MODELS AND METHODS OF ARTIFICIAL INTELLIGENCE FOR DATA PROCESSING IN COMPUTER NETWORKS

Abstract

The article discusses modern models and methods of artificial intelligence for effective data processing in computer networks. It analyzes the main approaches to the application of machine learning, deep learning, and neural networks for optimizing network traffic, detecting anomalies, and improving the security of network systems. It investigates algorithms for classifying network traffic, methods for predicting load, and AI-based intrusion detection systems. The goal of this work is to develop and study smart ways to handle data in computer networks that are scalable, adaptable, and energy efficient. To do this, we plan to create traffic classification models, load balancing algorithms, and cyber threat detection systems based on machine learning and deep learning technologies. Results: The paper proposes a hybrid model for network traffic classification, an adaptive load balancing algorithm based on reinforcement learning, and a real-time cyber threat detection system. Experimental studies have confirmed the effectiveness of the methods: classification accuracy exceeds 94%, and network performance has increased by more than 20%. Conclusions: The use of machine learning and deep learning methods significantly improves the efficiency of computer network management. The results obtained are of practical importance for building scalable, energyefficient, and secure next-generation network systems.