scholarly journals The use of deep recurrent neural networks to predict performance of photovoltaic system for charging electric vehicles

2021 ◽  
Vol 11 (1) ◽  
pp. 377-389
Author(s):  
Arkadiusz Małek ◽  
Andrzej Marciniak
Keyword(s):  
Neural Networks ◽  
Renewable Energy ◽  
Electric Vehicle ◽  
Electric Vehicles ◽  
Recurrent Neural Networks ◽  
Performance Monitoring ◽  
Renewable Energy Sources ◽  
Photovoltaic System ◽  
Energy Sources ◽  
Electric Cars

Abstract Electric vehicles are fully ecological means of transport only when the electricity required to charge them comes from Renewable Energy Sources (RES). When building a photovoltaic carport, the complex of its functions must consider the power consumption necessary to charge an electric vehicle. The performance of the photovoltaic system depends on the season and on the intensity of the sunlight, which in turn depends on the geographical conditions and the current weather. This means that even a large photovoltaic system is not always able to generate the amount of energy required to charge an electric vehicle. The problem discussed in the article is maximization of the share of renewable energy in the process of charging of electric vehicle batteries. Deep recurrent neural networks (RNN) trained on the past data collected by performance monitoring system can be applied to predict the future performance of the photovoltaic system. The accuracy of the presented forecast is sufficient to manage the process of the distribution of energy produced from renewable energy sources. The purpose of the numerical calculations is to maximize the use of the energy produced by the photovoltaic system for charging electric cars.

scholarly journals Development of Fast charging system with ZVS integrated with Fuzzy controller-based Hybrid renewable energy source

2021 ◽  
Vol 2070 (1) ◽  
pp. 012117
Author(s):  
Raghunath Niharika ◽  
K M Sai Pavan ◽  
P V Manitha
Keyword(s):  
Renewable Energy ◽  
Electric Vehicle ◽  
Electric Vehicles ◽  
Fuzzy Controller ◽  
Greenhouse Gas Emission ◽  
Renewable Energy Sources ◽  
Energy Sources ◽  
Pv System ◽  
Charging System ◽  
On The Road

Abstract Climate change is a growing concern due to greenhouse gas emission and transportation has increased the requirement for various energy sources with limiting and less pollution. But with the establishment of more electric vehicles on the road, charging EV’s will be difficult if the grid is used. When many numbers of electric vehicles are integrated to the grid, it will inevitably have a huge effect on its function and control. Hence, there is a requirement for an effective charging system for electric vehicles using renewable energy sources. Solar energy is renewable and green, but the volatile nature of energy from the Photo-Voltaic (PV) system and dynamic charging requirement of electric vehicles has added new problems to the effective charging of EV from these sources. The Solar powered charging station with battery storage system is a better solution for this problem. The power is transferred from the AC grid to the DC link when there is a depletion of power from solar. This paper deals with DC level 1 fast charger to charge an electric vehicle with phase shifted full bridge converter as a main charging topology which is able to deliver the load of 50KW to charge the electric vehicle. To maintain a constant voltage at the output of the boost converter connected to the solar panel, a fuzzy controller is also developed in the proposed system

Machine learning roles in advancing the power network stability due to deployments of renewable energies and electric vehicles

2020 ◽  
Vol 0 (0) ◽  
Author(s):  
Mohamad Nassereddine
Keyword(s):  
Machine Learning ◽  
Renewable Energy ◽  
Electric Vehicles ◽  
Renewable Energy Sources ◽  
Energy Sources ◽  
Power Network ◽  
Network Stability ◽  
Fast Charging ◽  
Electrical Loads ◽  
Charging Stations

AbstractRenewable energy sources are widely installed across countries. In recent years, the capacity of the installed renewable network supports large percentage of the required electrical loads. The relying on renewable energy sources to support the required electrical loads could have a catastrophic impact on the network stability under sudden change in weather conditions. Also, the recent deployment of fast charging stations for electric vehicles adds additional load burden on the electrical work. The fast charging stations require large amount of power for short period. This major increase in power load with the presence of renewable energy generation, increases the risk of power failure/outage due to overload scenarios. To mitigate the issue, the paper introduces the machine learning roles to ensure network stability and reliability always maintained. The paper contains valuable information on the data collection devises within the power network, how these data can be used to ensure system stability. The paper introduces the architect for the machine learning algorithm to monitor and manage the installed renewable energy sources and fast charging stations for optimum power grid network stability. Case study is included.

