KEYWORDS: Cloud computing, Computing systems, Computer security, Network security, Power grids, Data storage, Information security, Data processing, Clouds, Defense and security
With the increasing number of power grid information systems and the deepening requirements for information intensification, the concept of cloud computing has entered the sight of power grid enterprises. This paper discusses the application of cloud computing in power grid enterprises from the aspects of the concept, service level and core technology of cloud computing. This paper holds that the introduction of cloud computing into power network and the construction of power network security immune system cloud can provide effective support for the development of power network. Based on the characteristics of power network and relying on a new storage and calculation mode of cloud computing technology, this paper expounds how cloud computing technology provides technical support for data storage and analysis of power network, and analyzes the benefits brought by cloud computing technology to power network. The possible security threats of power network cloud and the corresponding preventive measures are discussed.
In order to improve the accuracy and convergence speed of power communication network security situation prediction, we introduced an optimization method called Particle Swarm Optimization (PSO) algorithm. This study applied the PSO algorithm to predict the security situation of power communication networks and achieved significant results. Firstly, we adopted the PSO computing framework, which has the characteristics of memory computing and quasi real-time processing, making it very suitable for the needs of big data processing in power communication. This framework can efficiently process large-scale data, enabling prediction algorithms to complete calculations in a relatively short time. Secondly, we propose a PSO optimization algorithm to correct the weights of the neural network. Through the iterative process of the PSO algorithm, we can find better weight combinations, thereby improving the learning efficiency and accuracy of the neural network. In order to further improve computational efficiency, we also propose a parallel PSO optimized neural network algorithm, which enables computation to be carried out simultaneously on multiple processing units, accelerating the entire prediction process. Finally, through experimental comparison, we conclude that the prediction method based on PSO optimization algorithm has higher accuracy. Compared with traditional Hadoop based prediction methods, there is also a significant improvement in processing speed. This means that we can quickly obtain accurate predictions of the security situation of the power communication network, providing better support for the management and decision-making of the power communication system.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.