In this paper, we provide an analysis of selforganized network management, with an end-to-end perspective of the network. Self-organization as applied to cellular networks is usually referred to Self-organizing Networks (SONs), and it is a key driver for improving Operations, Administration, and Maintenance (OAM) activities. SON aims at reducing the cost of installation and management of 4G and future 5G networks, by simplifying operational tasks through the capability to configure, optimize and heal itself. To satisfy 5G network management requirements, this autonomous management vision has to be extended to the end to end network. In literature and also in some instances of products available in the market, Machine Learning (ML) has been identified as the key tool to implement autonomous adaptability and take advantage of experience when making decisions. In this paper, we survey how network management can significantly benefit from ML solutions. We review and provide the basic concepts and taxonomy for SON, network management and ML. We analyse the available state of the art in the literature, standardization, and in the market. We pay special attention to 3rd Generation Partnership Project (3GPP) evolution in the area of network management and to the data that can be extracted from 3GPP networks, in order to gain knowledge and experience in how the network is working, and improve network performance in a proactive way. Finally, we go through the main challenges associated with this line of research, in both 4G and in what 5G is getting designed, while identifying new directions for research.

Abstract-In this paper, we present a novel cell outage management (COM) framework for heterogeneous networks (HetNets) with split control and data planes -a candidate architecture for meeting future capacity, quality of service and energy efficiency demands. In such architecture, the control and data functionalities are not necessarily handled by the same node. The control base stations (BSs) manage the transmission of control information and user equipment (UE) mobility, while the data BSs handle UE data. An implication of this split architecture is that, an outage to a BS in one plane has to be compensated by other BSs in the same plane. Our COM framework addresses this challenge by incorporating two distinct cell outage detection (COD) algorithms to cope with the idiosyncrasies of both the data and control planes. The COD algorithm for control cells leverages the relatively larger number of UEs in the control cell to gather large scale minimize drive testing (MDT) reports data, and detects outage by applying machine learning and anomaly detection techniques. To improve outage detection accuracy, we also investigate and compare the performance of two anomaly detecting algorithms, i.e. k− nearest neighbor and local outlier factor based anomaly detector, within the control COD. On the other hand, for data cells COD, we propose a heuristic grey-prediction based approach, which can work with the small number of UEs in the data cell, by exploiting the fact that the control BS manages UE-data BS connectivity, by receiving a periodic update of the received signal reference power (RSRP) statistic between the UEs and data BSs in its coverage. The detection accuracy of the heuristic data COD algorithm is further improved by exploiting the Fourier series of residual error that is inherent to grey prediction model. Our COM framework integrates these two COD algorithms with a cell outage compensation (COC) algorithm which can be applied to both planes. Our COC solution utilizes an actor critic (AC) based reinforcement learning (RL) algorithm, which optimizes the capacity and coverage of the identified outage zone in a plane, by adjusting the antenna gain and transmission power of the surrounding BSs in that plane. The simulation results show that the proposed framework can detect both data and control cell outage, and also compensate for the detected outage in a reliable manner.

In this paper we present an automatic and selforganized Reinforcement Learning (RL) based approach for Cell Outage Compensation (COC). We propose that a COC module is implemented in a distributed manner in the Enhanced Node Base station (eNB)s in the scenario and intervenes when a fault is detected and so the associated outage. The eNBs surrounding the outage zone automatically and continually adjust their downlink transmission power levels and find the optimal antenna tilt value, in order to fill the coverage and capacity gap. With the objective of controlling the intercell interference generated at the borders of the extended cells, a modified Fractional Frequency Reuse (FFR) scheme is proposed for scheduling. Among the RL methods, we select a Temporal Difference (TD) learning approach, the Actor Critic (AC), for its capability of continuously interacting with the complex wireless cellular scenario and learning from experience. Results, validated on a Release 10 Long Term Evolution (LTE) system level simulator, demonstrate that our approach outperforms state of the art resource allocation schemes in terms of number of users recovered from outage.

Planning future mobile networks entails multiple challenges due to the high complexity of the network to be managed. Beyond 4G and 5G networks are expected to be characterized by a high densification of nodes and heterogeneity of layers, applications, and Radio Access Technologies (RAT). In this context, a network planning tool capable of dealing with this complexity is highly convenient. The objective is to exploit the information produced by and already available in the network to properly deploy, configure, and optimise network nodes. This work presents such a smart network planning tool that exploits Machine Learning (ML) techniques. The proposed approach is able to predict the Quality of Service (QoS) experienced by the users based on the measurement history of the network. We select Physical Resource Block (PRB) per Megabit (Mb) as our main QoS indicator to optimise, since minimizing this metric allows offering the same service to users by consuming less resources, so, being more cost-effective. Two cases of study are considered in order to evaluate the performance of the proposed scheme, one to smartly plan the small cell deployment in a dense indoor scenario and a second one to timely face a detected fault in a macrocell network.

This paper aims to find patterns of knowledge from physical layer data coming from Heterogeneous Long Term Evolution (LTE) networks. We discuss how the collected data is employed in such a manner that improves Minimization of Drive Tests (MDT) functionality in LTE networks. In particular we aim to predict Quality of Service (QoS) expressed in terms of throughput of the User Datagram Protocol (UDP) traffic flow. We propose regression models to estimate QoS, by extrapolating information independently of the user's physical location. In particular our approach allows to estimate the QoS in any location, based on measurements collected at anytime in the past, or anywhere in the network. This will allow to significantly reduce costs of future network deployments, even in complex and heterogeneous scenarios, such as those foreseen in stadiums, events, etc. We identify three feasible regression models, and we compare results in terms of prediction accuracy.