Multistep-ahead neural-network predictors for network traffic reduction in distributed interactive applications

ABSTRACT

Predictive contract mechanisms such as dead reckoning are widely employed to support scalable remote entity modeling in distributed interactive applications (DIAs). By employing a form of controlled inconsistency, a reduction in network traffic is achieved. However, by relying on the distribution of instantaneous derivative information, dead reckoning trades remote extrapolation accuracy for low computational complexity and ease-of-implementation. In this article, we present a novel extension of dead reckoning, termed neuro-reckoning, that seeks to replace the use of instantaneous velocity information with predictive velocity information in order to improve the accuracy of entity position extrapolation at remote hosts. Under our proposed neuro-reckoning approach, each controlling host employs a bank of neural network predictors trained to estimate future changes in entity velocity up to and including some maximum prediction horizon. The effect of each estimated change in velocity on the current entity position is simulated to produce an estimate for the likely position of the entity over some short time-span. Upon detecting an error threshold violation, the controlling host transmits a predictive velocity vector that extrapolates through the estimated position, as opposed to transmitting the instantaneous velocity vector. Such an approach succeeds in reducing the spatial error associated with remote extrapolation of entity state. Consequently, a further reduction in network traffic can be achieved. Simulation results conducted using several human users in a highly interactive DIA indicate significant potential for improved scalability when compared to the use of IEEE DIS standard dead reckoning. Our proposed neuro-reckoning framework exhibits low computational resource overhead for real-time use and can be seamlessly integrated into many existing dead reckoning mechanisms.

