Hot or Not? Forecasting Cellular Network Hot Spots Using Sector Performance Indicators

Abstract

Abstract-To manage and maintain large-scale cellular networks, operators need to know which sectors underperform at any given time. For this purpose, they use the so-called hot spot score, which is the result of a combination of multiple network measurements and reflects the instantaneous overall performance of individual sectors. While operators have a good understanding of the current performance of a network and its overall trend, forecasting the performance of each sector over time is a challenging task, as it is affected by both regular and non-regular events, triggered by human behavior and hardware failures. In this paper, we study the spatio-temporal patterns of the hot spot score and uncover its regularities. Based on our observations, we then explore the possibility to use recent measurements' history to predict future hot spots. To this end, we consider tree-based machine learning models, and study their performance as a function of time, amount of past data, and prediction horizon. Our results indicate that, compared to the best baseline, tree-based models can deliver up to 14% better forecasts for regular hot spots and 153% better forecasts for non-regular hot spots. The latter brings strong evidence that, for moderate horizons, forecasts can be made even for sectors exhibiting isolated, non-regular behavior. Overall, our work provides insight into the dynamics of cellular sectors and their predictability. It also paves the way for more proactive network operations with greater forecasting horizons.

A Large-scale Examination of ”Socioeconomic” Fairness in Mobile Networks

“…As mobile Internet access has become a vital resource for a large population, we believe it is imperative to examine potential unfairness or discrimination. While many works are made on large scale mobile network performance analysis (e.g.,, user mobility [12,30], network KPIs and planning [23,36], network performance metrics [9,41], and user Quality-of-Experience [3,31]), the body of literature does not employ the socioeconomic perspective. The literature on digital divide puts much emphasis on the topic.…”

Deep-Learning Aided Atomic-Scale Phase Segmentation toward Diagnosing Complex Oxide Cathodes for Lithium-Ion Batteries

“…U-Net, a neural network often used for image segmentation, adopts a U-shaped architecture, with an encoder capturing features and a decoder restoring spatial information. To classify the numerous atomic columns with ultrasmall features, we leverage a hard attention mechanism to enable the deep network to focus on only one pixel of each atomic column (Figure b). This mechanism is incorporated into our model by modifying the loss function, which calculates the loss at every pixel.…”