From statistical‐ to machine learning‐based network traffic prediction

Abstract

Nowadays, due to the exponential and continuous expansion of new paradigms such as Internet of Things (IoT), Internet of Vehicles (IoV) and 6G, the world is witnessing a tremendous and sharp increase of network traffic. In such large‐scale, heterogeneous, and complex networks, the volume of transferred data, as big data, is considered a challenge causing different networking inefficiencies. To overcome these challenges, various techniques are introduced to monitor the performance of networks, called Network Traffic Monitoring and Analysis (NTMA). Network Traffic Prediction (NTP) is a significant subfield of NTMA which is mainly focused on predicting the future of network load and its behavior. NTP techniques can generally be realized in two ways, that is, statistical‐ and Machine Learning (ML)‐based. In this paper, we provide a study on existing NTP techniques through reviewing, investigating, and classifying the recent relevant works conducted in this field. Additionally, we discuss the challenges and future directions of NTP showing that how ML and statistical techniques can be used to solve challenges of NTP.

Metrologia na Era do Aprendizado de Máquina

“…A predição de tráfego pode resolver diversos problemas de gerenciamento de redes, entre eles o provisionamento de recursos, a detecção de congestionamento e a tolerância a falhas. Apesar do sucesso obtido com a aplicação dos modelos de AM, ainda existem desafios a serem superados como alto custo computacional, dificuldade de treinamento e retreinamento, alta volatilidade dos dados e falta de dados rotulados [25]. As técnicas de predição de tráfego são aplicadas com diferentes escalas de tempo ou, até mesmo, em problemas independentes de tempo.…”

What happens next? Combining enhanced multilevel script learning and dual fusion strategies for script event prediction

“…Event analysis based on big data has thus been attracting huge attention from the research community and covered various research directions such as event detection, summarization, and prediction. Among these directions, event prediction focuses on the analysis of future possible events, and has become an increasingly crucial issue in a broad range of fields, such as financial investment, 7 network monitoring, 8 network security, 9 disease prevention, 10 and disaster management. 11 Along this line, we investigate a special and challenging event prediction task in this paper, that is, script event prediction (SEP).…”

Machine Learning with Variable Sampling Rate for Traffic Prediction in 6G MEC IoT

“…It has always been a meaningful research topic to analyze the distribution and demand of communication trafc by predicting the wireless network trafc to guide the communication resources' allocation [7]. Te previous wireless trafc prediction adopted manual prediction and statisticalbased prediction methods, and their limitations are obvious.…”