scholarly journals Optimisation of Energy Accumulation for Renewable Energy Sources

2021 ◽  
Vol 19 ◽  
pp. 205-210
Author(s):  
Milan Belik ◽  
Keyword(s):  
Renewable Energy ◽  
Model Building ◽  
Residential Buildings ◽  
Renewable Energy Sources ◽  
Photovoltaic System ◽  
Energy Sources ◽  
Pv System ◽  
Energy Accumulation ◽  
Wind Power Station ◽  
Future Production

This project focuses on optimisation of energy accumulation for various types of distributed renewable energy sources. The main goal is to prepare charging – discharging strategy depending on actual power consumption and prediction of consumption and production of utilised renewable energy sources for future period. The simulation is based on real long term data measured on photovoltaic system, wind power station and meteo station between 2004 – 2021. The data from meteo station serve as the input for the simulation and prediction of the future production while the data from PV system and wind turbine are used either as actual production or as a verification of the predicted values. Various parameters are used for trimming of the optimisation process. Influence of the charging strategy, discharging strategy, values and shape of the demand from the grid and prices is described on typical examples of the simulations. The main goal is to prepare and verify the system in real conditions with real load chart and real consumption defined by the model building with integrated renewable energy sources. The system can be later used in general installations on commercial or residential buildings.

scholarly journals Selected issues of the design of electrical installation RES type on the example of a home photovoltaic plant

2018 ◽  
Vol 19 (12) ◽  
pp. 66-74
Author(s):  
Marcin Chrzan ◽  
Daniel Pietruszczak ◽  
Mirosław Wiktorowski
Keyword(s):  
Renewable Energy ◽  
System Design ◽  
Renewable Energy Sources ◽  
Photovoltaic System ◽  
Energy Sources ◽  
Photovoltaic Plant ◽  
Electrical Installation

The paper presents issues related to renewable energy sources and their current use. Home photovoltaic installations RES and their types are discussed. It presents the benefits that a basic household can derive from it. Details of the photovoltaic system design in a monocular house are described.

The Forecasting of Renewable Energy Generation for Turkey by Artificial Neural Networks and a Auto-Regressive Integrated Moving-Average Model -2023 Generation Targets by Renewable Energy Resources

2021 ◽  
Author(s):  
özlem karadag albayrak
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Renewable Energy ◽  
Moving Average ◽  
Renewable Energy Sources ◽  
Energy Generation ◽  
Energy Sources ◽  
Ann Model ◽  
Artificial Neural ◽  
Renewable Energy Generation

Abstract Turkey attaches particular importance to energy generation by renewable energy sources in order to remove negative economic, environmental and social effects caused by fossil resources in energy generation. Renewable energy sources are domestic and do not have any negative effect, such as external dependence in energy and greenhouse gas, caused by fossil resources and which constitute a threat for sustainable economic development. In this respect, the prediction of energy amount to be generated by Renewable Energy (RES) is highly important for Turkey. In this study, a generation forecasting was carried out by Artificial Neural Networks (ANN) and Autoregressive Integrated Moving Average (ARIMA) methods by utilising the renewable energy generation data between 1965-2019. While it was predicted by ANN that 127.516 TWh energy would be generated in 2023, this amount was estimated to be 45.457 TeraWatt Hour (TWh) by ARIMA (1.1.6) model. The Mean Absolute Percentage Error (MAPE) was calculated in order to specify the error margin of the forecasting models. This value was determined to be 13.1% by ANN model and 21.9% by ARIMA model. These results suggested that the ANN model provided a more accurate result. It is considered that the conclusions achieved in this study will be useful in energy planning and management.

Sign in / Sign up

Export Citation Format

Share Document