Search

To overcome range anxiety problem of electric vehicles (EVs), an accurate real-time energy consumption estimation is necessary, which can be used to provide the EV's driver with information about the remaining range in real time. A hybrid CNN–BDT approach has been developed, in which convolutional neural network (CNN) is used to provide an energy consumption estimate considering the effect of temperature, wind speed, battery's SOC, auxiliary loads, road elevation, vehicle speed and acceleration. Further, bagged decision tree (BDT) is used to fine-tune the estimate. Unlike existing techniques, the proposed approach does not require internal vehicle parameters from manufacturer and can easily learn complex patterns even from noisy data. The comparison results with existing techniques show that the developed approach provides better estimates with least mean absolute energy deviation of 0.14. [ABSTRACT FROM AUTHOR]

The goal of this work is to reduce driver's range anxiety by estimating the real-time energy consumption of electric vehicles using deep convolutional neural network. The real-time estimate can be used to accurately predict the remaining range for the vehicle and hence, can reduce driver's range anxiety. In contrast to existing techniques, the non-linearity and complexity induced by the combination of influencing factors make the problem more suitable for a deep learning approach. The proposed approach requires three parameters namely, vehicle speed, tractive effort and road elevation. Multiple experiments with different variants are performed to explore the impact of number of layers and input feature descriptors. The comparison of proposed approach and five of the existing techniques show that the proposed model performed consistently better than existing techniques with lowest error. • D-CNN based approach has been proposed to estimate the energy consumption of EVs. • EV manufacturer data is not required to estimate energy using the proposed method. • The model can be trained for any EV using speed, road grade and tractive effort. • Input features like Gramian Angular Field, Covariance & Eigenvector are explored. • The model has achieved a lowest mean percentage energy deviation of 5.09%. [ABSTRACT FROM AUTHOR]

A microgrid is an integrated form of distributed energy resources (DERs) which are connected together to serve electrical power to the selected consumers or can exchange power with the existing utility grid suitably under standalone or grid connected mode. The microgrid can be cited as a physical system which is a combination of DERs such as, Photovoltaic Generator, Wind turbine, Fuel Cell, Microturbine etc. and can be modelled with suitable assumptions depending upon specific operational condition to be studied. Interconnection of several kinds of power sources would impact the quality of power within the microgrid. Since voltage and frequency are not the only factors for a system delivering good quality power, the capacity of the same to withstand instability due to transient condition is one of the prime factors to be considered to accept a system as a stable system. Before practical integration of distributed energy resources, it would be essential to check the stability of the system at the design stage. In this paper, the authors have presented the microgrid based on control system engineering. To represent the individual components of microgrid, the DERs (Distributed Energy Resources) have been represented with their transfer functions and they have been simulated using Simulink-Matlab. To observe the response of the DERs, the frequency fluctuation due to step and random change in output power/load are considered as the main factors for stability analysis. All the DERs are integrated forming the microgrid which is represented with an equivalent transfer function based model. The models are studied and results are discussed with the waveforms. This paper shows one feasible method to check the dynamic stability of a proposed microgrid. [ABSTRACT FROM AUTHOR]