Linear UCB for Online SON Management

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.

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 paper discusses quality of service in LTE and LTE-A networks seen as a challenge that can be met with SelfOrganizing Networks (SON) functionalities. The SON concepts have been included in the LTE (E-UTRAN) standards since the first release of the LTE technology. Self-optimization functionalities will monitor and analyze performance measurements, notifications, and self-test results and will automatically trigger re-configuration actions on the affected network nodes when necessary. The SON specifications have been built over the existing 3GPP network management architecture, the ultimate implementation of SON in 4G networks will bring many advantages. Successive SON procedures are waiting for their time and money to be implemented in 4G, though some essential issues for example of inter Radio Access Technology (RAT) interfaces must be overworked.

Self-Organizing Networks (SONs) are being researched extensively in the existing 3G and 4G landscape primarily to facilitate a convenient yet cost-effective approach in the configuration, optimization and troubleshooting of networks. However, the existing SONs will be no match for the operational complexity of the envisioned 5G networks. The promise of 5G revolves around the premise of infinite capacity and zero latency. 5G networks are set for commercial availability by 2020 and these networks will be part of a flexible and dynamic telecom ecosystem supporting cross-domain integration and multi-RAT environments. Network Densification, Network Function Virtualization, Flexible spectrum allocation, E2E security and Massive MTC are a few of the features promised by 5G networks. With this assortment of numerous technologies, it is obvious that SONs have to evolve beyond the existing reactive paradigm without which the maintenance and management of 5G networks would prove to be a herculean task. Hence, we propose a novel Proactive SON methodology based on the Big Data framework to enable the shift in the SON paradigm. In this article we present a comprehensive Big-Data based SON framework involving innovative Machine Learning techniques which would cater to scalability and programmability of 5G networks with respect to availability, reliability, speed, capacity, security and latency.

Dynamic Time Duplex Division (D-TDD) is a promising solution to accommodate the new emerging 5G and 6G services characterised by asymmetric and dynamic Uplink (UL) and Downlink (DL) traffic demands. D-TDD dynamically changes the TDD configuration of a cell without interrupting users' connectivity, hence balancing the bandwidth for UL or DL communication according to the traffic pattern. However, 3GPP standard does not specify algorithms or solutions to derive the TDD configuration, i.e., the number of slots to dedicate to UL and DL. In [1], we have proposed a Machine Learning (ML)-based solution relaying on Deep Reinforcement Learning (DRL) to allow the base station (or gNB) to self-adapt to the traffic pattern of the cell by periodically adapting the number of slots dedicated to UL and DL. In this work, we implemented the DRL algorithm on top of an open-source gNB based on OpenAirInterface (OAI) [2] to demonstrate its efficiency. To this end, we relied on the O-RAN architecture [3], where the proposed DRL algorithm is deployed as xApp at the Near Real-time RAN Intelligent Controller (RIC) and communicates with the base station using O-RAN E2 interface. We developed xTDD Service Model (SM) following the E2SM standard [3], allowing the DRL solution to monitor DL and UL buffers from the gNB to deduce the optimal TDD configuration that accommodates the current traffic. Then, the decision (i.e., TDD configuration) is pushed to the base station. We implemented the solution on top of the OAI 5G StandAlone (SA) platform and Flexric RIC [4]. To the best of our knowledge, this is the first demonstration of a ML-based D-TDD on top of a real 5G network, showing the advantage of O-RAN architecture to building Self Organized Network (SON) function for dynamic configuration of D-TDD.

Self-organizing wireless access networks rely on key configuration parameters that guarantee quality of operation. Poorly planned network access parameters, such as channel assignments or cell identifying codes, result in increased interference on system-critical control channels, network access failures, and poor quality of service. Therefore, the optimization of such network parameters is a vital task for self-organizing wireless networks. This paper considers Long-Term Evolution (LTE) systems and identifies a number of network parameter optimization problems encountered when designing self-organizing wireless access networks. A Mixed Integer Quadratic Program (MIQP) optimization model is proposed for each problem. The optimization of frequency channel assignments, Tracking Area Codes, Physical Cell Identifiers, and LTE coordination clusters is discussed and modeled in detail. Simulation results demonstrate significant network quality gains from optimizing network parameters using the proposed integer optimization models.

<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>

Automatic monitoring management for 5G mobile networks

In this paper we introduce a mathematical model in the framework of long term evolution (LTE) to solve the problem of coverage and capacity optimization by employing multi-level random Taguchi's Method. The optimization process runs in a centralized manner with no human intervention required and interacts with environment situation automatically. Under the mathematical model which combines coverage and capacity optimization by a coefficient factor, conventional Taguchi's Method transcends traditional trial-and-error approach in convergence speed and simple implementation, to offer even more search capacity, Gaussian shrink coefficient and random optimization offset are applied to the level-to-tilts mapping function. Antenna tilt is an effective interference reduction technique, which has been adopted as the tuning parameter. The simulation results turn out to be better than traditional Taguchi's Method and trial-and-error approach. The system model presented and evaluated also gives an insight to the mathematical model especially the trade-off between coverage and capacity in homogeneous scenario.

