Cell Site Classification for Telecom Network Merge Forecasting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing network planning tools are complex and unreliable, particularly when merging or expanding telecommunications networks with limited information about cell site characteristics, leading to challenges in predicting service degradation and redundant coverage.
Innovation Solution
A network planning tool that classifies cell sites based on spatial and coverage criteria to determine which sites can be decommissioned without causing unacceptable service degradation, using Voronoi polygons to simulate network layouts and estimate coverage areas.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If network planning tools use complex algorithms and multiple data sources to improve forecasting accuracy, then prediction reliability improves, but tool complexity increases
Solution Approach 1:
The network planning tool is divided into distinct functional modules: a data acquisition module that collects cell site information from multiple sources, a simulation module that generates network layouts using Voronoi polygons, and an analysis module that evaluates coverage and identifies redundant sites. This segmentation allows each module to handle specific tasks independently, improving overall reliability while managing complexity through modular design.
Solution Approach 2:
The tool performs preliminary simulations and classifications of cell sites before final network planning decisions are made. By pre-processing data to identify potential redundant coverage areas and classify cell sites based on spatial relationships, the system prepares forecasts in advance, improving reliability of final predictions while reducing the complexity of real-time decision-making.
2Measurement precision
If network planners use detailed signal measurements and logged information to improve coverage prediction accuracy, then measurement precision improves, but information processing time increases
Solution Approach 1:
The system creates simplified geometric representations (Voronoi polygons) that copy and approximate the complex signal propagation patterns. Instead of processing all detailed signal measurements directly, the tool generates polygonal models that replicate coverage areas, maintaining prediction accuracy while dramatically reducing processing time through geometric simplification.
Solution Approach 2:
The tool transforms detailed signal measurement data into spatial parameters by converting coverage information into geometric polygon representations. This parameter transformation changes the data from continuous signal strength measurements to discrete spatial boundaries, enabling faster processing while preserving the essential coverage characteristics needed for accurate predictions.
3Reliability
If the tool simulates complete network layouts with all cell sites to improve forecasting accuracy, then prediction reliability improves, but computational resources increase
Solution Approach 1:
The system extracts and identifies redundant cell sites by comparing simulated coverage areas. By taking out or removing the identification of unnecessary sites from the complete network simulation, the tool reduces computational resources required for subsequent planning decisions while maintaining forecasting reliability through the preliminary identification of redundant coverage areas.
Solution Approach 2:
The tool performs a complete simulation initially to ensure accuracy, but then uses the results to focus subsequent analysis only on critical areas or potential redundant sites. This partial action approach maintains forecasting reliability by doing a full simulation when needed, while reducing computational resources by limiting detailed analysis to specific regions of interest identified in the initial comprehensive simulation.
Data Source
AI summary
The disclosed embodiments include a method for classifying cell sites of a virtual network that simulates merging a donor network with an anchor network. The method can include obtaining cell site information of the anchor network and the donor network, simulating the virtual network that merges the donor network with the anchor network, and classifying each donor site based on a value associated with the donor site relative to nearest anchor sites. Any anchor site that is located a threshold distance from the donor site is a nearest anchor site. A donor site is classified for decommissioning when the value is less than or equal to a threshold or the donor site is classified for retaining when the value is greater than the threshold. The method can further include causing an output of an indication of any donor site that is classified for decommissioning or retaining.