Published on:
8 May 2024
Primary Category:
Systems and Control
Paper Authors:
Hossein Mehri,
Hao Chen,
Hani Mehrpouyan
Proposes ML framework combining LSTM and DenseNets to predict bursty traffic
Develops efficient online prediction algorithm that leverages real-time data
Achieves 52% higher accuracy than traditional methods
Identifies congestion events before they occur
Well-suited for time-critical, resource-constrained applications
Predicting Bursty Traffic in M2M Networks
This paper presents a machine learning framework to forecast bursty traffic patterns in massive machine-type communication networks. It uses long short-term memory and dense neural networks to accurately predict traffic and identify congestion events by assimilating real-time data. A new online prediction algorithm updates model states efficiently. Evaluations demonstrate 52% higher accuracy without additional overhead.
Predicting traffic patterns with neural networks
Predicting Cellular Traffic in Real Time
Learning traffic patterns from road network data
Liquid neural networks adapt to network failures
Predicting inter-packet arrival times to improve scheduling in cellular V2X
Multi-range spatiotemporal traffic forecasting
No comments yet, be the first to start the conversation...
Sign up to comment on this paper