Operational Troubleshooting-Enabled Coordination in Self-Organizing Networks

<p>WiFi networks based on the IEEE 802.11 standard are widely used indoors or outdoors as simple and cost-effective wireless technology. However, the data connection is significantly disrupted when mobile stations (STAs) switch between access points (APs). Furthermore, high packet loss occurs during the switching period. Therefore, mobility is a critical issue that needs to be solved in WiFi networks. In cellular networks, handover is used to keep ongoing data transfer when network clients switch between base stations. However, the handover algorithm is not supported in the 802.11 standard for WiFi networks. Self-Organizing Network (SON) functionality enables seamless handover in cellular networks, improving network performance. However, the SON functionality has not been fully researched in WiFi networks, especially for mobility management. Motivated by the SON functionalities, a SON approach is proposed to automatically optimize the handover algorithms for WiFi networks. This approach focuses on the SON functionalities including self-configuration, self-optimization and self-healing using machine learning techniques to develop new algorithms for WiFi mobility management. The overall goal of this thesis is to optimize handover performance as well as enhance the network’s capabilities.</p>

The management and operation of a Self-Organizing Network (SON)-enabled mobile network still requires considerable human effort. On the one hand, SON Functions need to be configured through low-level parameters in order to control the optimization of the network. On the other hand, an operator wants to steer the system with solely technical objectives, and the underlying network should be adapted accordingly. This opens up a gap in network management that is currently closed manually. This paper presents an approach that overcomes the manual gap between technical objectives and SON Functions by choosing the best values for the SON Functions' configurations automatically. Main advantage of this approach is that it allows to manage a system at a high level of abstraction and, at the same time, reduces manual effort. The approach is explained by applying it in a case study in the field of mobile networks with four SON Functions, namely Mobility Load Balancing (MLB), Coverage and Capacity Optimization (CCO), Energy Savings Management (ESM) and Mobility Robustness Optimization (MRO).

The Self-Organizing Network (SON) paradigm enables automated management of next generation mobile communication networks by introducing a set of autonomous functions that jointly achieve self-configuration, self-optimization, and self-healing. Each SON function is driven by a specific objective to optimize one or more Key Performance Indicators (KPIs). If a function encounters situations in which the given targets cannot be achieved, it can produce undesired behavior, resulting in an impaired SON. This paper presents the idea of SON Operational Troubleshooting function and outlines a concept for the automatic detection, analysis, and mitigation of operational problems.

Future wireless networks (LTE and beyond) will experience a continuous growth regarding the number of network elements with increasingly complex interrelations between the configuration of multiple network elements (NEs). A related trend is the seamless integration of multiple radio technologies into a single heterogeneous wireless network. Both developments increase network management complexity and require new management concepts with a very high degree of automation such as Self-Organizing Network (SON) concepts, which are currently discussed in the network operator (NGMN), research, and standardization (3GPP) communities. SON functions have to be coordinated and supervised in an automated way in order to enable a stable system operation with tight control over the system behavior by the network operator together with a high degree of automation. Based on a detailed analysis of the requirements for the coordination, a policy-based approach to realize the coordination-related decision making based on the network configuration and SON function context is presented. Results for two use cases (fully automatic hardware to site mapping and coverage & capacity optimization) are presented to show the applicability of the developed approach to diverse SON use cases.

The deployment, operation and maintenance of complex cellular networks are managed autonomously by multiple concurrently executing Self-Organizing Network (SON) functions with dedicated objectives, that can often negatively impact the functioning of each other. It is essential to avoid the blinkered view to their individual targets and consider a holistic approach towards identifying the best possible coordination between them, in order to achieve desired overall network gains while ensuring stable and robust network operation. The designing of appropriate SON-coordination mechanisms is quite challenging as it requires comprehensive modelling of all the complementing and conflicting interactions among them. This article discusses the application of Machine Learning based online Recommender Systems to model the dynamics between SON functions. To evaluate its applicability, in this work, the focus is to jointly implement two intertwined SON functions - Inter Cell Interference Coordination (ICIC) and Coverage and Capacity Optimization (CCO), to implicitly handle their conflicts and achieve the desired trade-off between coverage and capacity by optimizing a joint objective. The proposed cooperative learning and distributed configuration enforcement based ICIC-CCO coordinated SON solution has been evaluated on a system-level LTE network simulator with varied traffic distributions. It has been observed that the outage situations in the network are significantly reduced while still achieving high Signal-to-Interference Ratios (SIRs), even with reduced transmit power settings on several occasions.

