Improving Traffic Forecasting Accuracy in Mobile Networks Through Machine Learning-Based Classification Techniques
Abstract
Network traffic forecasting is one of the activities that employs machine learning techniques for efficient network administration.This activity tries to manage user demands, minimize service disruptions, monitor user behavior in applications, and detect any issues before they arise [1].A base station uses traffic predictions for intelligent power use.This issue is examined using base station sleeping, mobile edge computing, network slicing, and extra power during periods of high demand.Both short-term and long-term forecasts are used for traffic, although occasionally medium-term forecasting is also required.Forecasting the amount of internet traffic is one of the most crucial duties in the proactive administration of contemporary telecommunications networks.Enhancing traffic demand forecasting's precision and effectiveness can aid ISPs in creating sensible business plans and boosting the sector's financial gains.Additionally, very accurate forecasting findings can be useful for advanced network design, route planning, both immediate and long-term business capacity planning, and improved resource management.To put it another way, an accurate traffic prediction system may help ISPs manage their networks in advance and guarantee improved network quality of experience (QoS) [2].Regardless of their location or time, mobile networks enable users to stay connected at all times, particularly while they are outside.The availability of mobile connection services is still lacking,…
How strong is the evidence?
Evidence Hub reads this as a dataset, done in computer models (in silico), not in people. Its evidence level is 5 of 5 (Very low · case / narrative / animal / in vitro / in silico). Case reports, narrative reviews, and animal, cell or computer-model studies give the weakest evidence for human health.
Read the paper
Related studies
- Active Learning during Federated Learning for Object Detection
- Fairness-aware federated learning
- Decentralized Federated Learning
- Building a Personally Identifiable Information Recognizer in a Privacy Preserved Manner Using Automated Annotation and Federated Learning
- Preservation of Patient Level Privacy: Federated Classification and Calibration Models
- Efficient explainable federated learning
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.