DARPA ULTRALOG Final Report - Industrial and Manufacturing ...

More documents

Recommendations

Info

5 Conclusions and Future Research The generic predictor framework provides core functionality to Cougaar, making Cougaar a more survivable agent infrastructure. The predictor plugins can be invoked by any agent participating in the logistics supply process. Different algorithms can be hooked into the framework to use the data and other predictor services, hence eliminating the need to write predictor plugins from scratch. Initial studies show that the estimator models work well for items across different supply classes with the prediction almost mimicking the actual demand values. However, due to the low variability and uncertainty of the observed demand, the performance of predictors has not been extensively tested. Testing with variable demand is currently in progress. Furthermore as a certain class of predictors seems to perform better for a particular class of data, hybrid approaches to intelligently selecting the predictor algorithms based on data-type and demand are being investigated. One such approach is to use a SMART predictor (Figure 12) as explained below. Here a smart predictor would monitor the demand coming from the customers and choose which method should be used during the communication loss. We observe that each method (Model based state estimator and Moving-average) gives good forecasts for certain types of data. Thus by building a SMART predictor which chooses the type of predictor to be used depending on the situation would result in better forecasts. Brinn and Beth DePass for their support, comments and insightful discussions. We would also like to thank Lora Goldston for her support in the development of the reconciliation code and in the testing and integration of the predictor algorithms. 7 References 1. Ultra*Log Adaptive Logistics Defense Team Plan, Revised version 2.0, 2003. 2. Welch .G, Bishop., G. An introduction to Kalman filter., Department of Computer Science, University of North Carolina at Chapel Hill, Chapel Hill, TR 95-041, March 11 2002. 3. John Moody and Christian J. Darken, Fast learning in networks of locally-tuned processing units, Neural Computation 1, 281-294, 1989. 4. G. Rätsch, T. Onoda, and K.-R. Müller. Soft margins for AdaBoost. Machine Learning, 42(3):287-320, March 2001. 5. Y.Hong, N.Gautam, S.R.T.Kumara, A.Surana, H.Gupta, S.Lee, V.Narayanan, H.Thadakamalla, M. Greaves, M. Brinn, Survivability of Complex System – Support Vector Machine Based Approach Conf., Artificial Neural Networks in Engineering (ANNIE) 2002. 6. Osuna, E. E., Freund R. and Girosi, F., 1997, Support Vector Machines: Training and Applications, Technical Report AIM-1602, MIT A.I. Lab. 7. Vapnik, V. N., 1998, Statistical Learning Theory, John wiley & sons, Inc, New York. 8. Burges, C. J. C., 1998, A Tutorial on Support Vector Machines for Pattern Recognition, Knowledge Discovery and Data Mining, Vol. 2, No. 2, pp. 121-167. 9. Cougaar Website (www.cougaar.org) Figure 12. Description of SMART Predictor 6 Acknowledgements This research was performed under the DARPA Ultralog effort and was supported by DARPA grant MDA972-1-1-0038 and Contract 2087-IAI-ARPA-0038. We would like to thank Dr. Mark Greaves, Marshall
1 SURVIVABILITY OF COMPLEX SYSTEM – SUPPORT VECTOR MACHINE BASED APPROACH Y, HONG, N. GAUTAM, S. R. T. KUMARA, A. SURANA, H. GUPTA, S. LEE, V. NARAYANAN, H. THADAKAMALLA The Dept. of Industrial Engineering, The Pennsylvania State University, University Park, PA 16802 M.BRINN BBN Technologies, Cambridge, MA M. GREAVES DARPA IXO/JLTO, Arlington, VA 22203 ABSTRACT Logistic systems which are inherently distributed, in general can be classified as complex systems. Survivability of these systems under varying environment conditions is of paramount importance. Different environmental conditions in which the logistic system resides are translated into several stresses. These in turn will manifest as internal stresses. Logistic systems can be modeled as a collection of software agents. Each agent’s behavior is a result of the stresses imposed. Predicting the agents’ collective behavior is of paramount importance to ensure survivability. Analytical modeling of such systems becomes very difficult, albeit impossible. In this paper, we study a supply chain in which a real life scenario is used. We implement the supply chain in Cougaar (Cognitive Agent Architecture developed by DARPA) and develop a predictor, based on Support Vector Machine. We report our methodology and results with real-life experiments and stress scenarios. INTRODUCTION Logistic systems can be classified as complex systems (Choi et al., 2001, Baranger, http://necsi.org/projects/baranger/cce.pdf). Logistic systems have many components such as suppliers and distributors at several stages. These components are distributed geographically but interdependent. At each component some form of nonlinear decision making process goes on. Typically the system would respond in a stable manner to external disturbances. But