The instrumentation of Self-Organising Network (SON) Functions in such way that they contribute to the operational objectives defined by a wireless network operator is a complex task. In order to enable automation of this configuration, we previously described the concept of a SON Objective Manager (SOM) which determines the best configuration based on conditional, ranked objectives and SON Function models describing the Key Performance Indicators (KPIs) optimised by some configuration. However, the simplicity of the models and the complexity of the design-time inference may limit the applicability of the initial concept. In this paper, we present an extended and enhanced run-time SOM with more expressive input models, namely, context-dependent, weighted operator objectives allowing a better trade-off and SON Function models defining the possible values of KPIs for some configuration. These improvements together allow for a broader application of the concept.

Over the last years the complexity of mobile communication networks has significantly increased. Therefore, Self-Organizing Network (SON) features have been introduced to automate the process of fault-remedying, configuring Network Elements (NEs), and optimizing their operation. Such features are typically implemented by SON functions which actively perform changes to Configuration Management (CM) parameters in order to achieve certain objectives. However, having such features also requires a mechanism that allows us to verify their actions. In case certain NEs experience an undesired behavior, we have to be able to determine whether it is caused by CM changes and, if so, identify the responsible ones for that to happen. In this paper we propose a novel CM change performance assessment method with dynamic scope management for automated CM undo decision making. Our method includes two key properties: the ability to determine the minimal set of cells that are possibly influenced by a certain CM change, and generate a recommendation to accept or reject it based on the observed network performance. Results from our real data evaluation show our method is able to detect anomalous network behavior and identify the responsible changes.

This demonstrator visualises a new paradigm for the management of Self-Organising Networks (SON), and the impact of SON management decisions on a heterogeneous mobile radio network. The main aspects shown thereby cover the operability of the system from a network operator perspective, and the effects of different SON implementation options on the Key Performance Indicators (KPIs) of the network. In terms of operability, the demonstrator shows that even a complex definition of target values for KPIs through the operator, which may be weighted against each other and have different values depending on the operational and network context, can be deployed to the implemented SON functions in a fully automated way. Changes to the target values, the context or the implemented SON functions lead to an automated adaptation of the SON system such that the KPI targets are achieved in the best possible way.

Edge intelligence in radio access network (RAN) is an emerging concept wherein machine learning (ML) driven self-organizing network (SON) functions reside in edge nodes or base stations (BSs). This allows to fulfill ultra-low latency, scalability, ultra-high reliability and signaling needs and requirements for beyond-5G applications. However, the resource-intensive hyper-parameter search of edge-distributed ML workloads is a major challenge that undermines the gains of ML driven automated networks. In current edge-ML, resource-constraints force the ML driven SON functions to incline towards inference-only workloads at the edge, whereas their training is done in the central infrastructure in non-collaborative fashion. This requires a redundant transfer of big data for training from the edge to the central location and a hyper-parameter search with high space time complexity, eventually resulting in high signaling costs and delays. This paper aims to address these challenges by presenting the Coordinated HypEr-paramETer seArcH (CHEETAH) frame-work for edge intelligence. It is a resource-efficient, low time-complexity distributed framework that eliminates the transfer of large training data from the edge to the central location and reduces the time required to find optimal (or near-optimal) hyper-parameters. Using a traffic forecasting use-case based on real network data, we demonstrate that as compared to state-of-the-art, the CHEETAH framework offers an attractive pragmatic solution in terms of predicting the best hyper-parameter configuration while keeping the associated costs low.

Traffic forecasting plays an important role in improving network quality and energy saving of mobile networks. In 5G, traffic forecasting directly influences the self-organizing network (SON) in managing and controlling the network effectively. Especially, long-term traffic forecasting can provide a detailed pattern of future traffic, besides permitting more time for planning and optimizing. Most of the traffic forecasting models used the history of traffic, while the utilization of another network KPIs (key performance indicators) for traffic forecasting is limited. Therefore, the authors propose here a practical platform and process for traffic forecasting, based on big data, machine-learning (ML), and network KPIs that are flexible to forecast accurately different statistical traffic characteristics of different types of cells (GSM, 3G, 4G) for both long- and short-term forecasting. The performance of the proposed model was evaluated by applying it to a real dataset that collected KPIs of more than 6000 cells of a real network during the years, 2016 and 2017.

