In this paper, a survey of the literature of the past 15 years involving machine learning (ML) algorithms applied to self-organizing cellular networks is performed. In order for future networks to overcome the current limitations and address the issues of current cellular systems, it is clear that more intelligence needs to be deployed so that a fully autonomous and flexible network can be enabled. This paper focuses on the learning perspective of self-organizing networks (SON) solutions and provides, not only an overview of the most common ML techniques encountered in cellular networks but also manages to classify each paper in terms of its learning solution, while also giving some examples. The authors also classify each paper in terms of its self-organizing use-case and discuss how each proposed solution performed. In addition, a comparison between the most commonly found ML algorithms in terms of certain SON metrics is performed and general guidelines on when to choose each ML algorithm for each SON function are proposed. Lastly, this paper also provides future research directions and new paradigms that the use of more robust and intelligent algorithms, together with data gathered by operators, can bring to the cellular networks domain and fully enable the concept of SON in the near future.

/pdf/a-survey-of-machine-learning-techniques-applied-to-self-5ggfpvrhwz.pdf

A Survey of Machine Learning Techniques Applied to Self-Organizing Cellular Networks

From 4G to 5G: Self-organized network management meets machine learning

As the complexity of commercial cellular networks grows, there is an increasing need for automated methods detecting and diagnosing cells not only in complete outage but with degraded performance as well. Root cause analysis of the detected anomalies can be tedious and currently carried out mostly manually if at all; in most practical cases, operators simply reset problematic cells. In this paper, a novel integrated detection and diagnosis framework is presented that can identify anomalies and find the most probable root cause of not only severe problems but even smaller degradations as well. Detecting an anomaly is based on monitoring radio measurements and other performance indicators and comparing them to their usual behavior captured by profiles, which are also automatically built without the need for thresholding or manual calibration. Diagnosis is based on reports of previous fault cases by identifying and learning their characteristic impact on different performance indicators. The designed framework has been evaluated with proof-of-concept simulations including artificial faults in an LTE system. Results show the feasibility of the framework for providing the correct root cause of anomalies and possibly ranking the problems by their severity.

An Automatic Detection and Diagnosis Framework for Mobile Communication Systems

Mobile cellular network operators spend nearly a quarter of their revenue on network management and maintenance. Incidentally, a significant proportion of that budget is spent on resolving outages that degrade or disrupt cellular services. Historically, operators mainly rely on human expertise to identify, diagnose, and resolve such outages. However, with growing cell density and diversifying cell types, this approach is becoming less and less viable, both technically and financially. To cope with this problem, research on self-healing solutions has gained significant momentum in recent years. Self-healing solutions either assist in resolving these outages or carry out the task autonomously without human intervention, thus reducing costs while improving mobile cellular network reliability. However, despite their growing popularity, to this date no survey has been undertaken for self-healing solutions in mobile cellular networks. This paper aims to bridge this gap by providing a comprehensive survey of self-healing solutions proposed in the domain of mobile cellular networks, along with an analysis of the techniques and methodologies employed in those solutions. This paper begins by providing a quantitative analysis to highlight why in emerging mobile cellular network self-healing will become a necessity instead of a luxury. Building on this motivation, this paper provides a review and taxonomy of existing literature on self-healing. Challenges and prospective research directions for developing self-healing solutions for emerging and future mobile cellular networks are also discussed in detail. Particularly, we identify that the most demanding challenges from self-healing perspective are the difficulty of meeting 5G low latency and the high quality of experience requirement.

Self-Healing in Emerging Cellular Networks: Review, Challenges, and Research Directions

The increase in the size and complexity of current cellular networks is complicating their operation and maintenance tasks. While the end-to-end user experience in terms of throughput and latency has been significantly improved, cellular networks have also become more prone to failures. In this context, mobile operators start to concentrate their efforts on creating self-healing networks, i.e., those networks capable of troubleshooting in an automatic way, making the network more reliable and reducing costs. In this paper, an automatic diagnosis system based on unsupervised techniques for Long-Term Evolution (LTE) networks is proposed. In particular, this system is built through an iterative process, using self-organizing maps (SOMs) and Ward's hierarchical method, to guarantee the quality of the solution. Furthermore, to obtain a number of relevant clusters and label them properly from a technical point of view, an approach based on the analysis of the statistical behavior of each cluster is proposed. Moreover, with the aim of increasing the accuracy of the system, a novel adjustment process is presented. It intends to refine the diagnosis solution provided by the traditional SOM according to the so-called silhouette index and the most similar cause on the basis of the minimum $X$ th percentile of all distances. The effectiveness of the developed diagnosis system is validated using real and simulated LTE data by analyzing its performance and comparing it with reference mechanisms.

