Comparison of Artificial Intelligence and Semi-Empirical Methodologies for Estimation of Coverage in Mobile Networks

Abstract

To help telecommunication operators in their network planning, namely coverage estimation and optimisation tasks, this paper presents a comparison between a semi-empirical propagation model and a propagation model generated using Artificial Intelligence (AI). These two types of propagation models are quite different in their design. The semi-empiric Automatically Calibrated Standard Propagation Model (ACSPM) is specific for an operating antenna, being calibrated every time a use case application is used and the Artificial Intelligence Propagation Model (AIPM) can be applied in different scenarios, once trained, allowing to estimate coverage for a new antenna location, using information from neighboring antennas. These models have quite different features and applicability. The ACSPM should be applied in network optimisation, when using data from the current state of the antennas. The AIPM can be used in the deployment of new antennas, as it uses data from a certain geographical area. For a better comparison of the models studied, extensive Drive Tests (DT) collection campaigns conducted by operators are used, since coverage estimations are more realistic when DTs are considered. Both models are generated using very different methodologies, but their resulting performance is very similar. The AIPM achieves a Mean Absolute Error (MAE) up to 6.1 dB with a standard deviation of 4 dB. When compared to the ACSPM we have an improvement of 0.5 dB, since this only achieves a MAE up to 6.6 dB. AIPM achieves better results and is the characterised for being completely agnostic and definition-free, when compared with known propagation models.

Autonomous Configuration of Communication Systems for IoT Smart Nodes Supported by Machine Learning

“…To evaluate the model performance, and since a regression is used, the Mean Absolute Error (MAE) metric will be used, as it is the most common metric for regression. It measures the average absolute error between the real data and the estimated value, using (2) [37], where P rx is the real value,P rx is the estimated value, and N the number of samples.…”

Estimating the Performance of MIMO SC-FDE Systems Using SISO Measurements

“…Through the fitted curves, shown in Figure 6, it is possible to predict the G∆ (the difference between SISO and MIMO systems for a given BER performance), considering the variation in the R/P ratio. For the first iteration and considering a BER performance of 10 −2 the fitted curve is given by Equation (27). Equation (28) corresponds to a BER of 10 G∆ BER=10 −2 = 0.67 × ln (R/P) − 0.12;…”

“…Note that this relationship is a function of the R/P ratio, so the higher this ratio the greater the impact. As an example, and according to Equation (27), for a BER of 10 −2 and the first iteration of IB-DFE, the value of E b /N 0 , improves by approximately 2.4 dB (G∆ = 2.4 dB), when moving from a SISO system to a MIMO system with 2 transmitting antennas and 10 receiving antennas (R/P = 5).…”

“…This platform is currently used by several mobile operators worldwide, aggregating Configuration Management (CM) and Key Performance Indicators (KPI) data, as well as DTs from their networks. If the radiation pattern of the transmitting antenna was considered, with the gain in the receiving antenna of 0 dB, and the DT campaign measures taken, it is possible to apply the ACSPM model and to estimate the coverage area for this scenario as in [27], depicted in Figure 8. As mentioned above, E b /N 0 values improve by 2.4 dB (G∆ = 2.4 dB) when changing from a SISO system to a MIMO system with an R/P = 5 and a BER of 10 −2 .…”

Cloud-Based Implementation of a SON Radio Resources Planning System for Mobile Networks and Integration in SaaS Metric

“…The gathering and processing of such large quantities of information coming from these networks may be enabled by cloud services, which offer scal-able and elastic storage, processing and networking resources on-demand. In [5]- [9], it is demonstrated that the estimation of coverage within a SON context may gain from the use of cloud services. The large variety of different configuration parameters and Key Performance Indicators (KPIs) from cells using equipment from various manufacturers may be normalised thanks to a cloud-based infrastructure enabling their congregation and combination with large amounts of Drive Tests (DTs) to build accurate estimations of cell coverage.…”