due to information delay, inherent feedback structure and nonlinear components unstable phenomena can arise which may ultimately manifest as chaotic behavior. Efficient resource allocation and collective oscillations (of say inventory levels) are some examples of emergent behavior shown by supply chains. They have structure at many scales, each component itself represents a simple supply chain. The components compete due to resource limitation but collobarate/cooperate to maximize their gains which is another characteristic feature of a complex system. The survivability of logistic systems under varying environmental conditions is of paramount importance. Survivability is going to be itself an emergent property of a logistic system and it represents the ability of the system
Page 1 and 2:
Ultra*Log PSU/IAI Final Report for
Page 3 and 4:
Contents Contents .................
Page 5:
Executive Summary Ultra*Log is a De
Page 8 and 9:
2.3 Gnanasambandam, N., Lee, S., Ku
Page 10 and 11:
6 Characterization and analysis of
Page 12 and 13: timizing simultaneously the link de
Page 14 and 15: where ∆ 1 (j) ≥ 0 and ∆ 2 (i,
Page 16 and 17: Table 2. GA Results Agent N A D max
Page 18 and 19: connected component, in which a pat
Page 20 and 21: Random Small-world Scale-free with
Page 22 and 23: Growth mechanisms Start with a smal
Page 24 and 25: Table 2. The proposed network’s c
Page 26 and 27: ¡ ¡ ¢ £ ¤ ¥ ¦ £ § ¨ © ¥
Page 28 and 29: © © ¤ ¢ ¨ ¤ £ ¦ ¨ © §
Page 30 and 31: DMAS Controller. The functional uni
Page 32 and 33: 1000 500 0 -500 -1000 0.2 0.4 0.6 0
Page 34 and 35: tems. Proceedings of the Second Joi
Page 36 and 37: Proceedings of the 1st Open Cougaar
Page 44 and 45: 1 SITUATION IDENTIFICATION USING DY
Page 46 and 47: 3 3.2 Behavior In SSC society an ag
Page 48 and 49: 5 All the behavior parameters may n
Page 50 and 51: Estimating Global Stress Environmen
Page 52 and 53: chaotic deterministic time series.
Page 54 and 55: 100% 1 95% 2 14 15 64% TAO 4 64% 62
Page 56 and 57: interactions as a dynamical system
Page 58 and 59: ehavior states under varying system
Page 60 and 61: Extensive testing and validation of
Page 64 and 65: 2 to function critically even under
Page 66 and 67: 4 points into a corresponding inner
Page 68 and 69: 6 stresses well. The Warehouse 1 ag
Page 70 and 71: © £ ¨ ¥ ¤ § ¢ ¥ ©
Page 72 and 73: Table 1: Notation Symbol Descriptio
Page 74 and 75: 4 Conclusions and Future Work 4.1 C
Page 76 and 77: O, U Stresses Physical/Infrastructu
Page 78 and 79: Manuscript for IEEE Transactions on
Page 106 and 107: 2 discuss problem domain and in Sec
Page 108 and 109: 4 t Si t ∫ + ( ) i ) t When RA i
Page 110 and 111: 6 S UB i ∑ = P LI / LI . (16) i p
Page 112 and 113:
8 policies while underutilizing in
Page 114 and 115:
architecture based on both the Grid
Page 116 and 117:
to machines (network topology) and
Page 118 and 119:
component is a member of one of the
Page 120 and 121:
denotes the immediate predecessors
Page 122 and 123:
limit of large number of tasks. If
Page 124 and 125:
Min-min heuristic algorithm Step 1:
Page 126 and 127:
We set up eight different experimen
Page 128 and 129:
0. 4 8057 8237 0.5 6439 6635 0.6 53
Page 130 and 131:
pp. 191-200. [3] I. Foster, C. Kess
Page 132 and 133:
Technology, Cambridge, MA, 1995. [2
Page 134 and 135:
Manuscript for IEEE TRANSACTIONS ON
Page 136 and 137:
Page 138 and 139:
Page 140 and 141:
Page 142 and 143:
Page 144 and 145:
Page 146 and 147:
Page 148 and 149:
Page 150 and 151:
Page 152 and 153:
Page 154 and 155:
Page 156 and 157:
Coordinating Control Decisions of S
Page 158 and 159:
directly. It has coarser scale. It
Page 160 and 161:
Understanding Agent Societies Using
Page 162 and 163:
• For tasks, the UID of the direc
Page 164 and 165:
for tracking the dependencies betwe
Page 166 and 167:
within the monitored enclave. With
Page 168 and 169:
Figure 1. Agent Hierarchy in CPE So
Page 170 and 171:
Figure 3. The World Model CPY Agent
Page 172 and 173:
Table 2. TechSpecs: Infrastructure
Page 174 and 175:
terms of the average waiting times
Page 176 and 177:
Acknowledgements The work described
Page 178 and 179:
key realization to tackle this prob
Page 180 and 181:
are or ignored perturbations. The e
Page 182 and 183:
sustained oscillations. If the inst
Page 184 and 185:
solved by biological systems for li
Page 186 and 187:
non-linear and non-stationarity. Ne
Page 188 and 189:
D k : Outflow from high priority qu
Page 190 and 191:
the system starts to perform self-s
Page 192 and 193:
sustained in a supply chain. Resour
Page 194 and 195:
which are necessary to make good mo
Page 196 and 197:
focusing on the computational compl
Page 198 and 199:
line of research that deals with ne
Page 200 and 201:
ealizable. But the inherent complex
Page 202 and 203:
Min, H. and Zhou, G., 2002, Supply
Page 204 and 205:
In the rest of this paper we report
Page 206:
shows relatively irregular behavior
show all

DARPA ULTRALOG Final Report - Industrial and Manufacturing ...

You also want an ePaper? Increase the reach of your titles

Delete template?

Save as template?