In today's world, electric vehicles (EVs) play a significant role in transportation automation systems, and these vehicles are the replacement for fossil fuel usage vehicles. An EV generally depends on electric charges where the appropriate usage, charging, and energy management are the key constraints in EVs. To overcome these issues, proper energy management is essential in current EV management. In this paper, a novel blockchain‐based secure energy management has been proposed to provide efficient energy management in transportation automation. Primarily, the EVs have connected to the Internet of Things (IoT) sensors for collecting information like charging level, distance to be traveled, and location of the EVs. This information has been processed by an information center and transferred to the random forest classifier to identify the price of charging. Afterward, it can be transferred to the power scheduling algorithm for finding the nearest charging location (shortest distance) and time of charging to a specific EV. Finally, this information is stored in blocks to mitigate the misleading of EVs and to offer secure price transactions between the users and charging stations. The results manifest that the proposed scheme provides improved EV management with 94.5% of accuracy and maintains 10% lesser communication overhead as compared with existing state‐of‐the‐art techniques.

An energy‐efficient blockchain approach for secure communication in IoT‐enabled electric vehicles

AbstractA precise and real-time object detection system is crucial to ensuring the safety, smoothness, and trust of Autonomous Vehicles (AVs). Several machine learning techniques have been designed to improve vehicle detection capabilities and reduce the shortcomings caused by limited data and by transferring these data to a central server, which has shown poor performance under different conditions. In this paper, we propose an active federated learning-integrated solution over AVs that capitalizes on the You Only Learn One Representation (YOLOR) approach, a Convolutional Neural Network (CNN) specifically designed for real-time object detection. Our approach combines implicit and explicit knowledge, together with active learning and federated learning with the aim of improving the detection accuracy. Experiments show that our solution achieves better performance than traditional solutions (i.e., Gossip decentralized model and Centralized model).KeywordsAutonomous vehiclesActive LearningFederated LearningYOLORObject detectionEdge computing 

Active Federated YOLOR Model for Enhancing Autonomous Vehicles Safety

Electricity is one of the mandatory commodities for mankind today. To address challenges and issues in the transmission of electricity through the traditional grid, the concepts of smart grids and demand response have been developed. In such systems, a large amount of data is generated daily from various sources such as power generation (e.g., wind turbines), transmission and distribution (microgrids and fault detectors), load management (smart meters and smart electric appliances). Thanks to recent advancements in big data and computing technologies, Deep Learning (DL) can be leveraged to learn the patterns from the generated data and predict the demand for electricity and peak hours. Motivated by the advantages of deep learning in smart grids, this paper sets to provide a comprehensive survey on the application of DL for intelligent smart grids and demand response. Firstly, we present the fundamental of DL, smart grids, demand response, and the motivation behind the use of DL. Secondly, we review the state-of-the-art applications of DL in smart grids and demand response, including electric load forecasting, state estimation, energy theft detection, energy sharing and trading. Furthermore, we illustrate the practicality of DL via various use cases and projects. Finally, we highlight the challenges presented in existing research works and highlight important issues and potential directions in the use of DL for smart grids and demand response.

Deep Learning for Intelligent Demand Response and Smart Grids: A Comprehensive Survey.

Electric mobility is a promising global method for reducing carbon emissions in the transportation industry. India is one among few countries to back the global EV30@30 initiative, which aims for 30% of new vehicle sales to be electric by 2030. In this regard, both public and private sector companies have shown extreme interest and growth in this new vertical. On the other hand, developing an ecofriendly charging station is a real challenge in the current scenario. Hence there is a real need to develop a smart charging station. The aim of the proposed study is to develop a prototype of RFID based electric vehicle charging station. The study involves two modules namely coin acceptor and RFID identification module to facilitate both Card-based and physical currency (coin)-based interactions. In the proposed modules the study focuses on providing a user friendly platform facilitating, emergency cut off and repay policy for the duration left uncharged during the charging process of electric vehicle. And moreover the developed module can be switched in to coin or RFID based setup based on the need of the end user. In the prototype, the user is provided with an option to choose either coin or RFID based transaction. Upon coin insertion, the initiation of charging the vehicle is indicated by a blue LED and completion of the charging process is also notified. The module has facility to showcase the time left for charging and also the balance amount in the user valet. Hence the developed prototype would facilitate a user friendly ambience for forthcoming generation of electric vehicle.

Coin and RFID Based EV Charging Station

Wind Speed Short-Term Prediction Based on Empirical Wavelet Transform, Recurrent Neural Network and Error Correction

In order to reduce the greenhouse gas emission and limit the rise in global temperature, the trend in automotive industry is changing rapidly and most of the manufacturers are moving towards the electrification of vehicles. Computational intelligence and machine learning play a very important role in the field of electric vehicles (EVs) due to the necessity of automatic control in battery charging and port accessibility. Due to the limited ranges of EVs, they have to be charged periodically during their travels and its charging will take more time. As the number of EVs increases, suitable charging infrastructure having many charging stations and co‐ordination of scheduling the charging vehicles from charging stations are necessary. As charging stations have less number of fast charging ports, accessing these fast charging ports needs proper planning. The major challenge of an EV is to identify the charging station with a fast charging port which is on route to the destination with minimum waiting time. This article deals with the application of machine learning in selecting a charging station with available fast charging port and minimum waiting time.

R. Resmi

Papers

Machine learning‐based charge scheduling of electric vehicles with minimum waiting time