L-3 PROPRIETARY 1 Real-time IO-oriented Soar Agent for Base Station-Mobile Control David Daniel, Scott Hastings L-3 Communications.

Slides:



Advertisements
Similar presentations
SCO 3 Crewing Optimization As-Is Processes January 9, 2006
Advertisements

Prashant Bajpayee Advisor: Dr. Daniel Noneaker SURE 2005 Motivation Currently most radio-frequency spectrum is assigned exclusively to “primary” users.
Maximum Battery Life Routing to Support Ubiquitous Mobile Computing in Wireless Ad Hoc Networks By C. K. Toh.
Ethernet over VDSL Technical Specifications. Agenda –Rate – Reach –Band Allocation –SNR and BER –PSD mask and Power Backoff Algorithm –Rate Limitation.
Topology Control of Multihop Wireless Networks Using Transmit Power Adjustment Paper By : Ram Ramanathan, Regina Resales-Hain Instructor : Dr Yingshu Li.
1 ENERGY: THE ROOT OF ALL PERVASIVENESS Anthony Ephremides University of Maryland April 29, 2004.
1/24 Passive Interference Measurement in Wireless Sensor Networks Shucheng Liu 1,2, Guoliang Xing 3, Hongwei Zhang 4, Jianping Wang 2, Jun Huang 3, Mo.
Chapter 2 The Cellular Concept
Wireless Mesh Networks 1. Architecture 2 Wireless Mesh Network A wireless mesh network (WMN) is a multi-hop wireless network that consists of mesh clients.
Differentiated Surveillance for Sensor Networks Ting Yan, Tian He, John A. Stankovic CS294-1 Jonathan Hui November 20, 2003.
Prénom Nom Document Analysis: Artificial Neural Networks Prof. Rolf Ingold, University of Fribourg Master course, spring semester 2008.
1 Chunking with Confidence John Laird University of Michigan June 17, th Soar Workshop
Self-Management in Chaotic Wireless Deployments A. Akella, G. Judd, S. Seshan, P. Steenkiste Presentation by: Zhichun Li.
On the Construction of Energy- Efficient Broadcast Tree with Hitch-hiking in Wireless Networks Source: 2004 International Performance Computing and Communications.
Impact of Working Memory Activation on Agent Design John Laird, University of Michigan 1.
Prénom Nom Document Analysis: Artificial Neural Networks Prof. Rolf Ingold, University of Fribourg Master course, spring semester 2008.
Incorporating Advice into Agents that Learn from Reinforcement Presented by Alp Sardağ.
Digital Voice Communication Link EE 413 – TEAM 2 April 21 st, 2005.
CS541 Advanced Networking 1 Cognitive Radio Networks Neil Tang 1/28/2009.
Polyscheme John Laird February 21, Major Observations Polyscheme is a FRAMEWORK not an architecture – Explicitly does not commit to specific primitives.
Soar-RL: Reinforcement Learning and Soar Shelley Nason.
Mobility Increases The Capacity of Ad-hoc Wireless Networks By Grossglauser and Tse Gautam Pohare Heli Mehta Computer Science University of Southern California.
Impact of Problem Centralization on Distributed Constraint Optimization Algorithms John P. Davin and Pragnesh Jay Modi Carnegie Mellon University School.
Business Analytics, Part I Introduction Presented by Scott Koegler Editor, ec-bp.org.
Adaptations to Resistance Training. Key Points Eccentric muscle action adds to the total work of a resistance exercise repetition.
CS Reinforcement Learning1 Reinforcement Learning Variation on Supervised Learning Exact target outputs are not given Some variation of reward is.
For 3-G Systems Tara Larzelere EE 497A Semester Project.
Special Topics on Algorithmic Aspects of Wireless Networking Donghyun (David) Kim Department of Mathematics and Computer Science North Carolina Central.
Capacity of Wireless Mesh Networks: Comparing Single- Radio, Dual-Radio, and Multi- Radio Networks By: Alan Applegate.
MAXIMIZING SPECTRUM UTILIZATION OF COGNITIVE RADIO NETWORKS USING CHANNEL ALLOCATION AND POWER CONTROL Anh Tuan Hoang and Ying-Chang Liang Vehicular Technology.
