Title: Cloud service security evaluation of smart grid using deep belief network

Authors: Liping Chen; Jun Liu; Weitao Ha

Addresses: Computer College, Weinan Normal University, Weinan, 714000, China ' Computer College, Weinan Normal University, Weinan, 714000, China ' Computer College, Weinan Normal University, Weinan, 714000, China

Abstract: In this paper, we analyse key security problems in the scalable platform architecture of cloud service of smart grid. We also establish evaluating process according to the lack of evaluation mechanism. They evaluate security risks in 5 respects which are policy and organisational risks, general technical risks, SaaS risks, PaaS risks and IaaS risks. The evaluation model based on deep belief network (DBN) is proposed which is composed of multiple RBMs and a BP neural network. The RBMs are trained by greedy training algorithm, and then BP algorithm is used to fine-tuning. After case verification, it is found that the various errors (including mean absolute error (MAE), mean relative error (MRE), mean square error (MSE), maximum error and minimum error) of DBN model are the smallest compared BP and AE model. It avoids the problem that multilayer neural network is trapped in the local optimum.

Keywords: smart grid; cloud service security; scalable platform architecture; evaluating process; evaluating index system; evaluation model; DBN deep belief network; RBM; restricted Boltzmann machines; BP neural network; fine tuning.

DOI: 10.1504/IJSNET.2020.107875

International Journal of Sensor Networks, 2020 Vol.33 No.2, pp.109 - 121

Received: 19 Nov 2019
Accepted: 19 Nov 2019

Published online: 20 Jun 2020 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article