Blockchain and Semi-Distributed Learning-Based Secure and Low-Latency Computation Offloading in Space-Air-Ground-Integrated Power IoT
IEEE Journal on Selected Topics in Signal Processing
Power systems impose stringent security and delay requirements on computation offloading, which cannot be satisfied by existing power Internet of Things (PIoT) networks. In this paper, we tackle this challenge by combining blockchain, space-air-ground integrated PIoT (SAG-PIoT) and machine learning. Low earth orbit (LEO) satellites assist in broadcasting a consensus message to reduce the block creation delay, and unmanned aerial vehicles (UAVs) provide flexible coverage enhancement. Specifically, we propose a Blockchain and semi-distributed leaRning-based secure and low-latency electromAgnetic interferenCe-awarE computation offloading algorithm (BRACE) to minimize the total queuing delay under the long-term security constraint. First, the task offloading is decoupled from the computational resource allocation by Lyapunov optimization. Second, the task offloading problem is solved by the proposed federated deep actor-critic-based electromagnetic interference-aware task offloading algorithm (FDAC-EMI). Finally, the resource allocation problem is solved by smooth approximation and Lagrange optimization. Simulation results verify that BRACE achieves superior delay and security performance. © 2007-2012 IEEE.
Antennas, Blockchain, Electromagnetic pulse, Internet of things, Learning systems, Network security, Orbits, Air grounds, Block-chain, Computation offloading, Computational modelling, Delay, Distributed learning, Electromagnetic interference awareness, Electromagnetics, Integrated power, Interference awareness, Security, Semi-distributed, Semi-distributed learning, Space-air-ground-integrated power IoT, Task analysis, Signal interference
H. Liao, et al., "Blockchain and Semi-Distributed Learning-Based Secure and Low-Latency Computation Offloading in Space-Air-Ground-Integrated Power IoT", IEEE Journal on Selected Topics in Signal Processing, vol 16(3), pp. 381-394, Apr 2022. doi: 10.1109/JSTSP.2021.3135751