Deep Learning Empowered Task Offloading for Mobile Edge Computing in Urban Informatics
read more
Citations
Convergence of Edge Computing and Deep Learning: A Comprehensive Survey
Convergence of Edge Computing and Deep Learning: A Comprehensive Survey
Blockchain Empowered Asynchronous Federated Learning for Secure Data Sharing in Internet of Vehicles
Deep Reinforcement Learning for Offloading and Resource Allocation in Vehicle Edge Computing and Networks
Efficient and Privacy-Enhanced Federated Learning for Industrial Artificial Intelligence
References
Playing Atari with Deep Reinforcement Learning
Deep reinforcement learning with double Q-learning
Deep reinforcement learning with double Q-Learning
The Future of Industrial Communication: Automation Networks in the Era of the Internet of Things and Industry 4.0
Vehicular Fog Computing: A Viewpoint of Vehicles as the Infrastructures
Related Papers (5)
Mobile Edge Computing: A Survey on Architecture and Computation Offloading
Human-level control through deep reinforcement learning
Frequently Asked Questions (18)
Q2. What is the effect of higher traffic density on offloading reliability?
As higher traffic density leads to worse vehicular communication performance, more redundant transmission and corresponding communication cost are required to ensure the offloading reliability.
Q3. Why does the scheme get higher utility?
due to the adaptive number of redundant path as well as the cooperation of multiple transmission modes, which help reduce the offloading cost, their scheme still gets higher utility.
Q4. Why does the offloading scheme have a higher utility?
Due to the interference between vehicle communicationpairs, in the scenario with high traffic density, too much redundant transmission may further aggravate the interference, and worsen offloading reliability.
Q5. what is the way to maximize the utility of the offloading system?
In order to maximize the utility of the offloading system, the authors need to obtain an optimal strategy π∗, which consists of offloading actions for various tasks in different time frames.
Q6. Why does fixed number offloading scheme reduce data delivery rate?
The reason is that in high traffic density scenario, fixed number offloading scheme results in significant interference in vehicular communication, which reduces data delivery rate while increasing offloading delay.
Q7. Why do the authors propose an adaptive redundant offloading algorithm?
the authors focus on reliable offloading in presence of task transmission failure, and propose an adaptive redundant offloading algorithm to ensure offloading reliability while improving system utility.
Q8. In what study did the authors unveiled underutilized vehicular computing resources?
In [10], the authors unveiled underutilized vehicular computing resources, and put them into use for providing efficient computational support to MEC servers.
Q9. What is the reason why the greedy algorithm is ignored?
Although the greedy algorithm jointly optimizes file transmission path and MEC server selection in current frame, it ignores the follow-up effects.
Q10. What is the cost of using a unit spectrum of the cellular network and for that belonging?
The costs for using a unit spectrum of the cellular network and for that belonging to the vehicular network in a unit time are cc and cv , respectively.
Q11. What is the effect of the proposed offloading scheme?
It can be seen that adopting their proposed offloading scheme, the proportion of task transmission in V2B mode becomes higher as Pg increases.
Q12. How can the authors determine the time cost for offloading a task?
To choose the offloading target server efficiently, the offloading strategy taken by each task in time frame l depends on the characteristics of current vehicle network as well as the server states in frame l − 1.
Q13. What is the utility of the offloading scheme with fixed number of redundant paths?
It is noteworthy that when ρ is above 0.08, the utility of the scheme with fixed number of redundant paths is lower than that of the offloading scheme without any redundant transmission.
Q14. What is the effect of offloading a large number of generated tasks?
Offloading a large number of generated tasks through vehicular communication may bring serious interference and impair offloading efficiency.
Q15. Why does the offloading scheme have a low utility?
due to the resource constraints of Serv0, this approach can not continuously improve offloading utility when the number of generated tasks is high.
Q16. How many time frames does it take to learn the optimal offloading strategy?
From this figure, the authors see that the learning process takes about 8000 time frames to reach the optimal offloading strategies with different vehicle density ρ.
Q17. What is the simplest way to get the utility of offloading?
The reliable offloading scheme that prevents offloading failure through optimal redundant transmission is illustrated in Algorithm 2.
Q18. What is the average number of tasks generated on vehicles located in one road segment at the same time?
The average number of tasks generated on vehicles located in one road segment at the same time frame will beN̄task = ∞∑ k=1 Pgk(ρe) k exp(−ρe)/k!. (28)According to their proposed deep Q-learning based task offloading scheme, the tasks of the same type and generated in the vehicles at the same road segment are offloaded in an identical approach.