Master Thesis - Anomaly Detection in evolved NodeB

Job description

Ericsson Overview

Ericsson is a world-leading provider of telecommunications equipment & services to mobile & fixed network operators. Over 1,000 networks in more than 180 countries use Ericsson equipment, & more than 40 percent of the world's mobile traffic passes through Ericsson networks. Using innovation to empower people, business & society, we are working towards the Networked Society, in which everything that can benefit from a connection will have one. At Ericsson, we apply our innovation to market-based solutions that empower people & society to help shape a more sustainable world.

We are truly a global company, working across borders in 175 countries, offering a diverse, performance-driven culture & an innovative & engaging environment where employees enhance their potential everyday. Our employees live our vision & core values. They share a passion to win & a high responsiveness to customer needs that in turn makes us a desirable partner to our clients. To ensure professional growth, Ericsson offers a stimulating work experience, continuous learning & growth opportunities that allow you to acquire the knowledge & skills necessary to reach your career goals.

We welcome the opportunity to meet you!

Background

The NodeB (eNB) in the LTE RAN administrates and controls radio resources and mobile equipment within a 4G network, and handles radio communications towards user equipment. As understood, an eNB controls very valuable resources, and therefore it is expected that these resources are used in most optimal way. Identifying problems in a RAN, and/or in a complex node such eNB, is complex and may be costly in terms of man-hours. There are also situations that the abnormal behavior is not easy to discover / observe.During operation, eNB generates, continuously, large amount of data and logs. The large amounts of data from many different eNBs contain valuable information, ranging from traffic and operational state to node's internal/external events. Monitoring the node's operation and learning its behavior makes it possible to identify current, as well as, coming issues and bottlenecks. Machine learning (ML) algorithms provides efficient tools for these types of analysis.

Thesis Description

The assignment is to compare, decide and implement ML algorithms that analyze nodes' data in order to conclude possible divergence from a normal behavior (anomaly detection), and also help to narrow down the scope of potential area of problems. This, in turn, means that the algorithm/program needs to learn (or to be learned) and be improved continuously based on data from different nodes and different software releases.Identifying trends and finding correlations among different parameters/events is considered as the preparation steps towards the implementation of the learning process. The study shall suggest and implement principles for identification of normal and abnormal behavior in the node, and compare the results. The main scope is RAN and eNB.

Qualifications

The project is aimed at students with mathematical background and/or computer science or similar discipline.

·  Good knowledge in statistical methods, Machine Learning and data mining
·  Good knowledge of databases (SQL, Hadoop)
·  Programming skills (Python, SCALA, R, SQL)
·  Basic knowledge about Radio Networks and Mobile Communication (optional)

Ericsson provides equal employment opportunities (EEO) to all employees and applicants for employment without regard to race, color, religion, sex, sexual orientation, marital status, pregnancy, parental status, national origin, ethnic background, age, disability, political opinion, social status, veteran status, union membership or genetics.

Ericsson complies with applicable country, state and all local laws governing nondiscrimination in employment in every location across the world in which the company has facilities. In addition, Ericsson supports the UN Guiding Principles for Business and Human Rights and the United Nations Global Compact.

This policy applies to all terms and conditions of employment, including recruiting, hiring, placement, promotion, termination, layoff, recall, transfer, leaves of absence, compensation, training and development.

Ericsson expressly prohibits any form of workplace harassment based on race, color, religion, sex, sexual orientation, marital status, pregnancy, parental status, national origin, ethnic background, age, disability, political opinion, social status, veteran status, union membership or genetic information.

Primary country and city: Sweden (SE) || || Stockholm || Stud&YP

Req ID: 194186