC load. Multi-control structures within the hybrid U-MIMO system ensure a constant DC bus voltage, adhering to IEEE 519 standards. A comprehensive analysis with two modes and one scenario demonstrates effective power management, synchronization and power quality control, validating the system's capability to support diverse loads and applications efficiently.
As solar energy continues to increase its share in the electrical mix, accurate forecasting of photovoltaic (PV) output will play an increasingly critical role in grid integration. This paper presents a comparative st...
详细信息
ISBN:
(数字)9798331507671
ISBN:
(纸本)9798331507688
As solar energy continues to increase its share in the electrical mix, accurate forecasting of photovoltaic (PV) output will play an increasingly critical role in grid integration. This paper presents a comparative study of four machine learning models, K-Nearest Neighbors (KNN), Random Forest, XGBoost, and Linear Regression, in addition to physical and statistical methodologies for forecasting PV power. Real-field data is used in this work to enhance the trustworthiness and importance of the findings. It also shows the influence of certain input parameters, such as air temperature, runtime hours, and dust, on the performance of the models. Also, the assessment of all models is done using several evaluation criteria, which include mean absolute error (MAE), root mean squared error (RMSE), $\mathbf{R}$ squared (R2) and mean percentage error (MPE), in order to guarantee that there is no bias in the evaluation. The result shows XGBoost as the best-performing model.
Photovoltaic (PV) systems exhibit a high degree of environmental sensitivity, which can result in power losses and reduced system efficiency. To analyze power loss in PV systems, this paper presents an analytical meth...
详细信息
ISBN:
(数字)9798350367065
ISBN:
(纸本)9798350367072
Photovoltaic (PV) systems exhibit a high degree of environmental sensitivity, which can result in power losses and reduced system efficiency. To analyze power loss in PV systems, this paper presents an analytical method that uses the Random Forest algorithm while accounting for environmental factors like dust density, temperature, irradiance, humidity, and wind speed. To investigate these relationships, cross-sectional data were analyzed. The data came from rooftop PV plant situated at a university in Delhi, India, were collected between January 1, 2021, and December 31, 2021. Because of its ability to manage non-linear relationships between variables and enable a thorough understanding of complex interactions, the Random Forest model was chosen. It can be helpful in predicting power outages as well as identifying how specific environmental factors affected the operation of the system. Pair plots and scatter plots were used in data preprocessing and exploratory analysis to show that dust concentration is one of the main factors affecting power loss. Dust concentration is closely correlated with ambient temperature, highlighting the urgent need for strategies to mitigate these impacts to increase the efficiency of PV systems. The data reveals that power loss peaks around 2000 W, indicating a significant loss threshold. The results highlight the need for ongoing observation and flexible management to improve performance in a variety of environmental settings.
This study explores data-driven methodologies for State of Health (SOH) and Remaining Useful Life (RUL) prediction of lithium-ion batteries, vital for electric vehicle (EV) adoption. Leveraging NASA and Oxford Battery...
详细信息
ISBN:
(数字)9798350364729
ISBN:
(纸本)9798350364736
This study explores data-driven methodologies for State of Health (SOH) and Remaining Useful Life (RUL) prediction of lithium-ion batteries, vital for electric vehicle (EV) adoption. Leveraging NASA and Oxford Battery Degradation datasets, advanced state of the art machine learning techniques like LSTM networks and Transformers and Gated Recurrent Unit (GRU) are integrated to develop and validate a predictive model. Challenges such as non-linear behavior and limited data are addressed with a novel neural network. A comprehensive literature review along with comparative analysis is done to assess the better performing model and it’s strengths compared to others. The study advances battery health prediction technologies, enhancing EV battery reliability and efficiency.
The squirrel cage induction machine (SCIM) based water pumping system (WPS) remains a cost-effective and robust option compared to other alternatives. However, the voltage-to-frequency-based controllers and direct-on-...
