network management game
Post on 11-Jan-2016
29 Views
Preview:
DESCRIPTION
TRANSCRIPT
University of Nevada, Reno
Network Management Game
Engin Arslan,Murat Yuksel,
Mehmet H. Gunes
LANMAN 2011 North Carolina
Outline
• Motivation
• Related Work
• Network Management Game (NMG) Framework
• User Experiments & Results
• Conclusion
Motivation
• High demand for multimedia applications
(VoIP, IPTV, teleconferencing, Youtube)
• ISPs have to meet customer demand
Service Level Agreement (SLA)
• Network management and automated configuration of large-
scale networks is a crucial issue for ISPs
• ISPs generally trust experienced administrators to manage
network and for better Traffic Engineering
Training Network Administrators
• Network administrator training is a long-term process
• Exposing inexperienced administrators to the network is too
risky
• Current practice to train is apprenticeship
Can we train the network administrators using a game-like environment rather than months of
years of apprenticeship?
Related Work
• Training by virtualized game-like environment
Pilot training
Investor training
Commander training
• Compeau et al. : End-user training and learningDeborah Compeau, Lorne Olfman, Maung Sei, and Jane Webster. 1995. End-user training and learning. Commun. ACM 38, 7
• Chatham et al. : Games for training Ralph E. Chatham. 2007. Games for training. Commun. ACM 50, 7 (July 2007), 36-43.
• Network administrator programs: Cisco Certification
Framework
1
Network Configuration
Simulation Engine(NS-2)
5
Calculate new routes
2 6
Traffic tracesGraphical User
Interface
3 7
Display traffic
Change link weight
4
Block diagram of Network Management Game (NMG) components.
Network Simulator (NS-2)
System Configuration Output
NS-2
• No real time interactivityRun simulation See the results
• Necessitates adequate level of TCL scripting• Not designed for training purpose
Simulator-GUI Interaction
• Concurrency is challengingRun the simulation engine for a time period then
animate in GUI before the engine continuesSlowdown animator – chose this approach
• GUI-Engine interaction is achieved via TCP portAnimator opens a socket to send simulation tracesGUI opens a socket to send commands
Sample Message: $ns $n1 $n2 2 set weight of link between n1 and n2 to 2
NMG Screenshot
User Goal
• Increase Overall Throughput by manipulating link weights within a given time period
A
B
E
C
1Mb/s1Mb/s
3Mb/s 3Mb/sD4Mb/s
1Mbps
3Mbps
User Experiments
We conducted 2 user experiments• Training without Mastery
No specific skills targeted No success level obligated
• Training with Mastery Two skills are targeted to train Success level obligated
Introduction| Related Work | NMG Framework | User Experiments| Conclusion
Training without Mastery
• 5 training scenarios• For every scenario, user has fixed 3-5 minutes
to maximize overall throughput• 8 users attended• Took around 45 minutes for each user• User performance evaluated for failure and no
failure cases
User Experiment
6 7 21 3 4 5 6’ 7’
Before Training Training After Training
Tutorial
No failure scenarios
Failure scenarios
No Failure CaseBeforeTraining (Mbps)
Ratio to Optimal (%)
After Training (Mbps)
Ratio to Optimal (%)
No Player 6 66.6 6 66.6
Genetic Algorithms - - 6.8 75.5
Random Recursive Search - - 8.5 94.4
Users (Average) 7.11 79 8.6 95.5
Optimal 9 100 9 100
After TrainingBefore Training
16% increase
P-test value :0.0002
Failure CaseBeforeTraining (Mbps)
Ratio to Optimal (%)
After Training (Mbps)
Ratio to Optimal (%)
No Player 4 30.7 5 38
Genetic Algorithms - - 7.9 60.7
Random Recursive Search - - 8 61.5
Users (Average) 9.73 74.8 10.01 77
Optimal 13 100 13 100
Before Training After Training
2.2% increase
Users outperform heuristic solutions
P-test value: 0.27
Training with Mastery
• Two skills are targetedHigh bandwidth path selectionDecoupling of flows
• 7 training scenarios 7 levels• Success level is obligated to advance next level• 5 users attended• Took 2-3 hours on average per user
Introduction| Related Work | NMG Framework | User Experiments| Conclusion
Training with Mastery
8 21 3 4 5 8’
Before Training Training After Training
Tutorial 76
Introduction| Related Work | NMG Framework | User Experiments| Conclusion
Results of Training with Mastery
Introduction| Related Work | NMG Framework | User Experiments| Conclusion
P-test value: 0.00001
Conclusion
• Performance of a person in network management can be improved via our tool16% improvement first user experiment13%- 21% improvement second user experiment
• People outperform heuristic algorithms in case of dynamism in network
• Targeting skills and designing specific scenarios for skills lead better training Success level of second user training
Introduction| Related Work | NMG Framework | User Experiments| Conclusion
Future Work
• Extend for large scale networks• Extend quantity and quality of test cases• Using different metrics in addition to throughput
such as delay or loss• Improve for investment based simulations (what-
if scenario)• Simulate multiple link failure (disastrous
scenario)
Thank you!
For offline questions: enginars@buffalo.edu
Related Work
• Ye et al. :Large-scale network parameter configuration using an on-line simulation frameworkTao Ye, Hema T. Kaur, Shivkumar Kalyanaraman, and Murat Yuksel. 2008. Large-scale network parameter configuration using an on-line simulation framework. IEEE/ACM Trans. Netw
• Gonen et al. :Trans-Algorithmic search for automated network management and configuration
B. Gonen, etal. Probabilistic Trans-Algorithmic search for automated network management and configuration. In IEEE International Workshop on Management of Emerging Networks and Services (IEEE MENS 2010
• Wang et al. :IGP weight setting in multimedia ip networks
R. D. D. Wang, G. Li, “Igp weight setting in multimedia ip networks,”in IEEE Infocom Mini’07, 2007.
top related