A study on machine learning and regression based models for - - PowerPoint PPT Presentation

Motivation Problem statement Simulation scenario Results of performance prediction Conclusions

A study on machine learning and regression based models for performance estimation of LTE HetNets

• B. Bojovi´

c1, E. Meshkova2, N. Baldo1,

• J. Riihijärvi2 and M. Petrova2

1Centre Tecnològic de Telecomunicacions de Catalunya (CTTC)

Castelldefels, Spain

2Institute for Networked Systems, RWTH Aachen University,

Aachen, Germany

ACROPOLIS 3rd Annual Workshop - London, 2013

Bojovi´ c, Meshkova, Baldo, Riihijärvi, Petrova Machine Learning and regression for performance estimation

Motivation Problem statement Simulation scenario Results of performance prediction Conclusions

Outline

1

Motivation Femtocell network deployments Inter-cell interference awareness Dynamic frequency allocation for LTE system

2

Problem statement LTE physical layer Proposed prediction methods and covariates

3

Simulation scenario

4

Results of performance prediction Issues in predicting performance Machine learning techniques for performance estimation

Bojovi´ c, Meshkova, Baldo, Riihijärvi, Petrova Machine Learning and regression for performance estimation

Motivation Problem statement Simulation scenario Results of performance prediction Conclusions Femtocell network deployments Inter-cell interference awareness Dynamic frequency allocation for LTE system

Femtocell network deployments

Goals and issues.

Recently, there was much interest in femtocells deployments for different network technologies. The most of attention was in shown for WCDMA technology in 3G network deployments The same concept could be applied also to more recent technologies such as WiMAX, LTE,.. The goal is to improve the performance of the mobile network by:

extending indoor coverage achieving higher data rate for the indoor and short range

• utdoor communications

The main challenge is how to manage the available spectrum resources

Bojovi´ c, Meshkova, Baldo, Riihijärvi, Petrova Machine Learning and regression for performance estimation

Motivation Problem statement Simulation scenario Results of performance prediction Conclusions Femtocell network deployments Inter-cell interference awareness Dynamic frequency allocation for LTE system

Femtocell network deployments.

Goals and issues.

One approach could be to divide the available spectrum into several frequency bands and then to assign to each femtocell a different one In previous case, the drawback are: low or no frequency reuse, not feasible for dense deployments and requires much maintenance Another approach, which is typically considered in recent technologies, is to share available frequency bands among femtocells In the previous case the main issue is the interference between femtocells, between femtocell and macro cells Consequence: the network performance degradation and unfairness among users

Bojovi´ c, Meshkova, Baldo, Riihijärvi, Petrova Machine Learning and regression for performance estimation

Motivation Problem statement Simulation scenario Results of performance prediction Conclusions Femtocell network deployments Inter-cell interference awareness Dynamic frequency allocation for LTE system

Inter-cell interference awareness

Previous work

Many studies have identified significant performance gains in the systems that are aware of the inter-cell interference Objective: to maximize the system performance and to provide fairness among users by minimizing the inter-cell interference Some of proposed techniques are based on: power control schemes, static and adaptive fractional frequency reuse schemes, cancellation techniques, intelligent scheduling, network power coordination,...

Bojovi´ c, Meshkova, Baldo, Riihijärvi, Petrova Machine Learning and regression for performance estimation

Motivation Problem statement Simulation scenario Results of performance prediction Conclusions Femtocell network deployments Inter-cell interference awareness Dynamic frequency allocation for LTE system

Dynamic frequency allocation for LTE system

Our approach

Our approach it to improve the system performance by enabling the dynamic frequency allocation We consider an LTE system, which is designed to be used with frequency reuse factor of 1 LTE technology includes advanced features such as OFDMA, SC-FDMA, AMC, dynamic MAC scheduling and HARQ,.. More difficult than in previous technologies to predict the system capacity for specified system configuration Our approach is to apply machine learning and regression analysis for system capacity estimation, that will enable efficient dynamic frequency allocation

Bojovi´ c, Meshkova, Baldo, Riihijärvi, Petrova Machine Learning and regression for performance estimation

Motivation Problem statement Simulation scenario Results of performance prediction Conclusions LTE physical layer Proposed prediction methods and covariates

LTE physical layer

Configurable network parameters

The OFDMA multicarrier technology provides flexible multiple-access scheme that allows different spectrum bandwidths to be utilized without changing the fundamental system parameters or equipment design In this work we consider:

1

the carrier frequency fc; and

2

he bandwidth B

In frequency domain resources are grouped in units of 12 subcarriers that are called resource blocks centered around fc and occupy 180 kHz in frequency domain

Bojovi´ c, Meshkova, Baldo, Riihijärvi, Petrova Machine Learning and regression for performance estimation

Motivation Problem statement Simulation scenario Results of performance prediction Conclusions LTE physical layer Proposed prediction methods and covariates

Configuring carrier frequency and bandwidth.