详细信息
ISBN:
(数字)9798350383997
ISBN:
(纸本)9798350384000
The squirrel cage induction machine (SCIM) based water pumping system (WPS) remains a cost-effective and robust option compared to other alternatives. However, the voltage-to-frequency-based controllers and direct-on-line (DOL) start of SCIM within solar PV-based microgrids (MGs) result in voltage dips and harmonic disturbances. Hence, other electrical applications can't be used in parallel. The SCIM needs a dedicated system that increases the overall cost. Hence, maintaining load voltage and frequency constant in a power system with IEEE 519 standards is very critical with a SCIM-based WPS. To address this issue, a secondary droop-control supported cascaded proportional resonant (CPR) controller has been proposed and tested for a three-phase voltage source inverter (VSI) in a grid-interactive solar PV system for SCIM-based WPS. The objective is to keep constant load voltage and frequency with enhanced power quality as per IEEE 519 standards and optimize power management so that other applications can also be used in parallel with the same controller. Additionally, a “Grid-Start Grid-Run” mode has been discussed to protect solar modules from over-current during the DOL start of the WPS. The DC link voltage is regulated to ensure the motor torque and speed remain within specified operational parameters. The proposed control is stable, robust, and cost-effective, offering the flexibility to operate in islanded mode when necessary.
The efficiency of photovoltaic (PV) systems is an important component in delivering high revenue to achieve the necessary goals at minimum cost and to overcome various climatic conditions in different areas. This pape...
详细信息
ISBN:
(数字)9798331528171
ISBN:
(纸本)9798331528188
The efficiency of photovoltaic (PV) systems is an important component in delivering high revenue to achieve the necessary goals at minimum cost and to overcome various climatic conditions in different areas. This paper aims to provide detailed techno-economic investigation of a PV system installed in a university in Delhi, India for one year. The analysis targets fundamental technical parameters namely AC power inverter indications, solid and baseline solar irradiation data, real-time yield as well as possible output. A comparison is then made of the expected production levels at 100% efficiency, 80% efficiency, and 60% efficiency then comparing the forecasted values with the production rates while considering breakdown losses, performance deviations, and energy losses during communication downtimes. In parallel, qualitative assessment validates the impact of operational inefficiencies on the profitability of the organization, and numerical assessment of ROI, the operation and manufacturing costs, and consequences of production inefficiency. The additional combination of both technical and financial data provides a comprehensive understanding of system performance by showing how technical variations including those in the solar irradiation and in the efficiency of the system have impacts on financial aspects in the long run. Thus, providing correlation of these technical and financial parameters of this study will create a framework of how to enhance performance of the PV system and how to make good financial decisions. The findings help to enhance the knowledge of actual performance of PV systems and provide useful information for enhancement of PV systems design, control and economic assessment in the renewable power generation industry.
This work proposes Lyapunov theory based Fuzzy/Neural Reinforcement Learning (RL) controllers with guaranteed stability. We look at ways in which Lyapunov theory could be used to produce RL controllers wherein the con...
详细信息
A potent technology for demand response is proposed in this paper. The proposed algorithm is believed to bring significant monetary increments and improvements in grid stability, especially within the emerging context...
详细信息
ISBN:
(数字)9798350364866
ISBN:
(纸本)9798350364873
A potent technology for demand response is proposed in this paper. The proposed algorithm is believed to bring significant monetary increments and improvements in grid stability, especially within the emerging context of renewables as well as Electric Vehicles (EVs). This research presents an innovative strategy for finding residential participants with load profiles alone for maintaining grid stability, which is useful in data-scarce countries like India. The proposed algorithm aimed at maximizing customer and grid benefits. Additionally, the adoption of Distributed Energy Resources (DERs) will make Demand Side Management (DSM) strategies more effective, thus underlining their significance in molding a sustainable energy environment. More importantly, the study contributes to the knowledge of economic DSM practices outlining DER integration for future energy resilience and sustainability.
暂无评论