Main stages of data center service performance prediction were discussed, specifically data monitoring and gathering, calculation and prediction of key indexes and performance index prediction. It was proposed to build data center service performance prediction algorithm based on an analysis of the service transactions index, service resource occupancy index and service performance index. Prediction of the indexes is based on chaotic time series analysis that was used to estimate service transactions index time series trend, the radar chart method to calculate the service resource occupancy index value and weighted average method to calculate service performance index. For performance prediction, it is proposed to use a fuzzy judgment matrix with the service transactions index and service resource occupancy index as input values. It was taken into consideration that service transactions index is usually represented by nonlinear time series and thus the index time series parameters had to be predicted by chaos theory and for the calculation of this index, the estimation procedure of Lyapunov exponent value can be used. The radar chart demonstrates service resource occupancy index estimation of shared storage, mobile storage, memory, computational capability and network bandwidth. The prediction technique was based on the fuzzy nearness category that use input values of transactions index and dynamic changes of the service resource occupancy index.

Data Center cyberprotection methods based on host-based intrusion prevention systems and network based intrusion prevention systems were considered. Basic algorithm of intrusion prevention system functioning and operational readiness evaluation which includes objects of analysis, procedures and evaluation indicators was discussed. It was shown that procedures to be done by Data Center cyber-protection system are identification of the event, signatures database management and denial management. Evaluation of intrusion prevention system efficiency was proved to be based on errors' numbers and scalability. Thereby it should include accuracy, robustness, performance and scalability parameters. Main prevention systems which show model of detection systems interaction with monitored environment events were discussed. Specifically detection strategy based classification which includes cyberattack signatures analysis, anomalies analysis, hybrid strategy, detection system behavior based classification which includes active behavior, passive behavior, monitored environment based classification which includes local network, global network, hybrid environment, detection system architecture based classification which includes centralized architecture, distributed architecture, hierarchical architecture, detection system performance based classification which includes real time analysis, offline analysis were analyzed. It was mentioned that anomaly-based systems development has to be supervised by operators and adapted to the parameters of the Data Center network. They were divided to three groups: statistical modeling, knowledge based modeling and modeling based on machine learning techniques. It was mentioned that cyber-threats could be modeled as process of transmission of data in hidden channel that change state of some functional node of Data Center. Unified mathematical model of intrusion detection system work which includes states of the infrastructure functional nodes, events involved in a system and transition between the states caused by those events was proposed.