An example

The channel raster is 100 kHz for all bands LTE eNB operates using a set of B contiguous resource blocks(RB); the allowed values for B are 6, 15, 25, 50, 75, 100 RBs ( 1.4 , 3, 5, 10, 15, 20 MHz)

EARFCN

fc1

EARFCN

fc2

600kHz Femtocell 1 Femtocell 2 180kHz

fb1 - fo2

fo1 fb2 fo2 fb1

Bojovi´ c, Meshkova, Baldo, Riihijärvi, Petrova Machine Learning and regression for performance estimation

Motivation Problem statement Simulation scenario Results of performance prediction Conclusions LTE physical layer Proposed prediction methods and covariates

The optimization problem in broader context

The quality of the achieved performance depends on various factors: amount of available inputs, their usability in the context of particular models and optimization methods

Inputs Models & Decisions

Parameters & KPIs Topology Time granularity Spatial sampling Per user/femto reporting System information/dependencies Abstractions/simplifications Methods Online adaptation and/or training Required parameteres and prior info Complexity Training time Robustness Reusability Accuracy Optimality

Performance

Propagation losses, MAC and application layer throughput 2-4 node topology Schedulers Coloring, Graph abstraction, SINR, and MAC throughput estimation Regression analysis (several forms) Genetic algorithms Derived system dependencies (PHY - MAC(incl. schedulers) - Application)

• Num. of samples for training

Prediction accuracy Comments on computation effords Per network/femto/user predictions General criteria Criteria specifically discussed in our work

Bojovi´ c, Meshkova, Baldo, Riihijärvi, Petrova Machine Learning and regression for performance estimation

Motivation Problem statement Simulation scenario Results of performance prediction Conclusions LTE physical layer Proposed prediction methods and covariates

The specific optimization problem

An example

The specific problem that we are solving is: select for each for each deployed eNB i = 1, ..., N , the frequency fc and the system bandwidth B that will provide the best network performance. In this work we consider capacity as performance metric (we are interested to consider delay, fairness, different QoS metrics) Another aspect to consider is the number of possible solutions, which is exponential with N An example for 4 femtocell scenario, total available bandwidth of 5 MHz, fc muliple of 300 kHz and B that can take value 6,15,25 there are 4625 physically distinct solutions

Bojovi´ c, Meshkova, Baldo, Riihijärvi, Petrova Machine Learning and regression for performance estimation

Motivation Problem statement Simulation scenario Results of performance prediction Conclusions LTE physical layer Proposed prediction methods and covariates

LTE femtocell capacity estimation

design the cost function

Common approach is to use some variation of Shannon formula, but those approaches typically do not consider effects of AMC, MAC scheduling,.. The TB size for each given AMC scheme and number of RBs is defined by the LTE specification We consider effect of different schedulers and for that purpose we use Round Robin and Proportional Fair

−10 −5 5 10 15 20 25 30 500 1000 1500

SINR Capacity in bits/RB

LTE Shannon mod.Shannon

Bojovi´ c, Meshkova, Baldo, Riihijärvi, Petrova Machine Learning and regression for performance estimation

Motivation Problem statement Simulation scenario Results of performance prediction Conclusions LTE physical layer Proposed prediction methods and covariates

prediction methods and covariates

Our goal is to predict the performance of the femtocell accurately by using regression analysis and machine learning techniques The information used: basic pathloss and configuration information, a limited number of feedback measurements that provide the throughput and the delay metrics for a particular frequency settings Different regressors: SINR, SINR/MAC throughput mapping and different sampling technique affects the prediction performance The performance metrics considered are: network-wide and per-user throughput The methods considered: Bagging tree, Boosted tree, Kohonen network, SVM radial, K-nearest neighbor, Projection pursuit regression, Linear

Bojovi´ c, Meshkova, Baldo, Riihijärvi, Petrova Machine Learning and regression for performance estimation

Motivation Problem statement Simulation scenario Results of performance prediction Conclusions

Simulation scenario.