An algorithm for dynamic spectrum allocation in shadowing environment and with communication constraints Konstantinos Koufos Helsinki University of Technology.
1 Techniques to control noise and fading l Noise and fading are the primary sources of distortion in communication channels l Techniques to reduce noise.
When rate of interferer’s codebook small Does not place burden for destination to decode interference When rate of interferer’s codebook large Treating.
A Multi-Domain Evaluation of Scaling in Soar’s Episodic Memory Nate Derbinsky, Justin Li, John E. Laird University of Michigan.
Selecting Transmit Powers and Carrier Sense Thresholds in CSMA Jason Fuemmeler, Nitin Vaidya, Venugopal Veeravalli ECE Department & Coordinated Science.
ARES: an Anti-jamming REinforcement System for Networks Konstantinos Pelechrinis, Ioannis Broustis, Srikanth V. Krishnamurthy, Christos Gkantsidis.
New SVS Implementation Joseph Xu Soar Workshop 31 June 2011.
Limited Contribution of Self-Management in Chaotic Wireless Deployments Presented by Karl Deng.
ANTs PI Meeting, Nov. 29, 2000W. Zhang, Washington University1 Flexible Methods for Multi-agent distributed resource Allocation by Exploiting Phase Transitions.
Lecture 5: Cellular networks Anders Västberg Slides are a selection from the slides from chapter 10 from:
EPL 476 Fundamental Concepts in Wireless Networks
Cellular Networks Why use cellular networks? What mobile radio services where provided before cellular? Use multiple low-power transmitters (100 W or less),
1 Quality of Service  Quality of Service  Dropped connections  Unavailable websites  Network outages & Delays  Goal is to reduce user frustration.
Cognitive Radio Networks
Copyright: S.Krishnamurthy, UCR Power Controlled Medium Access Control in Wireless Networks – The story continues.
Integrating Background Knowledge and Reinforcement Learning for Action Selection John E. Laird Nate Derbinsky Miller Tinkerhess.
On Distinguishing the Multiple Radio Paths in RSS-based Ranging Dian Zhang, Yunhuai Liu, Xiaonan Guo, Min Gao and Lionel M. Ni College of Software, Shenzhen.
Reinforcement Learning 主講人:虞台文 Content Introduction Main Elements Markov Decision Process (MDP) Value Functions.
17/9/2009 Nakato Ruth Chapter one Introduction and review of strategic management.
COSMOSMotion Slides.
Scalable Video Coding and Transport Over Broad-band wireless networks Authors: D. Wu, Y. Hou, and Y.-Q. Zhang Source: Proceedings of the IEEE, Volume:
Computer Architecture Lecture 32 Fasih ur Rehman.
Multiuser Receiver Aware Multicast in CDMA-based Multihop Wireless Ad-hoc Networks Parmesh Ramanathan Department of ECE University of Wisconsin-Madison.
Dynamic Data Rate and Transmit Power Adjustment in IEEE Wireless LANs Pierre Chevillat, Jens Jelitto, and Hong Linh Truong IBM Zurich Research Laboratory.
Evaluating Wireless Network Performance David P. Daugherty ITEC 650 Radford University March 23, 2006.
By: David Gelbendorf, Hila Ben-Moshe Supervisor : Alon Zvirin
Beyond Chunking: Learning in Soar March 22, 2003 John E. Laird Shelley Nason, Andrew Nuxoll and a cast of many others University of Michigan.
Autonomous Mission Management of Unmanned Vehicles using Soar Scott Hanford Penn State Applied Research Lab Distribution A Approved for Public Release;
Presentation By SANJOG BHATTA Student ID : July 28’ 2009.
Modeling Primitive Skill Elements in Soar
Knowledge Representation and Reasoning
Techniques to control noise and fading
R SE to the challenges of ntelligent systems
Data Collection and Dissemination
Knowledge Representation and Reasoning
John E. Laird 32nd Soar Workshop
Cognitive Radio Networks
Support for Deferral Management in v
Spectrum Sharing in Cognitive Radio Networks
Parallel Programming in C with MPI and OpenMP
Presentation transcript:

