Connected vehicles (CVs) face significant challenges in continuous big data transmission, resulting in high transmission bandwidth costs and impacting real-time decision-making. To address this, we propose two dynamic, driving-aware compression mechanisms based on reinforcement learning and temporal compressive sensing to intelligently compress video data. These mechanisms adapt to driving conditions, reducing bandwidth while preserving sufficient information for accurate applications such as object detection and ensuring high-quality reconstruction when needed. We also implement a Vehicle-EdgeServer-Cloud (VEC) closed-loop framework that integrates these mechanisms. Specifically, a lightweight vehicle model performs real-time detection on compressed data (measurements), while the EdgeServer receives measurements and reconstructs scenes if needed. The measurements, reconstructed video, and analysis results are then sent to the cloud for vehicle model updates. Unlike conventional methods, our framework seamlessly adapts across vehicles, Edge-Servers, and the cloud, supporting efficient data transmission and dynamic model updates. Extensive evaluations were conducted on our designed roadside unit platform and robotic vehicle, both equipped with industry-grade sensors and computing units. The results demonstrate an 18x reduction in bandwidth at 320KB/s while maintaining high detection accuracy and reconstruction quality compared to non-adaptive measurements, highlighting the framework's promising real-world applications for CVs.

This paper focuses on addressing computational constraints and energy limitations prevalent in edge-based applications through an innovative approach, dynamic in-situ control for edge-based applications (DICE). DICE capitalizes on the burgeoning trend in vehicle sensor technologies, such as camera, Radar, and LiDAR, which are becoming increasingly powerful and capable of performing pre-processing computations. DICE introduces a concept of "downstream offloading", which distinguishes it from traditional offloading approaches that typically offload computational tasks from edge devices to more powerful Edge Servers. In contrast, DICE offloads part of the computational tasks from the Edge Server to the sensor itself, thereby optimizing data processing at the source and reducing the volume of data transmission required. This approach not only addresses the latency bottleneck frequently encountered in energy- intensive neural networks but also enhances the efficiency of data processing by selectively filtering out non-critical frames based on event-triggering mechanisms. DICE leverages the unique strengths of portable devices such as smartwatches and smartphones, even with their inherent computational and power limitations. The framework consists of an adaptive control layer for dynamic task allocation and an application layer designed to deploy quantized models on System on Chips (SoCs) like TinyML, thereby improving the efficiency of AI-driven applications while conservatively utilizing energy. This system proposes a sustainable, energy-efficient pathway for future edgebased applications.

The highly mobility nature of connected vehicles poses significant challenges in the research area of federated learning, and to the best of our knowledge, the existing federated learning approaches do not consider the problem of training multi-model for constantly on-the-wheel moving vehicles. To bridge this gap, we design and implement FLOW, a scalable multi-model federated learning framework for highly mobile connected vehicles, which includes three essential components: (1) a dynamic client vehicle selection algorithm to deal with problems such as signal loss or weak signals, which may prevent some vehicles from participating in the training cluster; (2) a well-designed model allocation algorithm to select appropriate vehicle computing units for specific model training tasks; (3) geofencing not independent and identically distributed (non-i.i.d) data training, which can make models more robust and generalizable to different geographic driving area. Finally, we compare the proposed framework with centralized training and explore the performance of four aggregation protocols. The experiment results demonstrated the effectiveness of FLOW for the real-world applications.

The dramatic development of Edge Computing technologies is strongly stimulating the adoption of machine learning models on connected and autonomous vehicles (CAVs) so that they can provide a variety of intelligent onboard services. When multiple services running on the resource-constrained CAVs, how limited resources can dynamically support the desired services is of the utmost importance for both automakers and domain researchers. In this context, efficiently and dynamically managing vehicle services becomes critical for autonomous driving. While previous research focused on service scheduling, computation offloading, and virtual machine migration, we propose EdgeWare, an extensible and flexible middleware to manage the execution of vehicle services, which is open-source to the community with four key features: i) on-demand model switch, i.e., easily switch and upgrade machine learning models, ii) function consolidation and deduplication to eliminate duplicate copies of repeating functions and maximize the reusability of vehicle services, iii) build event-driven applications to reduce workload, and iv) dynamic workflow customization which enables customizing workflow to extend the functionality. Our experiment results show that EdgeWare accelerates the execution of services about 2.6 $$\times$$ faster compared to the silo approach and save CPU and memory utilization up to around 50% and 17% respectively, and it allows domain researchers to dynamically add new services on CAVs or easily switch to the upgraded applications for the life cycle management of vehicle services.