To simulate this scenario we use LENA, LTE-EPC network simulator We choose a typical LTE urban scenario with buildings (in LTE literature known as dual stripe scenario) The HeNbs are randomly distributed in the buildings and each HeNb has equal number of users For the four femtocell scenarios we simulate:

1

three users per node allocation with the total of 2 MHz bandwidth, and

2

two users per node allocation with the total of 5 MHz bandwidth

Bojovi´ c, Meshkova, Baldo, Riihijärvi, Petrova Machine Learning and regression for performance estimation

Motivation Problem statement Simulation scenario Results of performance prediction Conclusions

Dual-stripe scenario

Radio environmental map in a scenario with 2 buildings and 2 HeNbs

200 220 240 260 280 300 220 240 260 280 300 320 340 y-coordinate [m] x-coordinate [m]

• 5

5 10 15 20 SINR [dB]

Bojovi´ c, Meshkova, Baldo, Riihijärvi, Petrova Machine Learning and regression for performance estimation

Motivation Problem statement Simulation scenario Results of performance prediction Conclusions Issues in predicting performance Machine learning techniques for performance estimation

Issues in predicting performance

Scenario 1

Scenario with 4 femtocells and 3 users each femto, using 2 MHz overall bandwidth, showing actual measured MAC throughput vs. Shannon models. Sum SINR means a sum

• ver all RBs

Even if correlations between the different SINR related metrics and the achieved throughputs are apparent, the dispersion of the results is rather substantial

Bojovi´ c, Meshkova, Baldo, Riihijärvi, Petrova Machine Learning and regression for performance estimation

Motivation Problem statement Simulation scenario Results of performance prediction Conclusions Issues in predicting performance Machine learning techniques for performance estimation

Issues in predicting performance

Scenario 1

1000 1200 1400 1600 Sum SINR [dB] MAC Throughput [Mbps] 6.0 7.0 7.5 8.5 Sum SINR/THR NS3 Mapping [Mbps] MAC Throughput [Mbps] MAC Throughput [Mbps] 120 240 360 480 100 150 200 250 300 MAC Throughput [kbps] 600 720 840 960 1080 1200 600 800 1000 1200 1400 MAC Throughput [kbps] (c) Measured MAC thoughput for two selected users vs. SINR/MAC THR mapping for a scenario with 4 femtos 3 users each, Proportional Fair (left) and Round Robin schedulers (right) for TCP traffic. 6.0 7.0 8.0 9.0 MAC Throughput [Mbps] (b) Measured MAC throughput vs. min SINR (left) and SINR/MAC thoughput mapping (right) for a scenario with 4 femtos with 3 users each, Round Robin scheduler, and TCP traffic. (a) Measured MAC throughput vs. min SINR (left) and SINR/MAC thoughput mapping (right) for a scenario with 4 femtos with 3 users each, Proportional Fair scheduler, and TCP traffic. Sum SINR/THR NS3 Mapping [Mbps] Sum SINR/THR NS3 Mapping [kbps] Sum SINR/THR NS3 Mapping [kbps] 6.5 8.0 6.0 7.0 8.0 9.0 6.0 7.0 7.5 8.5 5.5 6.0 7.0 7.5 6.5 8.0 6.5 5.5 6.0 7.0 7.5 6.5 Sum SINR [dB] 1000 1200 1400 1600

Bojovi´ c, Meshkova, Baldo, Riihijärvi, Petrova Machine Learning and regression for performance estimation

Motivation Problem statement Simulation scenario Results of performance prediction Conclusions Issues in predicting performance Machine learning techniques for performance estimation

Issues in predicting performance

Scenario 2

Scenarios with 2 femtocells and 5 users each and 4 femtocells with 2 users each, using a bandwidth of 5 MHz. Different behavior is noted for UDP and TCP traffic, and for different schedulers From these results we can expect effective performance prediction to be a challenging problem especially for TCP traffic and a small number of users per femtocell.

Bojovi´ c, Meshkova, Baldo, Riihijärvi, Petrova Machine Learning and regression for performance estimation

Motivation Problem statement Simulation scenario Results of performance prediction Conclusions Issues in predicting performance Machine learning techniques for performance estimation

