Radio Network Node Traffic Prediction for Power-Saving Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing power consumption adjustment techniques in telecommunications networks, such as DRX, can break service layer agreements and result in poor quality of service due to inadequate prediction of traffic from neighboring cells during handovers.
Innovation Solution
A radio network node generates a combined traffic model based on decentralized learning from frequently connected UEs and neighboring nodes, using machine learning models like LSTM neural networks, to accurately predict traffic patterns and enable/disable power-related features.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Use of energy by moving object
If DRX micro-sleep technique is used to reduce power consumption, then energy efficiency is improved, but service layer agreements such as latency and throughput may be broken and quality of service deteriorates
Solution Approach 1:
The system performs preliminary traffic prediction using machine learning models before activating DRX micro-sleep techniques. By analyzing historical traffic patterns and predicting future traffic demands, the system can proactively determine when it is safe to enter low-power states without violating service layer agreements, thus resolving the contradiction between energy savings and service reliability
Solution Approach 2:
The system implements feedback mechanisms that continuously monitor actual traffic patterns and compare them with predictions. This feedback loop allows the system to learn from past performance and refine its DRX activation decisions, ensuring that power consumption is reduced while maintaining service quality guarantees
2Use of energy by moving object
If DRX micro-sleep technique is used to reduce power consumption, then energy efficiency is improved, but quality of service for certain users deteriorates
Solution Approach 1:
The system applies different DRX strategies to different user groups based on their specific service requirements and traffic patterns. By segmenting users and applying localized quality-of-service policies, the system can allow more aggressive power saving for users with flexible requirements while maintaining high service quality for users with strict latency and throughput requirements
3Measurement precision
If traffic prediction is improved using decentralized modeling, then prediction accuracy is improved, but device complexity increases
Solution Approach 1:
The system segments the traffic prediction task by deploying lightweight machine learning models at the network node level rather than requiring a single complex centralized model. Each network node maintains its own simplified traffic prediction model based on local observations, which reduces individual device complexity while collectively achieving high prediction accuracy through aggregation of multiple node predictions
Data Source
AI summary
A method of operating a radio network node to adjust power consumption of a telecommunications network is provided. The method includes determining a traffic prediction representing how each node of a set of nodes will interact with the radio network node over a period of time using a combined traffic model based on a traffic model of each node in the set of nodes. The method further includes determining to enable or disable at least one power related feature of the radio network node based on the traffic prediction.