In this paper, we propose an Android-based distributed computing framework for accelerating DNN inference on Android edge devices. We experimentally demonstrate that the proposed distributed framework can reduce CPU utilization by 24 % (making the the CPU utilization close to that of idle status), reduce power consumption by 59.8 % to 71.8 %, without leading to high-bandwidth througput. The proposed framework can be applied to various Android devices to enable cooperation among edge devices in a distributed computing manner, accelerate DNN inference, and enrich the functionality of Android devices to enhance user experience.

The motivation of this work is to build a multimodal-based COVID-19 pandemic forecasting platform for a large-scale academic institution to minimize the impact of COVID-19 after resuming academic activities. The design of this multimodality work is steered by video, audio, and tweets. Before conducting COVID-19 prediction, we first trained diverse models, including traditional machine learning models (e.g., Naive Bayes, support vector machine, and TF-IDF) and deep learning models [e.g., long short-term memory (LSTM), MobileNetV2, and SSD], to extract meaningful information from video, audio, and tweets by 1) detecting and counting face masks, 2) detecting and counting cough for potential infected cases, and 3) conducting sentiment analysis based on COVID-19-related tweets. Finally, we fed the multimodal analysis results together with daily confirmed cases data and social distancing metrics into the LSTM model to predict the daily increase rate of confirmed cases for the next week. Important observations with supporting evidence are presented.

The recent proliferation of computing technologies (e.g., sensors, computer vision, machine learning, and hardware acceleration) and the broad deployment of communication mechanisms (e.g., dedicated short-range communication, cellular vehicle-to-everything, 5G) have pushed the horizon of autonomous driving, which automates the decision and control of vehicles by leveraging the perception results based on multiple sensors. The key to the success of these autonomous systems is making a reliable decision in real-time fashion. However, accidents and fatalities caused by early deployed autonomous vehicles arise from time to time. The real traffic environment is too complicated for current autonomous driving computing systems to understand and handle. In this article, we present state-of-the-art computing systems for autonomous driving, including seven performance metrics and nine key technologies, followed by 12 challenges to realize autonomous driving. We hope this article will gain attention from both the computing and automotive communities and inspire more research in this direction.

The COVID-19 pandemic brought unprecedented levels of disruption to the local and regional transportation networks throughout the United States, especially the Motor City: Detroit. That was mainly a result of swift restrictive measures such as statewide quarantine and lock-down orders to confine the spread of the virus. This work is driven by analyzing five types of real-world data sets from Detroit related to traffic volume, daily cases, weather, social distancing index, and crashes from January 2019 to June 2020. The primary goal is figuring out the impacts of COVID-19 on the transportation network usage (traffic volume) and safety (crashes) for the Detroit, exploring the potential correlation between these diverse data features, and determining whether each type of data (e.g., traffic volume data) could be a useful factor in the confirmed-cases prediction. In addition, a deep learning model was developed using long short-term memory networks to predict the number of confirmed cases within the next one week. The model demonstrated a promising prediction result with a coefficient of determination (R^2) of up to approximately 0.91. Moreover, in order to provide statistical evaluation measures of confirmed-case prediction and to quantify the prediction effectiveness of each type of data, the prediction results of six feature groups are presented and analyzed. Furthermore, six essential observations with supporting evidence and analyses are presented. The goal of this paper is to present a proposed approach which can be applied, customised, adjusted, and replicated for analysis of the impact of COVID-19 on a transportation network and prediction of the anticipated COVID-19 cases using a similar data set obtained for other large cities in the USA or from around the world.

The proliferation of edge computing technologies has boosted the development of new applications for a plethora of edge devices. However, many applications face privacy issues and bandwidth limitations. To solve these limitations, we propose a collaborative learning framework on the edges, named CLONE, which is steered by the real-world data sets collected from a large electric vehicle (EV) company and a grocery store of a shopping mall, respectively. We categorize two application scenarios for CLONE, i.e., CLONE in the training stage (CLONE_training) and CLONE in the inference stage (CLONE_inference). As to CLONE_training, we choose the failure prediction of EV battery and associated components as the first use case. While as for CLONE_inference, customer tracking in a grocery store is selected as another case study. In this work, the goal of the CLONE is to support real-time training and inference for connected vehicles and marketing intelligence services. Our experimental results on the EV data show that CLONE is able to reduce model training time without sacrificing algorithm performance. Furthermore, the experimental results on the video data from the grocery store reveal that CLONE is a useful approach to solve the multitarget multicamera tracking problem in a collaborative fashion.