Issues in predicting performance

Scenario 2

6.0 8.0 10.0 MAC Throughput [Mbps] 6.0 8.0 10.0 MAC Throughput [Mpbs] 5 10 15 20 4.0 Min SINR per RB [dB] 4.0 Sum SINR to MAC Throughput Mapping [Mbps] (a) Measured MAC throughput vs. min SINR (left) and SINR/MAC thoughput mapping (right) for a scenario with 4 femtos with 2 users each, Proportional Fair scheduler, and TCP traffic. 10.0 15.0 20.0 25.0 Sum SINR to MAC Throughput Mapping [Mbps] MAC Throughput [Mpbs] 5 10 15 20 Min SINR per RB [dB] 10.0 15.0 20.0 25.0 MAC Throughput [Mpbs] 0.8 1.2 1.6 2.0 2.4 2.0 3.0 4.0 5.0 2.0 3.0 4.0 5.0 4.0 6.0 8.0 10.0 Sum SINR to MAC Throughput Mapping [Mbps] Sum SINR to MAC Throughput Mapping [Mbps] MAC Throughput [Mpbs] MAC Throughput [Mpbs] (b) Measured MAC throughput vs. min SINR (left) and SINR/MAC thoughput mapping (right) for a scenario with 4 femtos with 2 users each, Proportional Fair scheduler, and UDP traffic. (c) Measured MAC throughput vs. SINR/MAC thoughput mapping for a selected femtocell (left) and a whole network (right) for a scenario with 2 femtos with 10 users each, Round Robin scheduler, and UDP traffic. 4.0 8.0 12.0 16.0 20.0 4.0 8.0 12.0 16.0 20.0

Bojovi´ c, Meshkova, Baldo, Riihijärvi, Petrova Machine Learning and regression for performance estimation

Motivation Problem statement Simulation scenario Results of performance prediction Conclusions Issues in predicting performance Machine learning techniques for performance estimation

Pursuit regression technique

Scenario with 4 femtocell and 3 users per each femto and bandwidth of 2MHz Random sampling with 10% of 337 permutations being explored The regression technique is applied The earlier expectation that UDP traffic with more primitive scheduler results in higher predictability is confirmed, the users the predictions are very accurate

Bojovi´ c, Meshkova, Baldo, Riihijärvi, Petrova Machine Learning and regression for performance estimation

Motivation Problem statement Simulation scenario Results of performance prediction Conclusions Issues in predicting performance Machine learning techniques for performance estimation

Pursuit regression technique

Figure

50 100 150 200 250 300 350 0.5 1.5 Throughput [Mbps] 1.0 Permutation (a) Measured and predicted MAC throughput for a selected user with permutations ordered after measured throughput for the scenario with TCP traffic, and proportional fair scheduler. Measured Predicted (c) Achieved performance ratio (predicted vs. measured MAC throughput) for the scenario with UDP traffic, and round robin scheduler. 1 2 3 4 5 6 7 8 9 10 11 12 0.4 0.6 0.8 1.0 User ID Achieved performance ratio 1 2 3 4 5 6 7 8 9 10 11 12 0.4 0.6 0.8 1.0 User ID Achieved performance ratio (b) Achieved performance ratio (predicted vs. measured MAC throughput) for the scenario with TCP traffic, and proportional fair scheduler.

Bojovi´ c, Meshkova, Baldo, Riihijärvi, Petrova Machine Learning and regression for performance estimation

Motivation Problem statement Simulation scenario Results of performance prediction Conclusions Issues in predicting performance Machine learning techniques for performance estimation

A simple linear regression model

Scenario with 4 femtocell scenario and 3 users per femto and bandwidth of 2 MHz TCP traffic and proportional fair scheduler This method results in poorer prediction average both in terms of median error, as well as the variability of the results The increased amount of information available for the predictor results in both improved median prediction performance, as well as substantial reduction in the magnitude of the outliers

Bojovi´ c, Meshkova, Baldo, Riihijärvi, Petrova Machine Learning and regression for performance estimation

Motivation Problem statement Simulation scenario Results of performance prediction Conclusions Issues in predicting performance Machine learning techniques for performance estimation

A simple linear regression model

Figure

(c) Achieved performance ratio for the linear regression method with 10% of samples and the stratified sampler. 1 2 3 4 5 6 7 8 9 10 11 12 0.4 0.6 0.8 1.0 User ID Achieved performance ratio 1 2 3 4 5 6 7 8 9 10 11 12 0.2 0.4 0.6 0.8 1.0 User ID Achieved performance ratio (c) Achieved performance ratio for the PPR regression method with 70% of samples and the stratified sampler. 1 2 3 4 5 6 7 8 9 10 11 12 0.6 0.7 0.8 0.9 1.0 (c) Achieved performance ratio for the Kohonen regression method with 10% of samples and the random sampler. User ID Achieved performance ratio

Bojovi´ c, Meshkova, Baldo, Riihijärvi, Petrova Machine Learning and regression for performance estimation

Motivation Problem statement Simulation scenario Results of performance prediction Conclusions

Conclusions

The initial results obtained here show that advanced regression techniques can result in good performance predictions In future work we plan to investigate an active sampling based on graph coloring

Bojovi´ c, Meshkova, Baldo, Riihijärvi, Petrova Machine Learning and regression for performance estimation