As motor, electrical control, and battery technology progress, electric vehicles (EVs) are becoming increasingly prevalent. The electronic-electrical (EE) architecture of EVs has been refined, offering a fertile environment for developing intelligent connected vehicles. The integration of vehicles with technologies like big data and cloud platforms gave rise to the Internet of Vehicles (IoV), Vehicle-toEverything (V2X) communication technology, and the concept of Intelligent Connected Vehicles (ICVs). By investigating the technologies of ICVs and IoV, the development background, research status of V2X communication technology and cloud platform big data technology are presented in this study. It also analyzes the challenges of the current application of these technologies in the ICV and IoV and proposes technical solutions to the corresponding problems in light of the challenges. Furthermore, it looks forward to the future development of IoV technology and ICVs and puts forward personal suggestions.

With the advancement of system-on-chip (SOC) technology, automotive electronic control units (ECUs) have shifted from the distributed heterogeneous multiprocessor architecture to the centralized heterogeneous multicore processor architecture. This transformation provides a high-speed inter-core data exchange mechanism based on shared memory. In the distributed architectures, automotive communication software predominantly leverages the CAN bus for inter-core communication, which fundamentally differs from shared memory-based communication methods. This difference can cause significant porting difficulties when porting existing communication software to new hardware architectures. Balancing communication performance and porting efficiency has become a new challenge. To this end, we introduce a communication framework for CAN bus in heterogeneous multicore systems, namely—VirtCAN, which is optimized based on the mainstream heterogeneous multicore communication framework RPMsg. RPMsg is a lightweight inter-core communication framework for heterogeneous multicore systems based on shared memory. VirtCAN emulates the functions of actual CAN controllers by optimizing and encapsulating RPMsg. This approach preserves the original CAN communication method while enabling faster inter-core data exchange through shared memory, thereby achieving a balance between software porting efficiency and communication performance. Experiments were conducted on heterogeneous multicore processors based on ARM architecture, validating VirtCAN's significant communication advantages over the CAN bus and the original RPMsg.

High-performance domain controllers' hardware and software are put to the test by the growing array of additional capabilities found in smart, connected cars. In smart connected automobiles, the energy consumption of high-performance domain controllers is contributing to the whole vehicle's energy consumption at an increasing rate, even though hardware systems' computing capacity is also expanding quickly. Thus, it is crucial to research reducing processor energy consumption while maintaining system performance and dependability. This paper investigates the problem of energy-optimized task scheduling in an on-board operating system for SOA-oriented architectures by combining the DVFS technique and the DAG task model under the constraints of scheduling duration and reliability. Firstly, the energy-optimal task scheduling problem for heterogeneous multicore systems is described, focusing on the constraints of scheduling duration and reliability. The shortcomings of traditional task scheduling algorithms are also analyzed. Secondly, a task scheduling algorithm based on the meta-heuristic Whale Optimization Algorithm (WOA) is proposed. This algorithm includes the design of encoding, decoding, and constraint processing schemes, and assigns processing units and corresponding DVFS levels to each task in the DAG task set to achieve energy consumption optimization while satisfying constraints. To address the suboptimal performance of the Whale Optimization Algorithm in high-dimensional problems, a multi-strategy optimization approach is introduced. This enhanced algorithm incorporates chaotic mapping, adaptive nonlinear convergence factors, dynamic inertia coefficients, the Lévy flight strategy, and the evolutionary population dynamics strategy. Finally, the effectiveness of the proposed algorithm is validated through simulation experiments.

With the rapidly growing Intelligent Connect-ed Vehicle (ICV) industry, modern Advanced Driver Assistance Systems (ADAS) integrate critical and non-critical software functions on the same hardware platform. These functions have complex timing requirements and associated dependencies. To ensure the real-time safety of critical au-tomotive applications, complex task chains with dependencies generated by automotive applications (e.g. sensor data acquisition, data processing, and control execution) must meet the worst end-to-end latency. The resulting task sched-uling problem requires the assignment of tasks to available cores for execution and the generation of static schedules that satisfy the timing constraints of the tasks and the end-to-end latency of the task chain. In this paper, a task sched-uling and task mapping method based on an intelligent heu-ristic algorithm is proposed for the ADAS platform, and simulated scheduling based on the EDF algorithm. The op-timal task scheduling scheme is selected by calculating the fitness function by the intelligent heuristic algorithm, and the simulated annealing algorithm (SA) is selected as the benchmark for the experiment. The experimental results show that the grey wolf optimizer converges faster and finds a better scheduling scheme, which reduces the total time of scheduling tasks.

Linux as a GPOS has the advantages of high average system throughput performance, a large number of open-source solutions, etc. It is a mature and complete operating system that can be used for in-vehicle system development. However, the vehicle in motion will produce a large number of real-time tasks, that need to be processed by the system promptly, and Linux's kernel preemption mechanism and interrupt mechanism are not designed to deal with real-time tasks, so they need to be improved. In this paper, we analyze the operation principle of each part of the Linux system, expound on the shortcomings of Linux as a real-time system, and then analyze the enhancement principle of Preempt_RT and Xenomai two kinds of patches on Linux real-time, and finally, we analyze the experimental data by carrying out experiments and applying probabilistic statistics to derive the results of Xenomai and Preempt_RT for Xenomai and Preempt_RT improve the task response latency of Linux system by 250% and 114%, respectively.