Folo: Latency and Quality Optimized Task Allocation in Vehicular Fog Computing

Abstract

With the emerging vehicular applications such as real-time situational awareness and cooperative lane change, there exist huge demands for sufficient computing resources at the edge to conduct time-critical and data-intensive tasks. This paper proposes Folo, a novel solution for latency and quality optimized task allocation in Vehicular Fog Computing (VFC). Folo is designed to support the mobility of vehicles, including vehicles that generate tasks and the others that serve as fog nodes. Considering constraints on service latency, quality loss, and fog capacity, the process of task allocation across stationary and mobile fog nodes is formulated into a joint optimization problem. This task allocation in VFC is known as a non-deterministic polynomial-time hard (NP-hard) problem. In this paper, we present the task allocation to fog nodes as a bi-objective minimization problem, where a trade-off is maintained between the service latency and quality loss. Specifically, we propose an event-triggered dynamic task allocation (DTA) framework using Linear Programming based Optimization (LBO) and Binary Particle Swarm Optimization (BPSO). To assess the effectiveness of Folo, we simulated the mobility of fog nodes at different times of a day based on real-world taxi traces and implemented two representative tasks, including video streaming and real-time object recognition. Simulation results show that the task allocation provided by Folo can be adjusted according to actual requirements of the service latency and quality, and achieves higher performance compared with naive and random fog node selection. To be more specific, Folo shortens the average service latency by up to 27% while reducing the quality loss by up to 56%.

Enhancing the User Experience in Vehicular Edge Computing Networks: An Adaptive Resource Allocation Approach

“…To trade the quality of computation tasks result for reducing response time and saving extra energy, Li et al [21] applied the scalable computing in a heterogeneous edge computing environment and selected separate Quality-of-Result level for each edge node. An event-triggered dynamic task allocation framework was designed in [22] that studied the trade-off between the service latency and computing quality loss. Moreover, Gao et al [23] investigated the optimal tradeoff between user experience and resources consumption in designing the MEC systems.…”

“…The resource requirements vary with different applications. An application can be decomposed into a set of tasks, and each task is considered to be the basic unit for service scheduling [22]. For example, AR-based driving assistance consists of tasks such as object recognition and video streaming.…”

Chameleon: Latency and Resolution Aware Task Offloading for Visual-Based Assisted Driving

“…According to the responding messages, the client vehicle can choose one fog node for offloading. In this paper, we just adopt a simple fog node selection scheme, in which the client vehicle would select the fog node with the shortest communication distance for task offloading [6], [18].…”

CrowdParking: Crowdsourcing Based Parking Navigation in Autonomous Driving Era

“…On the other hand, offloading these tasks to the cloud is not applicable, due to the remarkable transmission delay. Thus, the concept of vehicular fog computing has been proposed and widely explored by plenty of works [18], [19], [20], [21], [22]. Xiao et al [19] proposed to turn commercial fleets into fog nodes to serve neighboring vehicles and passengers, while Hou et al [18] suggested utilizing the extra computing power on slow moving or parked vehicles.…”

“…Furthermore, Zhu et at. [21], [22] designed a system for latency and performance balanced task offloading for video transmission and processing in vehicular networking.…”