Dangerous driving behaviors are diverse and complex. Determining how to analyze the driving behavior of public drivers objectively and accurately has always been a research challenge. This research proposes a macroscopic and dynamic method for evaluating drivers’ dangerous driving degree based on a fuzzy inference system. It also designs fuzzy-macro long short-term memory (LSTM), a variant of LSTM recurrent neural networks, which can predict drivers’ dangerous driving behaviors and risk degree. We elucidate how a macroscopic fuzzy inference dangerous driving behavior system is designed based on various driving behavior factors and the neuron architecture of the fuzzy-macro LSTM network. We collect real driving behavior data of drivers on the road and conduct a series of experimental analyses. Compared with five other commonly used time-series forecasting neural network models, our fuzzy-macro LSTM model performs best in terms of prediction error. Experimental results verify the effectiveness of the proposed method for macroanalysis and prediction of dangerous driving behavior.

Edge computing exhibits the advantages of real-time operation, low latency, and low network cost. It has become a key technology for realizing smart Internet of Things applications. Microservices are being used by an increasing number of edge computing networks because of their sufficiently small code, reduced program complexity, and flexible deployment. However, edge computing has more limited resources than cloud computing, and thus edge computing networks have higher requirements for the overall resource scheduling of running microservices. Accordingly, the resource management of microservice applications in edge computing networks is a crucial issue. In this study, we developed and implemented a microservice resource management platform for edge computing networks. We designed a fuzzy-based microservice computing resource scaling (FMCRS) algorithm that can dynamically control the resource expansion scale of microservices. We proposed and implemented two microservice resource expansion methods based on the resource usage of edge network computing nodes. We conducted the experimental analysis in six scenarios and the experimental results proved that the designed microservice resource management platform can reduce the response time for microservice resource adjustments and dynamically expand microservices horizontally and vertically. Compared with other state-of-the-art microservice resource management methods, FMCRS can reduce sudden surges in overall network resource allocation, and thus, it is more suitable for the edge computing microservice management environment.

As the demand for electric vehicles (EVs) rises globally, ensuring the safety and reliability of EV battery systems becomes paramount. Accurately predicting the state of health (SoH) and state of charge (SoC) of EV batteries is crucial for maintaining their safe and consistent operation. This paper introduces a novel approach leveraging deep learning methodologies to predict battery SoH, focusing on implementing a system prototype for real-world applications. The proposed system integrates an extended Kalman filter (EKF) with a deep learning framework, forming a system prototype known as FELL, aimed at EV battery diagnosis and prediction. We devise an algorithm utilizing the EKF to estimate the SoH of the battery. We present a detailed overview of the system architecture and implementation, showcasing its predictive capabilities. Experimental results demonstrate the effectiveness of the system in accurately estimating battery SoH with notable improvements in prediction accuracy. Additionally, the FELL system provides users with real-time predictions and comparative analysis across multiple prediction models, offering valuable insights for EV battery management.

The increasing adoption of electric vehicles (EVs) necessitates advanced predictive models to accurately forecast charging demand and ensure reliable infrastructure planning. This study introduces a novel analytical framework that integrates queuing network and Bayesian network models to enhance the prediction accuracy and reliability of EV charging demand. The objective is to develop a comprehensive system that accounts for various influencing factors, such as meteorological conditions and charging pile failure rates, to optimize EV infrastructure. The methodology involves creating a hybrid Bayesian Network-based deep learning (HBNDL) system architecture. This architecture uses extensive transaction data and climate analysis to build a detailed model of EV charging pile reliability. Additionally, two algorithms are designed to assess the usage and reliability of charging stations. The framework's effectiveness is tested through a series of experiments evaluating its performance in short-, medium-, and long-term prediction scenarios. The results demonstrate that the HBNDL framework significantly improves prediction accuracy and infrastructure reliability. The integration of queuing theory and Bayesian network models with deep learning techniques results in a robust system adaptable to various conditions. Experimental validation shows that the proposed framework outperforms existing models in forecasting EV charging demand, particularly under varying environmental influences.

The various applications of the Internet of Things and the Internet of Vehicles impose high requirements on the network environment, such as bandwidth and delay. To meet low-latency requirements, the concept of mobile edge computing has been introduced. Through virtualisation technology, service providers can rent computation resources from the infrastructure of the network operator, whereas network operators can deploy all kinds of service functions (SFs) to the edge network to reduce network latency. However, how to appropriately deploy SFs to the edge of the network presents a problem. Apart from improving the network efficiency of edge computing service deployment, how to effectively reduce the cost of service deployment is also important to achieve a performance-cost balance. In this paper, we present a novel SF deployment management platform that allows users to dynamically deploy edge computing service applications with the lowest network latency and service deployment costs in edge computing network environments. We describe the platform design and system implementation in detail. The core platform component is an SF deployment simulator that allows users to compare various SF deployment strategies. We also design and implement a genetic algorithm-based service deployment algorithm for edge computing (GSDAE) in network environments. This method can reduce the average network latency for a client who accesses a certain service for multiple tenants that rent computing resources and subsequently reduce the associated SF deployment costs. We evaluate the proposed platform by conducting extensive experiments, and experiment results show that our platform has a practical use for the management and deployment of edge computing applications given its low latency and deployment costs not only in pure edge computing environments but also in mixed edge and cloud computing scenarios.