Fifth-generation (5G) networks are evolving from special purpose-built networks to software-defined, intelligent, multipurpose networks, enabling service innovation and autonomous network operation. In this article, we present an intelligent mobile edge network based on standardized 5G network function entities and New Radio (NR) radio access networks (RANs). We propose a multitier, self-organizing network (SON) with a middle-tier SON (mSON), centralized SON (cSON), and distributed SON (dSON) to support increasing network dynamicity for different verticals and to take advantage of the latest high-layer F1 interface. This is essential to support low-latency applications and ultrahigh-reliability services. It also enables more dynamically tight interworking of 5G NR and LTE with dual connectivity, expanding initial 5G NR coverage. We analyze a lower-layer RAN split to optimize fronthaul and so further improve radio efficiency by utilizing the multitier SON among various radio nodes as well as distributed units (DUs) and centralized units (CUs). This will facilitate massive multiple-input/multiple-output (MIMO) antenna systems and accelerate centralized and virtualized RAN deployments.

Optimal network configuration is one of the effective approaches for power loss reduction of the distribution network. This paper shows a network reconfiguration method using improved backtracking search algorithm (IBSA). Wherein, IBSA is improved in the process of generating randomly the initialization population. The network reconfiguration method based on IBSA is used to find the optimal network configuration for the 33-node and 69-node systems. The results are compared to the original backtracking search algorithm (BSA), particle swarm optimization (PSO), firefly algorithm (FA) and previous approaches. From the compared results, IBSA can determine the optimal network configuration with higher success rate than BSA, PSO, FA and lower power loss than other previous approaches. As a result, IBSA is an effective approach for finding the optimal network configuration.

The available 5G network is going to have various industrial applications. Mobile communication operators will be able more effectively to utilize their spectral assets, provide higher-speed data communication services, and increase network capacity. Traditional network parameters are manually set or adjusted by the network management system, so substantial room exists for improvement in operational speed. Self-organizing networks (SON) provide an automated means of simplifying operational tasks and improving operational efficiency. In future 5G networks, especially, in congested urban areas, difficulties of network management and load balancing will arise. The proposed novel SON management mechanism influences the overall network behavior by arranging the SON function parameters and adjusting the configuration of devices, user-equipment, and small cells. Simulation results indicate that implementing the proposed mechanism increases the throughput by an average of 4% and a maximum of 4.5%.

Best neighbor strategy to enforce cooperation among selfish nodes in wireless ad hoc network

5G wireless networks aim to achieve seamless mobile broadband services, machine to machine and ultra-reliable low latency communications. These goals require massive improvements in terms of capacity, reliability, latency reduction, and scalability. Besides software defined networks and network function virtualization, self organizing networks (SON) is another enabling technology which makes 5G feasible. Automatic neighbor relations (ANR) is a prominent component of SON which has direct impact on reliability, scalability, and capacity of the wireless networks. When the current state of standardization and implementation of ANR functionality is considered, it is seen that a new approach is needed for ANR to comply with 5G requirements. Thus, in this paper a comprehensive hybrid ANR (H-ANR) architecture which leads to the management of relations utilizing an extensive set of universal performance criteria, configuration metrics, and measurements is proposed. The H-ANR functionality ranks the neighbors not based on instantaneous information but on historic values of the performance criteria and other metrics. The attributes of distributed ANR (D-ANR) module is also managed by H-ANR to prevent the repetitive addition of unwanted neighbors via D-ANR or X2 interface. Performance of the proposed H-ANR functionality is also compared with the case when only D-ANR is available on a Long Term Evolution Advanced network.

By studying of image processing,character feature extraction and neural network including network type selection,network parameter optimization,training and adjustment,the handwritten character recognition method based on self-organizing network with double-X feature as input is proposed.First of all,the image is preprocessed including gray,binaryzation,tailoring and scaling.Second,the characters' double-X feature extraction method is utilized to extract feature information of various characters.Finally,the feature data of cha-racters is input into self-organizing network for learning and to determine the ideal network parameters after many tests,so that it can be self-organized to distinguish the character-mode.Experimental results show that this approach reduces the amount of data inputed to the network,and the interference of redundant information to network,and the complexity of network processing was considerably reduced.The network training error is small and the network misjudged rate is just about 12%.