Federated Learning With Blockchain for Autonomous Vehicles: Analysis and Design Challenges

Pokhrel, Shiva Raj; Choi, Jinho

doi:10.1109/tcomm.2020.2990686

Cited by 374 publications

(203 citation statements)

References 25 publications

Supporting

Mentioning

203

Contrasting

Order By: Relevance

“…Most studies use RSUs, cloud servers, or edge servers as miners. A small number of studies discuss the use of vehicles as miners [ 66 , 68 , 70 , 74 , 76 , 83 , 86 , 90 ]. The current studies basically assume that the vehicles are connected to the blockchain network through the RSUs.…”

Section: Discussionmentioning

confidence: 99%

“…Pokhrel and Choi [ 74 ] proposed a blockchain-based approach to enable FL in a decentralized vehicular environment. The local models and different versions of the global models are maintained by the distributed ledger of blockchain, which is visible and verifiable by every vehicle.…”

Section: Blockchain and The Vehicular Internet Of Thingsmentioning

confidence: 99%

“…A reward is given to a miner based on the size of local models aggregated from multiple clients, incentivizing clients to verify the blocks. By using the blockchain technology, Reference [ 74 ] is able to perform decentralized FL in vehicular environments. The effect of the block arrival rate on the performance of system is also discussed by simulation and numerical analysis.…”

Section: Blockchain and The Vehicular Internet Of Thingsmentioning

confidence: 99%

See 2 more Smart Citations

Blockchain for Vehicular Internet of Things: Recent Advances and Open Issues

Peng

Gao

et al. 2020

Sensors

View full text Add to dashboard Cite

The vehicular Internet of Things (IoT) comprises enabling technologies for a large number of important applications including collaborative autonomous driving and advanced transportation systems. Due to the mobility of vehicles, strict application requirements, and limited communication resources, the conventional centralized control fails to provide sufficient quality of service for connected vehicles, so a decentralized approach is required in the vicinity to satisfy the requirements of delay-sensitive and mission-critical applications. A decentralized system is also more resistant to the single point of failure problem and malicious attacks. Blockchain technology has been attracting great interest due to its capability of achieving a decentralized, transparent, and tamper-resistant system. There are many studies focusing on the use of blockchain in managing data and transactions in vehicular environments. However, the application of blockchain in vehicular environments also faces some technical challenges. In this paper, we first explain the fundamentals of blockchain and vehicular IoT. Then, we conduct a literature review on the existing research efforts of the blockchain for vehicular IoT by discussing the research problems and technical issues. After that, we point out some future research issues considering the characteristics of both blockchain and vehicular IoT.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Blockchain and The Vehicular Internet Of Thingsmentioning

confidence: 99%

Section: Blockchain and The Vehicular Internet Of Thingsmentioning

confidence: 99%

See 1 more Smart Citation

Blockchain for Vehicular Internet of Things: Recent Advances and Open Issues

Peng

Gao

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…Perhaps federated learning algorithm proposed by Google, GFL [3], recently is the most successful case of distributed deep learning, which is focused on dealing with asymmetric and primarily distributed mobile environment datasets [4][5][6]. From a drone-assisted 6G perspective, the goal of federated learning is to train a common global model by simultaneously training the local models using local data privately at the drones [7].…”

Section: Federated Learning With Blockchainmentioning

confidence: 99%

“…To sum up, federated learning has the ability to incorporate the advantages of distributed computation. In order to overcome the above limitations of GFL approach (and to understand its pros), we propose a novel approach by combining blockchain with federated learning [3]. In specific, our approach replaces a centralised global federated learning platform with a blockchain mechanism and introduces a blockchained federated learning (BFL) [3] solution where the network structure allows local vehicle model updates to be shared while delivering and checking their corresponding updates.…”

Section: Federated Learning With Blockchainmentioning

confidence: 99%

Federated learning meets blockchain at 6G edge

Pokhrel

2020

Proceedings of the 2nd ACM MobiCom Workshop on Drone Assisted Wireless Communications for 5G and Beyond

Self Cite

View full text Add to dashboard Cite

We consider a new blockchain empowered federated learning approach which uses wireless mobile miners at drones in the future sixth generation (6G) networks for a disaster response system. Our focus is on the blockchain latency, and energy consumption in the proposed architecture of the network of drones. Maintaining low delay in wireless communication between the drones is required to minimize blockchain forking events while performing blockchain operations. Therefore, we quantify the probability of occurrence of forking events to analyze the uncertainty of the system towards the additional energy wastage. The forked block (due to channel impairments or mobility) incurs re-computation energy. We develop pragmatic analyses of the expected energy consumption by considering the parameters like the number of miners as well as the power consumed during computing, block transfer and 6G channel dynamics for the system. CCS CONCEPTS • Networks → Network performance analysis; • Computing methodologies → Distributed computing methodologies.

show abstract