Cloud-assisted control of ground vehicles using adaptive computation offloading techniques

Adiththan, Arun; Ramesh, S; Samii, Soheil

doi:10.23919/date.2018.8342076

Cited by 10 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, computation offloading has been employed to extend a single vehicle's computing capacity. The computation offloading methods, based on traditional cloud computing platforms [9], offload computing tasks to cloud computing centers with powerful computing capabilities, effectively alleviating the computing burden on vehicles. However, due to the long transmission distance between vehicles and cloud computing centers, it will not only cause serious service delays, but also lead to huge energy consumption, which can not meet the needs of in-vehicle intelligent applications [10].…”

Section: Introductionmentioning

confidence: 99%

Computation offloading strategy based on deep reinforcement learning for connected and autonomous vehicle in vehicular edge computing

Lin

et al. 2021

J Cloud Comp

View full text Add to dashboard Cite

Connected and Automated Vehicle (CAV) is a transformative technology that has great potential to improve urban traffic and driving safety. Electric Vehicle (EV) is becoming the key subject of next-generation CAVs by virtue of its advantages in energy saving. Due to the limited endurance and computing capacity of EVs, it is challenging to meet the surging demand for computing-intensive and delay-sensitive in-vehicle intelligent applications. Therefore, computation offloading has been employed to extend a single vehicle’s computing capacity. Although various offloading strategies have been proposed to achieve good computing performace in the Vehicular Edge Computing (VEC) environment, it remains challenging to jointly optimize the offloading failure rate and the total energy consumption of the offloading process. To address this challenge, in this paper, we establish a computation offloading model based on Markov Decision Process (MDP), taking into consideration task dependencies, vehicle mobility, and different computing resources for task offloading. We then design a computation offloading strategy based on deep reinforcement learning, and leverage the Deep Q-Network based on Simulated Annealing (SA-DQN) algorithm to optimize the joint objectives. Experimental results show that the proposed strategy effectively reduces the offloading failure rate and the total energy consumption for application offloading.

show abstract

Section: Introductionmentioning

confidence: 99%

Computation offloading strategy based on deep reinforcement learning for connected and autonomous vehicle in vehicular edge computing

Lin

et al. 2021

J Cloud Comp

View full text Add to dashboard Cite

show abstract

“…Modern high-end vehicles are equipped with up to 100 embedded Electronic Control Units (ECUs), each executing standard services with pre-defined inputs [1,2]. Advanced driver-assistant systems (ADAS) and multimedia applications are some examples of services that are realized by running complex algorithms on embedded ECUs [3]. However, those pre-specified functions cannot be enhanced throughout the traditional vehicle architecture, since it is very expensive to develop new services on the current static vehicle architecture [4].…”

Section: Introductionmentioning

confidence: 99%

Environmental-Based Speed Recommendation for Future Smart Cars

et al. 2019

View full text Add to dashboard Cite

Modern vehicles are enhanced with increased computation, communication and sensing capabilities, providing a variety of new features that pave the way for the deployment of more sophisticated services. Specifically, smart cars employ hundreds of sensors and electronic systems in order to obtain situational and environmental information. This rapid growth of on-vehicle multi-sensor inputs along with off-vehicle data streams introduce the smart car era. Thus, systematic techniques for combining information provided by on- and off-vehicle car connectivity are of remarkable importance for the availability and robustness of the overall system. This paper presents a new method to employ service oriented agents that cohesively align on- and off-vehicle information in order to estimate the current status of the car. In particular, this work combines, integrates, and evaluates multiple information sources targeting future smart cars. Specifically, the proposed methodology leverages weather-based, on-route, and on-vehicle information. As a use case, the presented work informs the driver about the recommended speed that the car should adapt to, based on the current status of the car. It also validates the proposed speed with real-time vehicular measurements.

show abstract

Reinforcement Learning-Based Computation Offloading Approach in VEC

Lin

Shao

2022

Computer Supported Cooperative Work and Social Computing

View full text Add to dashboard Cite

Cloud-assisted control of ground vehicles using adaptive computation offloading techniques

Cited by 10 publications

References 6 publications

Computation offloading strategy based on deep reinforcement learning for connected and autonomous vehicle in vehicular edge computing

Computation offloading strategy based on deep reinforcement learning for connected and autonomous vehicle in vehicular edge computing

Environmental-Based Speed Recommendation for Future Smart Cars

Reinforcement Learning-Based Computation Offloading Approach in VEC

Contact Info

Product

Resources

About