Vulnerability Analysis And Risk Assessment Of Cyber Security In Electric Power SCADA

Electric power SCADA system is a key secondary system. The two main functions of electric power SCADA is supervisory control and data acquisition. It collects the operation parameters through the sensors and monitors the operational status of the entire grid. If the power grid is running abnormally, electric power SCADA system makes it normal operation by adjusting running parameters of the power grid. SCADA system has played an extremely important role in maintaining the normal operation of the power system. The communication network of traditional SCADA system is separated and private. However, it will transmit information with public Internet with rapid development of network. The common internet protocols are used, which seriously increases the cyber risk in electric power SCADA. Network security of electric power SCADA system has become an urgent problem to solve.As the SCADA system itself has certain vulnerability, attackers can exploit it to attack the system. So firstly analyze the vulnerability and construct index system of cyber security risk to reflect vulnerability. Then, the reduce the indexes. Finally, construct the risk assessment model. The specific work is as follows:1. Firstly study the running mechanism of electric power SCADA system and analyze the vulnerability existed in the system. The index system of network security risk assessment is built with Delphi method and AHP (Analytic Hierarchy Process), in order to fully represent the vulnerability of electric power SCADA system.2. As index data of network security risk assessment in electric power SCADA is characterized by strong relation and high dimensionality, the method of Autoencoder is proposed to reduce dimensionality of index data by representing high-dimensional data in a low dimensional space. Conducts simulation experiments about reconstruction error in pre-training and fine-tuning process in MATLAB experimental platform, and the experimental results show that dimensional code received by reducing dimensionality of data can basically fully represent high-dimensional data.3. The hybrid algorithm of ABC (Artificial Bee Colony) optimizing GP (Gaussian Process) is proposed to construct evaluation model to automatically assess cyber security risk of electric power SCADA. The validity and applicability of the proposed method is demonstrated by simulation experiment in Matlab environment.