Cell Congestion Detection via Multi-Layer Data Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current technologies lack effective methods for mobile network operators and application service providers to accurately detect cell congestion, leading to suboptimal Quality of Experience (QoE) for users, as they cannot access explicit cell load information from core network elements or base stations.
Innovation Solution
A collective intelligence-based cell congestion detection system that utilizes machine learning algorithms to analyze Internet layer, transport layer, and application layer data to determine cell congestion, enabling core network elements and application servers to identify and mitigate congestion by applying appropriate traffic treatments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If core network elements or applications use traditional congestion detection methods, then they can identify congestion using built-in TCP congestion control or standalone data services, but they cannot access explicit cell load information leading to inaccurate detection
Solution Approach 1:
The patent introduces a data service as an intermediary component that collects cell load information from base stations and makes it accessible to core network elements and applications. This mediator bridges the information gap between the radio access network and the core network, enabling accurate congestion detection without requiring direct access to base station data.
Solution Approach 2:
The system implements feedback mechanisms where congestion detection results are used to dynamically adjust traffic routing and resource allocation decisions. The core network elements receive continuous feedback about cell congestion status, enabling them to adaptively manage traffic flows and prevent network overload.
2Productivity
If mobile network operators use throttling mechanisms to mitigate congestion, then they can reduce network load, but they lack accurate cell load information to determine proper treatment
Solution Approach 1:
The patent replaces traditional mechanical throttling mechanisms with an intelligent, data-driven approach. Instead of uniformly reducing traffic flow through throttling, the system uses machine learning algorithms and accessible cell load information to make precise, differentiated routing decisions that optimize network performance without unnecessary traffic reduction.
Solution Approach 2:
The system dynamically changes traffic routing parameters based on real-time cell load conditions. Rather than using fixed throttling thresholds, the network operators can adjust routing parameters adaptively, directing traffic away from congested cells to less loaded cells based on accurate load measurements from the data service.
3Reliability
If application service providers implement conservative transmission strategies to handle congestion, then they can maintain service delivery, but they cannot accurately detect congestion without explicit cell load information
Solution Approach 1:
The patent enables application service providers to take preliminary actions by providing them with advance congestion information through the data service. Applications can proactively adjust their transmission strategies before congestion occurs or worsens, rather than reactively implementing conservative modes after congestion is detected, thereby maintaining service reliability with more informed decisions.
4Adaptability or versatility
If core network elements route traffic through multiple cells, then they can balance load, but they lack the information necessary to make intelligent routing decisions
Solution Approach 1:
The data service acts as an intermediary that aggregates cell load information from multiple base stations and presents it to core network elements in a usable format. This enables intelligent routing decisions by providing the necessary cell load data that would otherwise be unavailable to the core network, allowing flexible and adaptive traffic distribution across multiple cells.
Data Source
AI summary
Concepts and technologies disclosed herein are directed to collective intelligence-based cell congestion detection in mobile telecommunications networks. According to some aspects of the concepts and technologies disclosed herein, a core network element or device application can detect cell congestion based upon Internet layer, transport layer, and application layer data, such as, for example, traffic type, volume, rate, latency, jitter, and the like. According to one aspect disclosed herein, a cell congestion detection (“CCD”) system can collect data from an Internet layer, a transport layer, and an application layer. The CCD system can apply a machine learning algorithm to the data to determine whether the cell is congested. According to another aspect the CCD system can collect the data that is associated with a specific application executed by a plurality of UE devices connected to a cell.