Automatic Root Cause Analysis for LTE Networks Based on Unsupervised Techniques

The Self-Organizing Networks (SON) concept includes the functional area known as self-healing, which aims to automate the detection and diagnosis of, and recovery from, network degradations and outages This paper focuses on the problem of cell anomaly detection, addressing partial and complete degradations in cell-service performance, and it proposes an adaptive ensemble method framework for modeling cell behavior The framework uses Key Performance Indicators (KPIs) to determine cell-performance status and is able to cope with legitimate system changes (ie, concept drift) The results, generated using real cellular network data, suggest that the proposed ensemble method automatically and significantly improves the detection quality over univariate and multivariate methods, while using intrinsic system knowledge to enhance performance

/pdf/detecting-anomalies-in-cellular-networks-using-an-ensemble-381e5h1i2j.pdf

Detecting anomalies in cellular networks using an ensemble method

The ever increasing complexity of commercial mobile networks drives the need for methods capable of reducing human workload required for network troubleshooting. In order to address this issue, several attempts have been made to develop automatic anomaly detection and diagnosis frameworks for mobile network operators. In this paper, the latest improvements introduced to one of those frameworks are discussed, including more sophisticated profiling and detection capabilities. The new algorithms further reduce the need for human intervention related to the proper configuration of the profiling and anomaly detection apparatus. The main concepts of the new approach are described and illustrated with an explanatory showcase featuring performance data from a live 3 G network.

An improved anomaly detection and diagnosis framework for mobile network operators

The rapid growth of IP-based mobile telecommunication technologies in the past few years has revealed situations where not only a single node but an entire network moves and changes its point of attachment to the Internet. The main goal of any protocol supporting network mobility is to provide continuous, optimal and secure Internet access to all nodes and even recursively nested mobile subnetworks inside a moving network. For this purpose, the IETF (Internet Engineering Task Force) has developed the NEtwork MObility Basic Support (NEMO BS) protocol which extends the operation of Mobile IPv6 (MIPv6). In order to bypass the same problems suffered by MIPv6 and NEMO BS, a novel Host Identity Protocol (HIP) extension called HIP-NEMO is introduced, proposed and evaluated in this paper. Our proposal is based on hierarchical topology of mobile RVSs (mRVS), signaling delegation and inter-mRVS communication to enable secure and efficient network mobility support in the HIP layer. The method provides secure connectivity and reachability for every node and nested subnet in the moving network and supports multihomed scenarios as well. Moreover, HIPNEMO reduces signaling and packet overhead during network mobility management by achieving route optimization inside any moving network even in nested scenarios. To evaluate the proposed scheme we present a simulation model implemented in OMNeT++ and discuss the results of our simulation based analysis to show the efficiency of the approach compared to the NEMO BS protocol formulated by the IETF.

Design and Evaluation of a Novel HIP-Based Network Mobility Protocol

The host identity protocol (HIP) is a rather new concept that separates the identity and location information both represented by IP addresses in the current Internet architecture. HIP also has capabilities and efficient extensions to serve macromobility, but it shows unnecessary signaling overhead and handoff latency, when used in micromobility environments. This paper introduces a new method how HIP can be extended to serve as a micromobility protocol.

Szabolcs Nováczki

Papers

An Automatic Detection and Diagnosis Framework for Mobile Communication Systems

Detecting anomalies in cellular networks using an ensemble method

An improved anomaly detection and diagnosis framework for mobile network operators

Design and Evaluation of a Novel HIP-Based Network Mobility Protocol

Micromobility support in HIP: survey and extension of host identity protocol