In mobile networks, handover (HO) is one of the most important and complex KPIs (Key Performance Indicators), which directly affect to Quality of Service (QoS), Quality of Experience (QoE), and mobility performance. Moreover, its configuration parameters such as handover thresholds and handover neighbor lists are the key factors for implementing network optimization such as load balancing and energy saving. In a study before, the authors proposed clustering and forecasting models using ML algorithms and Time Series models to cluster, forecast, and manage the HO behavior of a huge number of cells. In this study, on the other hand, the authors firstly investigated more network KPIs to analyze their relationship with HO KPIs, and then, proposed new clustering, forecasting, and abnormal detection models that are expected to make them much more comprehensive. Finally, the performances of the proposed models were evaluated by applying them to a real dataset collected from the HO KPIs and other KPIs of more than 6000 cells of a real network during the years, 2016 and 2017. The results showed that the study was successful in identifying the relationship among network KPIs and significantly improving the performance of the HO clustering, forecasting, abnormal detection models. Moreover, the study also introduced the integration of emerging technologies such as machine learning (ML), big data, software-defined network (SDN), and network functions virtualization (NFV) to establish a practical and powerful computing platform for future self-organizing networks (SON).

It has been observed that in overlaid 3G/2G networks certain user equipments (UE) may stay camped on 2G for long periods despite the fact there is available 3G coverage. In this paper we present a framework to enable network operators to identify these occurences, not easily recognized using counter-based observability. The proposed methodology relies on the post processing of performance monitoring (PM) events from the radio access and core networks, feature provided by most major network vendors. Based on that, new key performance indicators (KPI) are defined e.g. the time UEs camp on 2G. Then, we show how these event-based KPIs may be used as inputs to self-optimization algorithms, functioning as a self-organizing networks (SON) enabler. Results are shown using data from live 3G/2G networks.

The goal of our research and experiments is to find the definitions and values of key performance indicators (KPIs) in unstructured text. The direct access to opinions of customers served as a motivating factor for us to choose Twitter data for our experiments. For our case study, we have chosen the restaurant business domain. As in the other business domains, KPIs often serve as a solution for identification of current problems. Therefore, it is essential to learn which criteria are important to restaurant guests. The mission of our Proof-of-Concept KPI discovery tool presented in this paper is to facilitate the explorative analysis taking Twitter user posts as a data source. After processing tweets with Stanford CoreNLP toolkit, aggregated values are computed and presented as visual graphs. We see our tool as an instrument for data discovery applicable, for example, to define new qualitative and quantitative KPIs based on the values found in the graph. The graph represents a complete view of aggregated data that corresponds to the search results according to the user-defined keywords, and gives easy access to detailed data (tweets) that, in its turn, leads to better understanding of the post context and its emotional coloring.

The continuous growth and evolution of the wireless systems into dense and complex heterogeneous scenarios has posed new challenges in terms of complexity for system configuration and optimization tasks. To address this problem, self-organizing networks functionalities are one of the key components in next generation mobile networks, since they enhance system performance and reduce operational expenditures. Inspired by concepts from autonomic network management, cognitive networks, and mobile-edge computing, this paper proposes a cooperative and cognitive SON framework (CCSON) for 5G mobile radio access networks. The main idea is to provide RAN elements with cognitive capabilities, so that they build and adapt models dynamically to support the self-organizing features. Finally, extensive simulations show the effectiveness of our approach for a load balancing scenario in heterogeneous LTE networks.

Developing countries are experiencing simultaneous growth of population, income and private vehicle ownership, which significantly affects urban transport environment and poses challenges to policymakers and urban transport professionals. Experience shows that the performance of urban transport service delivery in many developing countries is low; policy makers have incomplete information to make decisions and managers and professionals rarely have a clear picture of their operational performance, best practices elsewhere or the desired level of their service provision, which is the case of urban transport services in Nigeria. Urban transport in Nigeria is largely an unregulated market and inadequate both in quality and quantitative terms. Urban transport technology in use in Nigeria is a combination of Para-transit modes, consisting of shared taxis, minibuses, motorcycles and tricycles. Only in the cities of Lagos and Abuja are conventional buses in use, but even in both cities the use of Paratransit modes of transport is obviously dominant. As a matter of fact, Nigeria remains the only country in the world where densely populated cities with over 6 million people do not have an organized urban transport system based on a combination of conventional buses and rail. It will be therefore imperative to identify Key performance indicators (KPIs) that can be used to measure and improve the performance of urban transport services in Nigeria. This paper is focused on the identification of Key Performance Indicators (KPIs) for urban transport development in Nigeria. The KPIs that have been identified in this paper following the performance measurement framework can be used to monitor and evaluate urban transport performance in Nigeria and eventually guide the further development and modernization of urban transport system in Nigeria, in the sense that the KPIs will assist in identifying key areas for improvement and also serve as a guide for transport policy makers in making decisions. The KPIs presented in this paper have been categorized into Safety, Security, Environmental pollution, Financial perspective, Traffic management and Customer satisfaction.