L-3 PROPRIETARY 1 Real-time IO-oriented Soar Agent for Base Station-Mobile Control David Daniel, Scott Hastings L-3 Communications

L-3 PROPRIETARY 2 Illustrative Concept Communications Link Lowering transmitter power lowers power consumption Lower power consumption = longer battery life Lowering transmitter power lowers maximum data rate the link can support Need to adjust power and rate jointly until both are optimized for app A means to optimize transmission power and data rate of a communications link between a power-limited mobile node and a fixed node The primary objective is to minimize transmitter power in the mobile node while achieving targeted data rate, R Target R target is application/data dependent (i.e. voice vs. images, vs. video… ) Mobile Node Fixed Node

L-3 PROPRIETARY 3 Motivation: Why CA for Comms? Maximize Power Savings: –Current ordinary non-cognitive approach relies on manual settings for transmission power and channel data rate with limited automatic adjustment. –Manual settings tend to be a hassle for users, so adjustment is often ill-timed. –To ensure comms does not drop out in an dynamic environment, power is often set to an excessive level to cover anticipated worse case channel conditions. A Cognitive Agent approach allows for dynamic control of comms channel power and rate settings to achieve and maintain channel optimization Minimize Interference : –Excessive power level as a result of manual settings generates unnecessary interference. –Interference limits channel access and re-use of codes/frequencies. Adapt to Real-time Channel Variations: –Fading and other varying channel conditions require real-time adjustment of power and rate to maintain optimal comms settings.

L-3 PROPRIETARY 4 Approach Multi-step Development of Comms Agent –Power Control Only (fixed data rate) version 1.Non-learning version 2.Reinforcement Learning (RL) version * 3.RL version augmented with chunking –Power and Rate Control version of Agent  Incorporation of rate adjustment  Trade off of rate and power learning to achieve channel optimization. (Workshop results for this version of the Comms agent) * Special thanks to Professor John E. Laird for key guidance in our efforts to migrate from a non-learning to a learning version of the agent !

L-3 PROPRIETARY 5 Agent Structure Primarily a Reinforcement Learning agent. –Uses chunking to generate RL rules  Allows for dynamic state-space  Allows for additional rules that set initial numeric preferences upon RL rule creation.  Must take care that the state-space won’t grow too large. Has one basic operator “adjust power”. –Can adjust power by steps of -4, -2, -1, 1, 2, or 4. –Can’t adjust beyond upper or lower bounds (this constrains the state-space).

L-3 PROPRIETARY 6 Agent Goals/Rewards Goal state can change (Dynamic Environment)  Power must adjust to optimize SNR. SNR changes depending on range/distance, weather, etc…  As opposed to the static environments in the example domains such as water jug and missionaries and cannibals that have a fixed goal (and don’t use the io-link). Agent is rewarded each time the goal is achieved (SNR reaches desired level). Agent is punished (negative reward) each time the link is lost. SNR – Signal to Noise Ratio

L-3 PROPRIETARY 7 Results Initial Run (untrained agent) Initial Power: 0 dBm Final Power: 22 dBm Range: 100 km Soar Decision Cycles: 45 RL Rules Created: 26 Trained agent Initial Power: 0 dBm Final Power: 22 dBm Range: 100 km Soar Decision Cycles: 17 RL Rules Created: 44

L-3 PROPRIETARY 8 Results Shorter range/less power Initial Power: 22 dBm Final Power: 9 dBm Range: 20 km Longer range/more power Initial Power: 9 dBm Final Power: 26 dBm Range: 150 km

L-3 PROPRIETARY 9 Nuggets and Coal Nuggets –Soar agents that base decisions on IO conditions may be successfully implemented via Reinforcement Learning (RL).  Real-time IO-oriented communications Soar agents are best architected as Reinforcement Learning (RL) agents –Performance is incrementally improved over multiple runs through revision of numeric preferences –Chunking may be successfully used to augment RL through automatic generation of RL rules (state- action pairs)  Allows agent to readily adapt to changing input conditions –Expert guidance via establishing initial preferences and conditions for selection of rules accelerates the learning process –Saving and reloading of RL productions allows agent to make use of previous learning

L-3 PROPRIETARY 10 Nuggets and Coal cont- Coal –First attempts at a learning version of comms agent failed.  Determined planning and chunking structured agent is not the best approach for implementing learning in real-time IO-oriented communications  Root of issue is comms environment is dynamic with values on IO links constantly changing  IO values appear in the condition (LHS) of operator application rules, they become dependencies of the state.  When a dependency (i.e. IO value) changes, all substates generated as a result of impasses are removed, thus preventing learning.

L-3 PROPRIETARY 11 Future Work Complete Base station-Mobile Control Agent Episodic Memory –Learning from patterns captured in episodic memory  A challenge for us… We would love to hear from any related attempts. Localized multi-agent coordination –Modular cognitive architectures with specialized domain decision making Multi-agent interaction and coordination – Sharing of learning and experience

L-3 PROPRIETARY 12 a work in progress… Questions ???? Comments ??? Thank you