Multiagent Deep Reinforcement Learning for Vehicular Computation Offloading in IoT

Zhu, Xiaoyu; Luo, Yueyi; Liu, Anfeng; Bhuiyan, Zakirul Alam; Zhang, Shaobo

doi:10.1109/jiot.2020.3040768

Cited by 110 publications

(29 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because in a monitoring network, the battery of most sensor nodes cannot be charged, when the first node dies, the network may not be able to cover the entire monitoring area, or if the critical node is dead, the data cannot be transmitted to the sink. The key to prolong lifetime is to reduce the energy consumption of code dissemination [8], [41], [42], [48], [51], [54]. The reduction of energy consumption can be reduced by the number of times the code is sent.…”

Section: ) Lifeitmementioning

confidence: 99%

“…The code sending times directly reflect the energy consumption. Therefore, the less sending times, the less energy consumption [8], [41], [42].…”

Section: ) Code Sending Timesmentioning

confidence: 99%

“…The development of Internet of Thing (IoT) has brought about tremendous changes in the network [1]- [3]. In the past research, the code update of WSNs is often concentrated [8], [41], [42], [48], [51], [54]. But with the development of IoT, due to a huge number of IoT devices are deployed in a wide range of application fields, and their data acquisition and code diffusion methods have also undergone tremendous changes, which can be seen from Figure 1.…”

Section: B Code Dissemination In Iotmentioning

confidence: 99%

“…There are many studies on code update of IoT devices [8], [41], [42], [48], [51], [54]. Zhao et al proposed an Update Code using Vehicles joint UAVs (UC-VU) scheme [48].…”

Section: B Code Dissemination In Iotmentioning

confidence: 99%

“…Most of these IoT devices are equipped with sensing devices that can sense the physical phenomena of surrounding environment, so that the system can deal with events accordingly [5]- [7]. Currently, these IoT devices are deployed in many application fields, such as transportation [8], [9], medical and health [10], [11], environmental monitoring [12], [13], industrial production, etc. [14]- [16].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Fast Multicast With Adjusting Transmission Power and Active Slots in Software Define IoT

Liu

Zhang

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

Section: ) Lifeitmementioning

confidence: 99%

“…The code sending times directly reflect the energy consumption. Therefore, the less sending times, the less energy consumption [8], [41], [42].…”

Section: ) Code Sending Timesmentioning

confidence: 99%

Section: B Code Dissemination In Iotmentioning

confidence: 99%

“…There are many studies on code update of IoT devices [8], [41], [42], [48], [51], [54]. Zhao et al proposed an Update Code using Vehicles joint UAVs (UC-VU) scheme [48].…”

Section: B Code Dissemination In Iotmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Fast Multicast With Adjusting Transmission Power and Active Slots in Software Define IoT

Liu

Zhang

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

Efficient task offloading with swarm intelligence evolution for edge‐cloud collaboration in vehicular edge computing

Wang

Chen

2022

Softw Pract Exp

View full text Add to dashboard Cite

In vehicular edge computing, both edge and cloud can provide computing services (i.e., tasks). The edge can reduce vehicular task delay by processing data nearby, but is resource‐constrained and cannot handle too many tasks simultaneously. The resource‐rich cloud can handle massive tasks, but is far from users and has low quality of service and energy efficiency. Currently, some work has been done on task offloading for edge‐cloud collaboration. However, either the collaboration among multiple devices is not considered and the load is easily imbalanced; or edge‐cloud collaboration is required for offloading decisions with too many parameters, affecting tasks to be processed efficiently. To address these issues, we learn from the swarm intelligence evolution of sparrow foraging, improve a sparrow search algorithm by integrating three strategies of flyer refine producer update, sin/cos perturbation follower update, and adaptive adjustment agitator update, to optimize the vehicular task offloading location for edge‐cloud collaboration. Furthermore, we combine delay relaxation variables and delay‐energy penalty operator to design a lightweight heuristic task offloading algorithm, and greedily compare the task preoffload location sets with different delay constraints based on the improved sparrow search algorithm, to obtain the optimal task offloading with integrated delay and energy. Simulation experiments verify that our approach can improve the algorithm's optimization accuracy, convergence speed, and robustness. Moreover, the average task delay, total task energy consumption, and load balance degree of our approach outperform the five benchmark algorithms, and can comprehensively optimize task delay and energy consumption, and achieve edge devices load balancing.

show abstract

A trustworthy data collection approach from sensor nodes using trust score of mobile vehicles for smart city

Kumar,

Tyagi,

Agarwal

et al. 2024

Security and Privacy

View full text Add to dashboard Cite

In smart cities, a substantial amount of data is collected for analytics and a better life for the citizens. The schemes based on data collection through mobile vehicles (MV) and further verification of that data through unmanned aerial vehicles (UAV) are popular. Many trust‐based schemes of the MV have been proposed recently. However, these schemes suffered from recognition accuracy, judgment trust, and collusion attack problems. In this paper, we propose a Gompetz function‐based trust evaluation scheme. In this scheme, the direct trust of the MV is computed by comparing the data provided by the MV and the same reported by the UAV. Since the UAV can collect only limited data, indirect trust of the vehicle is computed by comparing the data reported by the MV and the same reported by the MV having the highest trust. We also applied the variable trust, which considers the recent Trust of the MVs. Then, combining all these trusts with significant weight, the final trust score of the MV is computed. After experimenting, our proposed scheme is more credible and removes the shortcomings of the existing methods by providing better recognition, accuracy, judgment, and trust.

show abstract

Multiagent Deep Reinforcement Learning for Vehicular Computation Offloading in IoT

Cited by 110 publications

References 37 publications

Fast Multicast With Adjusting Transmission Power and Active Slots in Software Define IoT

Fast Multicast With Adjusting Transmission Power and Active Slots in Software Define IoT

Efficient task offloading with swarm intelligence evolution for edge‐cloud collaboration in vehicular edge computing

A trustworthy data collection approach from sensor nodes using trust score of mobile vehicles for smart city

Contact Info

Product

Resources

About