Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Predicting Drive Test Results in Mobile Networks Using Optimization Techniques

MohammadJava Taheri, Abolfazl Diyanat, MortezaAli Ahmadi, Ali Nazari

TL;DR

The paper addresses the challenge of costly drive tests in mobile networks by enabling RSRP prediction at uncovered locations using data from nearby drive-test points. It introduces an optimization-based method to estimate path-loss parameters via a Friis model, together with a novel shadowing-noise standard-deviation estimator that does not require cell-location data, and validates the approach on real Tehran network data collected with the Venus Android tool. The methodology combines circle-based point selection, cell-wise point grouping, and constrained optimization (MLE or MSE) to predict $P_r$ through $P_0$ and $\beta$ estimates, while quantifying shadowing via $\sigma$ estimated from power differences. Evaluation with large-scale field data demonstrates robustness to parameter choices, reveals the impact of shadowing on accuracy, and shows potential for substantially reducing field data collection in network optimization.

Abstract

Mobile network operators constantly optimize their networks to ensure superior service quality and coverage. This optimization is crucial for maintaining an optimal user experience and requires extensive data collection and analysis. One of the primary methods for gathering this data is through drive tests, where technical teams use specialized equipment to collect signal information across various regions. However, drive tests are both costly and time-consuming, and they face challenges such as traffic conditions, environmental factors, and limited access to certain areas. These constraints make it difficult to replicate drive tests under similar conditions. In this study, we propose a method that enables operators to predict received signal strength at specific locations using data from other drive test points. By reducing the need for widespread drive tests, this approach allows operators to save time and resources while still obtaining the necessary data to optimize their networks and mitigate the challenges associated with traditional drive tests.

Predicting Drive Test Results in Mobile Networks Using Optimization Techniques

TL;DR

The paper addresses the challenge of costly drive tests in mobile networks by enabling RSRP prediction at uncovered locations using data from nearby drive-test points. It introduces an optimization-based method to estimate path-loss parameters via a Friis model, together with a novel shadowing-noise standard-deviation estimator that does not require cell-location data, and validates the approach on real Tehran network data collected with the Venus Android tool. The methodology combines circle-based point selection, cell-wise point grouping, and constrained optimization (MLE or MSE) to predict through and estimates, while quantifying shadowing via estimated from power differences. Evaluation with large-scale field data demonstrates robustness to parameter choices, reveals the impact of shadowing on accuracy, and shows potential for substantially reducing field data collection in network optimization.

Abstract

Mobile network operators constantly optimize their networks to ensure superior service quality and coverage. This optimization is crucial for maintaining an optimal user experience and requires extensive data collection and analysis. One of the primary methods for gathering this data is through drive tests, where technical teams use specialized equipment to collect signal information across various regions. However, drive tests are both costly and time-consuming, and they face challenges such as traffic conditions, environmental factors, and limited access to certain areas. These constraints make it difficult to replicate drive tests under similar conditions. In this study, we propose a method that enables operators to predict received signal strength at specific locations using data from other drive test points. By reducing the need for widespread drive tests, this approach allows operators to save time and resources while still obtaining the necessary data to optimize their networks and mitigate the challenges associated with traditional drive tests.

Paper Structure

This paper contains 21 sections, 1 theorem, 27 equations, 10 figures.

Table of Contents

  1. Introduction
  2. Motivation
  3. Contribution
  4. Paper Structure
  5. Related works
  6. Proposed Approach
  7. System Model and Assumptions
  8. Proposed Methodology
  9. Points Selection
  10. Cells Identification and Points Grouping
  11. Path Loss Modeling
  12. Shadowing Noise Estimation
  13. Evaluation
  14. Data Collection
  15. Experimental Setup
  16. ...and 6 more sections

Key Result

Lemma 1

If the noise in equation eq:pip0math follows a Gaussian distribution, then MLE is optimal from the perspective of the , which represents the minimum variance for the parameter we want to estimate.

Figures (10)

  • Figure 1: Key Areas in Mobile Network Optimization from a Data Collection Perspective
  • Figure 2: Illustration of a Drive Test: The point $\rho_t$ is plotted on a hypothetical circle with radius $R$. Points within the circle form the set $\Phi$.
  • Figure 3: Each color represents a connection to a specific cell. For example, points within the hypothetical circle are connected to four distinct cells.
  • Figure 4: Visualization of Drive Test Points Connecting to Cells
  • Figure 5: Calculation of Distance Between Consecutive Measurements
  • ...and 5 more figures

Theorems & Definitions (2)

  • Lemma 1
  • proof