Cellular Busy Hour Traffic Modeling for Adaptive Resource Scaling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Cellular network resources are often underutilized or overutilized due to varying traffic loads, leading to inefficiencies and waste, as cloud computing resources are dedicated for managing wireless network communications.
Innovation Solution
A mechanism is employed to dynamically determine busy hour traffic in cellular networks by monitoring traffic loads on nodes, distinguishing between stable and high variance traffic, and calculating busy hour traffic based on average peak or median loads accordingly.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If cloud computing resources are dedicated for cellular network management, then network availability is improved, but resource utilization efficiency deteriorates due to underutilization or overutilization
Solution Approach 1:
The system dynamically determines busy hour traffic by monitoring traffic loads and distinguishing between stable and high variance traffic patterns. This dynamic approach allows resource allocation to adapt to changing network conditions, preventing both underutilization and overutilization of dedicated cloud computing resources while maintaining network availability.
Solution Approach 2:
The system changes the parameter used for busy hour determination based on traffic characteristics. For stable traffic, it uses average peak traffic load; for high variance traffic, it uses average median traffic load. This parameter adaptation optimizes resource utilization efficiency while preserving network reliability under different traffic conditions.
2Measurement precision
If average peak traffic load is used for stable traffic, then accurate busy hour determination is achieved, but resource waste occurs during underutilized periods
Solution Approach 1:
The system adapts the measurement parameter based on traffic stability. For stable traffic patterns, it uses average peak traffic load to maintain accurate busy hour determination. For high variance traffic, it switches to average median traffic load to prevent resource waste during underutilized periods, thus optimizing both measurement precision and resource utilization.
3Productivity
If average median traffic load is used for high variance traffic, then resource allocation efficiency is improved, but measurement precision for busy hour traffic deteriorates
Solution Approach 1:
The system strategically selects measurement parameters based on traffic characteristics. For high variance traffic, it uses average median traffic load to improve resource allocation efficiency and prevent waste. Although this reduces measurement precision compared to using peak values, it provides more realistic resource planning for volatile traffic patterns, achieving optimal balance between efficiency and accuracy.
4Speed
If cloud computing resources are scaled to handle peak traffic, then network performance is improved during busy periods, but resource underutilization occurs during low traffic periods
Solution Approach 1:
The system enables dynamic resource scaling by accurately determining busy hour traffic based on monitored patterns. This allows cloud computing resources to be scaled appropriately for peak performance during busy periods while being scaled down during low traffic periods, preventing resource underutilization and waste while maintaining network performance when needed.
Data Source
AI summary
Systems and methods are directed towards determining busy hour traffic of nodes in a cellular network based on different traffic loads on the nodes. One or more nodes in the cellular network are selected to be monitored. The traffic load on the selected node is monitored during a time period. The monitored traffic load on the node during the time period is determined to be stable traffic or high variance traffic. In response to the monitored traffic load on the node being stable traffic, busy hour traffic is determined for the node based on an average peak traffic load on the node. In response to the monitored traffic load on the node being high variance traffic, the busy hour traffic for the node is determined based on an average median traffic load on the node. The busy hour traffic for the node can then be used to predict future traffic on the node.