In the modern world, the number of different complex technical systems is only increasing every year, and any system incorporates or uses a third-party communication system. Disruption of the communication system and its elements functioning can lead to a situation where a complex technical system cannot realize its functions. It is required to ensure the guaranteed functioning of the communication system and its elements. One of the ways to ensure the stable operation of complex technical systems is the implementation of the control function by the control system, while in the process of system operation it is necessary to take into account not the characteristics and parameters of individual elements that describe their operation, but the ability of the system to perform tasks and functions. The paper proposes an approach to describing the functioning of a communication system through the formation of the system functioning profile, which is a set of matrices, which is used in the control system.

Keywords: functional stability, criticality, communication system, control system, complex technical system, functions, tasks, profile, regulations

The article describes an approach to the operation of a data transmission network protection system against computer attacks based on a hybrid neural network. It is proposed to use a hybrid neural network as a machine learning method. To calculate the output value of neural network signals, the activation function is used. The neural network model consists of recurrent cells - LSTM and GRU. Experiments have demonstrated that the proposed network protection system for detecting computer attacks based on an assessment of the self-similarity of the system functioning parameters using fractal indicators and predicting the impact of cyber attacks by applying the proposed structure of the LSTM neural network has a sufficiently high efficiency in detecting both known and unknown spacecraft. The probability of detecting known spacecraft is 0.96, and the zero-day attack is 0.8.

Keywords: data transmission network, computer attack, neural network, protection system, network traffic, auto-encoder, accuracy, completeness, detection, classifier, self-similarity, recurrent cells with long short-term memory

When building complex technical systems, as a rule, the resources of an existing system are used as a basis, which may be redundant due to the lack of a clear definition of what the system is needed for. This necessitates the determination of the system intended purpose, the selection of elements for its construction and management in the process of its operation, aimed at achieving the intended purpose and optimizing the resource support used to build the system. The paper proposes an approach to building a system based on the development of its functioning profile, which characterizes the achievement of its intended purpose, modeling the process of a complex technical system functioning and evaluating the effectiveness of the profile. The use of the proposed methodology will allow, at the stage of building a complex system, to improve the quality and efficiency of designing a complex technical system by taking into account the functional needs of the system, as well as determining the amount of resources required to fulfill them.

Keywords: profile, complex technical system, criticality, system design, system construction, control process automation, functions, tasks, resource