Abstract
The promise of low latency connectivity and efficient bandwidth utilization has driven the recent shift from vehicular cloud computing (VCC) towards vehicular edge computing (VEC). This paper presents an advanced deep learning-based computational offloading algorithm for multilevel vehicular edge-cloud computing networks. To conserve energy and guarantee the efficient utilization of shared resources among multiple vehicles, an integration model of computational offloading, and resource allocation is formulated as a binary optimization problem to minimize the total cost of the entire system in terms of time and energy. However, this problem is considered NP-hard and it is computationally prohibitive to solve this type of problem, particularly for large-scale vehicles, due to the curse-of-dimensionality problem. Therefore, an equivalent reinforcement learning form is generated and we propose a distributed deep learning algorithm to find the near-optimal computational offloading decisions in which a set of deep neural networks are used in parallel. Finally, simulation results show that the proposed algorithm can exhibit fast convergence and significantly reduce the overall consumption of an entire system compared to the benchmark solutions.
Highlights
IN recent years, the Internet of Things (IoT) and wireless sensors have become more popular in daily life
We propose a distributed deep Q learning algorithm to approximately minimize the expectation of the total reward, which is presented in Eq(18), in which D parallel deep neural network (DNN) are used to generate the binary computational offloading decision
Each roadside units (RSUs) is connected with a vehicular edge computing (VEC) server that can provide computational capabilities
Summary
IN recent years, the Internet of Things (IoT) and wireless sensors have become more popular in daily life. The limited computational capacity and battery power of vehicles pose a large challenge to meeting these requirements and ensuring the required quality of service (QoS)level [3]. To address the contradiction between the requirements of these applications and the limitations of resource-constrained vehicles, a computational offloading concept has been introduced in which resource-intensive computations are migrated from the vehicles to a resource-rich server for remote execution, and the results are returned [4]–[8]. Vehicular cloud computing (VCC) was initially developed to provide vehicles with flexibility in computing, storage and service capabilities, reducing power consumption and enhancing application performance. High latency is considered the main challenge for VCC, which makes it unsuitable for real-time and delay-sensitive applications [9], [10]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have