Low-time-delay security cloud side-end collaboration method for electric power Internet of Things

Abstract

The invention discloses an electric power Internet of Things low-delay security cloud side-end cooperation method, which comprises the following steps: constructing a system model consisting of PIOT equipment, a ground base station, an unmanned aerial vehicle, an edge server, a cloud server and a satellite; constructing a task unloading model; constructing a task processing model; constructing a queuing time delay model; constructing an alliance block chain model; the total queuing time delay of the PIOT equipment in the SAG-PIOT network under the long-term security constraint is minimized; and long-term constraint and short-term decision optimization are decoupled by using Lyapunov optimization. The method has the advantages that the system cost is reduced, the learning performance of model training is improved, and the allocation of computing resources is optimized; and the anti-EMI capability is improved, EMI perception is realized, and the adverse effect of EMI is reduced.

Description

technical field [0001] The invention relates to the technical field of the Internet of Things, in particular to a low-latency secure cloud-edge-terminal collaboration method for the Internet of Things. Background technique [0002] With the widespread deployment of edge computing in the power Internet of Things (PIoT), a large number of computationally intensive tasks generated by PloTPIoT devices are offloaded to edge servers for calculation. However, the existing PIoT network cannot meet the strict security and latency requirements of the power system for computing offload. On the one hand, the offloaded tasks and calculation results are easy to be tampered with and reversed, seriously endangering the security of the power system. On the other hand, limited communication infrastructure and rigid resource deployment cannot provide flexible and on-demand services. In addition, non-intelligent offloading and resource allocation methods lead to large computing delays and low...

AI Technical Summary

Problems solved by technology

[0004] (1) The trade-off between learning performance and cost: Traditional centralized learning methods have the best performance, but need to master the global state information (GSI) in advance, resulting in huge learning costs

[0005] (2) The trade-off between security and delay performance: the edge server performs task processing and block creation at the same time. When the edge server allocates more computing resources for task processing, the computing resources for block creation may be insufficient, resulting in block Increased block creation delay and reduced security

[0006] (3) Adverse effects of electromagnetic interference (EMI) on learning performance: In SAG-PIoT, strong EMI from transient processes and partial discharges from high-voltage power infrastructure adversely affects learning performance and model convergence

[0008] On the one hand, the above method does not mathematically model and optimize the security of task offloading; on the other hand, the above scheme does not consider the impact of EMI on network performance, and does not have the ability to perceive electromagnetic interference; in addition, the above method is in the model In the improvement of training and learning performance, the observation data of similar environments of nearby PIoT devices are not fully utilized

Images