Conflict Resolution in Mobile Networks: A Self-Coordination Framework Based on Non-Dominated Solutions and Machine Learning for Data Analytics [Application Notes]

Abstract

Self-organizing network (SON) is a well-known term used to describe an autonomous cellular network. SON functionalities aim at improving network operational tasks through the capability to configure, optimize and heal itself. However, as the deployment of independent SON functions increases, the number of dependencies between them also grows. This work proposes a tool for efficient conflict resolution based on network performance predictions. Unlike other state-of-the-art solutions, the proposed self-coordination framework guarantees the right selection of network operation even if conflicting SON functions are running in parallel. This self-coordination is based on the history of network measurements, Corresponding Author: Jessica Moysen (Email: jessica.moysen@tsc.upc.edu) which helps to optimize conflicting objectives with low computational complexity. To do this, machine learning (ML) is used to build a predictive model, and then we solve the SON conflict by optimizing more than one objective function simultaneously. Without loss of generality, we present an analysis of how the proposed scheme provides a solution to deal with the potential conflicts between two of the most important SON functions in the context of mobility, namely mobility load balancing (MLB) and mobility robustness optimization (MRO), which require the updating of the same set of handover parameters. The proposed scheme allows fast performance evaluations when the optimization is running. This is done by shifting the complexity to the creation of a prediction model that uses historical data and that allows to anticipate the network performance. The simulation results demonstrate the ability of the proposed scheme to find a compromise among conflicting actions, and show it is possible to improve the overall system throughput.

Multi-agent reinforcement learning for intent-based service assurance in cellular networks

“…Similarly, in the case of priority agents, the actions consist of decisions for increasing or decreasing the current packet priority of a service, i.e., A = {−1, 1}. The minimum/maximum priority values are defined to comply with the Network Emulator design, e.g., [1,100], where a small value denotes high priority.…”

“…any change in one closed loop may affect the KPIs assured by another closed loops. Optimization for each objective in isolation or in some cases sequentially [1] is possible through existing methods in literature, but the challenge manifests when the objectives conflict with each other and the model of the environment is not available. It is to be noted that the operator or higher domain functions, which are feeding such objectives, may not be aware of such conflicts and hence pre-planning on conflict avoidance may not be feasible in all scenarios.…”

Data Analytics Architectural Framework for Smarter Radio Resource Management in 5G Radio Access Networks

“…A significant number of them are related to self-healing, covering aspects such as anomaly detection [3], diagnosis [4] or alarm prediction [5]. Some other works have dealt with selfoptimization aspects, such as tilt and power adjustment [6], interference management, self-configuration of neighbour cell lists [7] and coordination of Self-Organizing Network (SON) functions [8]. With respect to the considered methodologies, most of the abovementioned works apply Machine Learning (ML) tools to process the data, such as K-means clustering [3], random forest prediction [5], Self-Organizing Maps [4] or regression models [6] [8].…”

“…Some other works have dealt with selfoptimization aspects, such as tilt and power adjustment [6], interference management, self-configuration of neighbour cell lists [7] and coordination of Self-Organizing Network (SON) functions [8]. With respect to the considered methodologies, most of the abovementioned works apply Machine Learning (ML) tools to process the data, such as K-means clustering [3], random forest prediction [5], Self-Organizing Maps [4] or regression models [6] [8]. These works have also considered different types of data sources, such as call detail records [3], mobile traces [4], counters [5] or User Equipment (UE) measurement reports [6] [8].…”

A Factorization Machine-Based Approach to Predict Performance Under Different Parameters in Cellular Networks

“…Recently, a few of studies have proposed to make predictions under parameters based on their historical data in cellular networks. In 2018, Moysen et al [7] used support vector machine regression model to predict the performance value of each self-organized network function. In 2019, Chuai et al [8] used Support Vector Regression (SVR) and Multilayer Perceptron (MLP) to predict the performance of NEs under their parameters.…”