Machine Learning-Based Recommender Systems to Achieve Self-Coordination Between SON Functions

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).

<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>

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.

Ultra-dense Heterogeneous networks (UDHN) are emerging as the inevitable approach to cope with the imminent cellular network capacity crunch. However, load imbalance and widely disproportionate SINR distribution between macro and small cells, remains the key hurdle in harnessing the full potential of UDHN. In this paper we address this problem by proposing and analysing a novel load-aware user association methodology that offers a mechanism to simultaneously optimize network capacity, load distribution and coverage. The solution concurrently leverages the three key optimization parameters for Coverage and Capacity Optimization (CCO) and Load Balancing (LB) SON functions i.e. antenna tilts, transmit powers and cell individual offsets (CIOs). The method incorporates exponential-weighting based prioritization of CCO and LB SON functions within the user association process. The results suggest that the proposed approach offers a distribution of load between macro and small cells that yields more gain in terms of both network capacity and user quality of service than conventional max signal strength or max SINR based association methods.

Simultaneously transmitting and reflecting reconfigurable intelligent surfaces (STAR-RISs) is a promising passive device that contributes to full-space coverage via transmitting and reflecting the incident signal simultaneously. As a new paradigm in wireless communications, how to analyze the coverage and capacity performance of STAR-RISs becomes essential but challenging. To solve the coverage and capacity optimization (CCO) problem in STAR-RIS-assisted networks, a multi-objective proximal policy optimization (MO-PPO) algorithm is proposed to handle long-term effects. To strike a balance between each objective, the MO-PPO algorithm provides a set of optimal solutions to approach a Pareto front (PF), where the solution on the approximate PF is regarded as an optimal result. Moreover, in order to improve the performance of the MO-PPO algorithm, two update strategies, i.e., action-value-based update strategy (AVUS) and loss function-based update strategy (LFUS), are investigated. For the AVUS, the improved point is to integrate the action values of both coverage and capacity and then update the loss function. For the LFUS, the improved point is only to assign dynamic weights for both loss functions of coverage and capacity, while the weights are calculated by a min-norm solver at every update. The numerical results demonstrated that the investigated update strategies outperform the fixed weights MO optimization algorithms in different cases, which include a different number of sample grids, the number of STAR-RISs, the number of elements in the STAR-RISs, and the size of STAR-RISs. Additionally, the STAR-RIS-assisted networks achieve better performance than conventional wireless networks without STAR-RISs. Moreover, with the same bandwidth, a millimetre wave is able to provide higher capacity than sub-6 GHz, but at a cost of smaller coverage.

A Self-Organizing Network (SON) performs automated network management through the coordinated execution of autonomous functions, each aiming to achieve a specific objective like the optimization of a network Key Performance Indicator (KPI) value. However, there are situations in which a SON function cannot achieve its objective which can lead to disturbed SON operation and inferior performance. We present a SON Operational Troubleshooting (SONOT) SON function that is able to detect such problematic situations and trigger respective countermeasures. Thereby, it can exploit regular SON functions as probes in order to improve problem detection. Simulations show that the tight integration of the SONOT function with SON coordination provides means to automatically overcome the problems and improve overall network performance.KeywordsSelf-Organizing NetworkSON operationSON coordinationTroubleshooting

This paper presents a framework for coverage and capacity optimization (CCO) in HCNs from stochastic geometry theory. Unlike conventional approaches, we propose a concept of effective capacity as t...

This paper presents a novel scheme of adaptive self-organization network (SON) by integrating cognitive radio (CR) with inter-cell interference coordination (ICIC) for LTE-A heterogeneous networks (HetNets). Particularly, we take advantage of the spectrum sensing function from CR and the radio resource layering function from ICIC. Our work addresses the issues of smart low-power node (SLPN) development, which associates appropriate sectorization with radio resource allocation during the self-organization process. We further develop a Hungary algorithm based self-organization strategy to improve the SLPN adaptive optimization. Simulation results show that our proposed scheme can achieve considerable gain in terms of throughput and coverage, with extra rewards of high flexibility and low complexity in HetNet SON.

To overcome the challenge of large data demanding in future 5G cellular networks, heterogeneous networks (HetNets) take advantage of low power nodes (LPNs) to enhance capacity and coverage. This paper aims at 5G HetNets and presents a novel scheme of adaptive self-organization network (SON) by integrating cognitive radio (CR) with inter-cell interference coordination (ICIC). Particularly, we combine the spectrum sensing function from CR and the radio resource layering function from ICIC. Our work addresses the issues of smart low-power node (SLPN) development, which associates appropriate sectorization with radio resource allocation during the self-organization process. We further develop a Hungarian algorithm based self-organization strategy to improve the SLPN adaptive optimization. Simulation results show that our proposed scheme can achieve considerable gain in terms of throughput and coverage, with extra rewards of high flexibility and low complexity in HetNet SON.

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.

The trend of cellular communication is not only to improve the network throughput, but user satisfaction. In particular, the cell edge performance is an important issue. A lot of studies have been done in the area of Inter-Cell Interference Coordination (ICIC), especially in the cell-edge performance. On the other hand, the issue of energy efficiency for wireless networks has recently gained a lot attention. In this paper, an energy saving mechanism is proposed which operates in conjunction with an autonomous ICIC algorithm for LTE. This allows enhanced NodeBs (eNBs) to cooperate autonomously in the absence of a standardized interface. Simulation results show that cell-edge performance has been significantly improved while using a small fraction of the transmit power compared to the baseline.

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.

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.

International audience

The evaluation of the Signal to Interference Ratio (SIR) in cellular networks is of primary importance for network dimensioning. For static studies, which evaluate cell capacity and coverage, as well as for dynamic studies, which consider arrivals and departures of mobile stations (MS), the SIR is always an important input. Contrary to most of the analytical works evaluating SIR, we assume in this paper that the MS is attached to the best server, i.e., to the base station (BS) from which it receives the highest power. This is a policy that is more realistic than the classical assumption that considers MSs to be attached to the nearest BS. The exact formulation of the SIR is however in this case uneasy to handle and numerical methods remain heavy. In this paper, we thus propose an approximate analytical study based on truncated lognormal distributions that provides very close results to Monte Carlo simulations.