Unsupervised Learning of Traffic Patterns in Self-Optimizing 4 Generation Mobile Networks

ثبت نشده
چکیده

Reverb Networks has developed a system that enables Self Optimizing Networks (SON). The system aims to maximize network performance by changing the tilts of antennas to shift load between them. SON can significantly reduce the need for labor intensive manual network optimization. Changes are currently applied with the assumption that the same tilt value will be valid at all times of the day. This project investigates whether the existing solution can be modified, with little effort, to find appropriate times to apply different tilts, using Artificial Intelligence and Machine Learning techniques, to possibly achieve a more optimal outcome. The given solution groups (clusters) segments in time using unsupervised learning. In addition, nearby cells (a cell is an area that has one or more antennas serving it) are grouped (clustered) to form zones with similar time segments. These individual time segments are then optimized by separate instances of the existing solution. The learning algorithms are evaluated with a dataset that contains information from 195 cells, which has been collected from a live network over the course of one month. The results show that several time segments can be identified for most cells. In many cases, these time segments are different in length, start time, and end time. A prototype is presented, which shows that it is possible to integrate the suggested approach with the existing solution and that the necessary changes are not extensive. While it is not yet possible to show that the proposed solution surely leads to a more optimized network (this will require testing in a live network or extensive network simulation), the fact that multiple time segments could be identified for most cells is encouraging. And it does seem reasonable to expect that more frequent changes will provide gains in network performance. Oövervakad inlärning av trafikmönster i självoptimerande fjärde generationens mobila nätverk Sammanfattning Reverb Networks har utvecklat ett system som möjliggör självoptimerande nätverk (s.k. SON). Systemet syftar till att maximera nätverkets prestanda genom att ändra på antenners lutning. Närliggande antenner som lutas kan på så sätt avlasta varandra. SON kan till stor del minska behovet för kostsam manuell optimering av nätverket. Ändringar görs i nuläget med antagandet att de är giltiga för alla tidpunkter. Det här exjobbet undersöker om den existerande produkten kan modifieras, utan att det krävs alltför mycket arbete, till att hitta lämpliga tidpunkter då olika lutningsvärden bör appliceras, genom tillämpning av artificiell intelligens och maskininlärning. Lösningen som läggs fram grupperar (klustrar) segment i tid med hjälp av oövervakad inlärning. Närliggande celler (en cell är ett område som betjänas av en eller flera antenner) grupperas (klustras) också till zoner som har liknande tidssegment. Segmenten optimeras sedan var för sig av instanser, som är oberoende av varandra, av den existerande lösningen. Inlärningsalgoritmerna utvärderas med data som samlats ihop från ett riktigt nätverk. Datat innehåller information från 195 celler som samlats ihop under en månad. Resultatet visar att flera tidssegment kan identifieras för flertalet av cellerna i datat. I många av fallen är de funna segmenten olika när det gäller längd, starttid och sluttid. En prototyp presenteras, som visar möjligheten att integrera inlärningsalgoritmerna med den existerande produkten, och att de kan ske utan alltför stora ändringar. Fast det ännu inte är säkert att den föreslagna lösningen leder till ett mer optimalt nätverk (detta kommer att kräva testning i ett riktigt nätverk eller nätverkssimulering), så är det ett framsteg att det gick att hitta tidssegment för de flesta cellerna. Det verkar rimligt att vänta sig att mer frekventa uppdateringar kommer att leda till bättre prestanda.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

ADAPTIVE ORDERED WEIGHTED AVERAGING FOR ANOMALY DETECTION IN CLUSTER-BASED MOBILE AD HOC NETWORKS

In this paper, an anomaly detection method in cluster-based mobile ad hoc networks with ad hoc on demand distance vector (AODV) routing protocol is proposed. In the method, the required features for describing the normal behavior of AODV are defined via step by step analysis of AODV and independent of any attack. In order to learn the normal behavior of AODV, a fuzzy averaging method is used fo...

متن کامل

Securing AODV routing protocol against the black hole attack using Firefly algorithm

Mobile ad hoc networks are networks composed of wireless devices to create a network with the ability for self-organization. These networks are designed as a new generation of computer networks to satisfy some specific requirements and with features different from wired networks. These networks have no fixed communication infrastructure and for communication with other nodes the intermediate no...

متن کامل

Exploring the Potential of a Mobile Messaging Application for Self-Initiated Language Learning

With the rapid expansion of deploying mobile instant messaging applications such as Telegram for the purpose of language learning, it is quite apparent that language research in this regard is lagging behind the trend. This study addressed the matter by exploring how language learners utilize a Telegram group for the purpose of language learning. In this regard, the activities of a Telegram lan...

متن کامل

Pattern Recognition and Learning Based Self Optimizing Networks

Self Optimizing Networks (SON) are becoming increasingly relevant as demand for wireless capacity increases and mobile networks get more complex with a large number of parameters and attributes needing to be optimized. These SON processes work in an autonomous, closed-loop mode – continuously monitoring the network through measurements made by the infrastructure and user equipment (UE), identif...

متن کامل

Analyzing TCP Traffic Patterns Using Self Organizing Maps

The continuous evolution of the attacks against computer networks has given renewed strength to research on anomaly based Intrusion Detection Systems, capable of automatically detecting anomalous deviations in the behavior of a computer system. While data mining and learning techniques have been successfully applied in host-based intrusion detection, network-based applications are more difficul...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2012