Disk drives are one of the most commonly replaced hardware components and continue to pose challenges for accurate failure prediction. In this work, we present analysis and findings from one of the largest disk failure prediction studies covering a total of 380,000 hard drives over a period of two months across 64 sites of a large leading data center operator. Our proposed machine learning based models predict disk failures with 0.95 F-measure and 0.95 Matthews correlation coefficient (MCC) for 10-days prediction horizon on average.

The great success of artificial intelligence and edge computing technology has largely promote the development of connected and autonomous driving. However, owing to the missing of the experiment platform for Road-Side Unit (RSU), majority of research works are either simulation based task offloading or commercial equipment's based scheduling design. The fundamental challenge of how to co-design the communication and computation in a practical system is not tackled.In this paper, we proposed Equinox, which is our design of the rode-side edge computing experimental platform for connected and autonomous vehicles. With communication, data, as well as the computation taken into consideration, Equinox provides stable and sufficient communication based on a combination of WiFi, LTE, and DSRC. Also, Equinox guarantees reliable and flexible data collection, data storage, and efficient data processing.

Voltage, temperature, and state of charge (SOC) are the main characterizing parameters for various battery faults that can cause these parameters' abnormal fluctuations. Accurate prediction for these parameters is critical for the safe, durable, and reliable operation of battery systems in electric vehicles. This paper investigates a new deep-learning-enabled method to perform accurate synchronous multi-parameter prediction for battery systems using a long short-term memory (LSTM) recurrent neural network. A year-long dataset of an electric taxi was retrieved at the Service and Management Center for electric vehicles (SMC-EV) in Beijing to train the LSTM model and verify the model's validity and stability. By taking into account the impacts of weather and driver's behaviors on a battery system's performance to improve the prediction accuracy, a Weather-Vehicle-Driver analysis method is proposed, and a developed pre-dropout technique is introduced to prevent LSTM from overfitting. Besides, the many-to-many(m-n) model structure using a developed dual-model-cooperation prediction strategy is applied for offline training the LSTM model after all hyperparameters pre-optimized. Additionally, the stability and robustness of this method have been verified through 10-fold cross-validation and comparative analysis of multiple sets of hyperparameters. The results show that the proposed model has powerful and precise online prediction ability for the three target parameters. This paper also provides feasibility for synchronous multiple fault prognosis based on accurate parameter prediction of the battery system. This is the first of its kind to apply LSTM to the synchronous multi-parameter prediction of the battery system.

State prediction and fault prognosis are generating considerable interest regarding battery system due to the healthy development momentum of electric vehicles. Voltage is one of the main characterisation parameters for various battery faults, so accurate voltage abnormity prognosis is critical to the safe and durable operation of the battery system. A novel deep-learning-enabled method to perform accurate multi-forward-step voltage prediction for battery systems is investigated using long short-term memory(LSTM) recurrent neural network. A high volume of real-world operational data of an electric taxi is acquired from the Service and Management Center for electric vehicles(SMC-EV) in Beijing. To improve the prediction accuracy, a Weather-Vehicle-Driver analysis is implemented to consider the impacts of weather and driver's behaviour on a battery system's performance, and the many-to-one(4-1) model structure using an improved pre-dropout technology and a developed dual-model-cooperation prediction strategy is applied for offline training the LSTM models after all hyperparameters pre-optimized. The results showcase that the proposed method has a powerful prediction ability for battery voltage, and the accuracy and robustness of this method are verified through the comparisons among different hyperparameters and seasons using 10-fold cross-validation. Furthermore, combined with alarm or warning thresholds, the prognosis feasibility, stability, and reliability of the proposed models for various voltage abnormities are also verified through actual operational data, thereby this method can assess the battery safety via predicting voltage to determine the advent of battery faults and mitigate runaway risk. This is the first of its kind to apply the LSTM to voltage prediction and fault prognosis of the battery system.

The wide deployment of 4G/5G has enabled connected vehicles as a perfect edge computing platform for a plethora of new services which are impossible before, such as remote real-time diagnostics and advanced driver assistance. In this work, we propose CLONE, a collaborative learning setting on the edges based on the real-world dataset collected from a large electric vehicle (EV) company. Our approach is built on top of the federated learning algorithm and long shortterm memory networks, and it demonstrates the effectiveness of driver personalization, privacy serving, latency reduction (asynchronous execution), and security protection. We choose the failure of EV battery and associated accessories as our case study to show how the CLONE solution can accurately predict failures to ensure sustainable and reliable driving in a collaborative fashion.