REFERENCES

• 1: Battaglia, G. J. 1996. Mean square error. AMP J. Technol. 5, 31--36.
• 2: Behnke, S., Egorova, A., Gloye, A., Rojas, R., and Simon, M. 2003. Predicting away robot control latency. In Proceedings of the 7th Robocup International Symposium (Padua, Italy, Jul.). 712--719.
• 3: Sumeer Bhola , Guruduth Banavar , Mustaque Ahamad, Responsiveness and consistency tradeoffs in interactive groupware, Proceedings of the 1998 ACM conference on Computer supported cooperative work, p.79-88, November 14-18, 1998, Seattle, Washington, United States [doi>10.1145/289444.331531]
• 4: Boné, R. and Crucianu, M. 2002. Multistep-Ahead prediction with neural networks: A review. Approches Connexionnistes en Sciences Économiques et en Gestion 2, 97--106.
• 5: Wentong Cai , Francis B. S. Lee , L. Chen, An auto-adaptive dead reckoning algorithm for distributed interactive simulation, Proceedings of the thirteenth workshop on Parallel and distributed simulation, p.82-89, May 01-04, 1999, Atlanta, Georgia, United States
• 6: Gavin C. Cawley, On a Fast, Compact Approximation of the Exponential Function, Neural Computation, v.12 n.9, p.2009-2012, September 1, 2000 [doi>10.1162/089976600300015033]
• 7: Chen, L. and Chen, G. 2005. A fuzzy dead reckoning algorithm for distributed interactive applications. In Proceedings of the 2nd International Conference on Fuzzy Systems and Knowledge Discovery (FSKD) (Changsha, China, Aug.). 961--971.
• 8: Yim-Pan Chui , Pheng-Ann Heng, Attitude dead reckoning in a collaborative virtual environment using cumulative polynomial extrapolation of quaternions: Research Articles, Concurrency and Computation: Practice & Experience, v.16 n.15, p.1575-1599, December 2004 [doi>10.1002/cpe.v16:15]
• 9: David N. Snowdon , Alan J. Munro , Elizabeth F. Churchill, Collaborative Virtual Environments: Digital Places and Spaces for Interaction, Springer-Verlag New York, Inc., Secaucus, NJ, 2001
• 10: Declan Delaney , Tomás Ward , Seamus McLoone, On consistency and network latency in distributed interactive applications: a survey--part I, Presence: Teleoperators and Virtual Environments, v.15 n.2, p.218-234, April 2006 [doi>10.1162/pres.2006.15.2.218]
• 11: Declan Delaney , Tomás Ward , Seamus McLoone, On Consistency and Network Latency in Distributed Interactive Applications: A Survey—Part II: Presence 2005: Eighth International Workshop I, Presence: Teleoperators and Virtual Environments, v.15 n.4, p.465-482, August 2006 [doi>10.1162/pres.15.4.465]
• 12: Delaney, D., Ward, T., and McLoone, S. 2003. Reducing update packets in distributed interactive applications using a hybrid model. In Proceedings of the 16th ISCA International Conference on Parallel and Distributed Computing Systems (PDCS) (Reno, NV, Aug.). 417--422.
• 13: Richard M. Fujimoto, Parallel and Distribution Simulation Systems, John Wiley & Sons, Inc., New York, NY, 1999
• 14: Saul Greenberg , David Marwood, Real time groupware as a distributed system: concurrency control and its effect on the interface, Proceedings of the 1994 ACM conference on Computer supported cooperative work, p.207-217, October 22-26, 1994, Chapel Hill, North Carolina, United States [doi>10.1145/192844.193011]
• 15: Hagan, M. T. and Menhaj, M. B. 1994. Training feedforward networks with the marquardt algorithm. IEEE Trans. Neural Netw. 5, 6, 989--993.
• 16: Harrington, P. B. 1993. Sigmoid transfer functions in backpropagation neural networks. Analyt. Chem. 65, 15, 2167--2168.
• 17: Amy E. Henninger , Avelino J. Gonzalez , Michael Georgiopoulos , Ronald F. DeMara, A Connectionist-Symbolic Approach to Modeling Agent Behavior: Neural Networks Grouped by Contexts, Proceedings of the Third International and Interdisciplinary Conference on Modeling and Using Context, p.198-209, July 27-30, 2001
• 18: IEEE 1995. Standard for Distributed Interactive Simulation---Application Protocols. IEEE Standard 1278.1--1995. Institute of Electrical and Electronics Engineers, Piscataway, NJ.
• 19: Lee, B.-S., Cai, W., Turner, S. J., and Chen, L. 2000. Adaptive dead reckoning algorithms for distributed interactive simulation. Int. J. Simul. Syst. Sci. Technol. 1, 1-2, 21--34.
• 20: Lin, K.-C., Wang, M., Wang, J., and Schab, D. E. 1995. The smoothing of dead reckoning image in distributed interactive simulation. In Proceedings of the AIAA Flight Simulation Technologies Conference (Baltimore, MD, Aug.). 83--87.
• 21: Lin, K.-C. and Schab, D. E. 1994a. Study on the network load in distributed interactive simulation. In Proceedings of the AIAA Flight Simulation Technologies Conference (Scottsdale, AZ, Aug.). 202--209.
• 22: Lin, K.-C. and Schab, D. E. 1994b. The performance assessment of the dead reckoning algorithms in DIS. Simul. 63, 5, 318--325.
• 23: Lloyd, J. 2004. The torque game engine. Game Devel. Mag. 11, 8, 8--9.
• 24: Michael R. Macedonia , Michael J. Zyda, A Taxonomy for Networked Virtual Environments, IEEE MultiMedia, v.4 n.1, p.48-56, January 1997 [doi>10.1109/93.580395]
• 25: Mathy, L., Edwards, C., and Hutchinson, D. 1999. Principles of QoS in group communications. Telecommun. Syst. 11, 1-2, 59--84.
• 26: McCoy, A., Delaney, D., McLoone, S., and Ward, T. 2005. Dynamic hybrid strategy models for networked multiplayer games. In Proceedings of the 19th European Conference on Modelling and Simulation (ECMS) (Riga, Latvia, Jun.). 727--732.
• 27: Aaron McCoy , Seamus McLoone , Tomas Ward , Declan Delaney, Investigating Behavioural State Data-Partitioning for User-Modelling in Distributed Interactive Applications, Proceedings of the 8th IEEE International Symposium on Distributed Simulation and Real-Time Applications, p.74-82, October 21-23, 2004 [doi>10.1109/DS-RT.2004.26]
• 28: Aaron McCoy , Declan Delaney , Tomas Ward, Game-state fidelity across distributed interactive games, Crossroads, v.9 n.4, p.4-9, June 2003 [doi>10.1145/904080.904082]
• 29: Larry Mellon , Darrin West, Architectural optimizations to advanced distributed simulation, Proceedings of the 27th conference on Winter simulation, p.634-641, December 03-06, 1995, Arlington, Virginia, United States [doi>10.1145/224401.224700]
• 30: Miller, D. C. and Thorpe, J. A. 1995. SIMNET: The advent of simulator networking. Proc. IEEE 83, 8, 1114--1123.
• 31: Mizutani, E. and Dreyfus, S. E. 2001. On complexity analysis of supervised MLP-learning for algorithmic comparisons. In Proceedings of the 14th INNS-IEEE International Joint Conference on Neural Networks (IJCNN) (Washington, DC, Jul.). 347--352.
• 32: Palant, W., Griwodz, C., and Halvorsen, P. 2006. Evaluating dead reckoning variations with a multi-player game simulator. In Proceedings of the 16th ACM International Workshop on Network and Operating Systems Support for Digital Audio and Video (NOSSDAV) (Newport, RI, May). 20--25.
• 33: Lothar Pantel , Lars C. Wolf, On the suitability of dead reckoning schemes for games, Proceedings of the 1st workshop on Network and system support for games, p.79-84, April 16-17, 2002, Bruanschweig, Germany [doi>10.1145/566500.566512]
• 34: Papadopoulos, G., Edwards, P. J., and Murray, A. F. 2001. Confidence estimation methods for neural networks: A practical comparison. IEEE Trans. Neural Netw. 12, 6, 1278--1287.
• 35: Jose C. Principe , Neil R. Euliano , W. Curt Lefebvre, Neural and Adaptive Systems: Fundamentals through Simulations with CD-ROM, John Wiley & Sons, Inc., New York, NY, 1999
• 36: Rodgers, J. L. and Nicewander, W. A. 1988. Thirteen ways to look at the correlation coefficient. Ameri. Statis. 42, 1, 59--66.
• 37: Roehle, B. 1997. Channeling the data flood. IEEE Spectrum 34, 3, 32--38.
• 38: Ryan, P. and Oliver, W. 2006. Modelling of dead reckoning and heartbeat update mechanisms in distributed interactive simulation. In Proceedings of the European Simulation Interoperability Workshop (Stockholm, Sweden, Jun.). 06E-SIW-025.
• 39: Sas, C., O'Hare, G., and Reilly, R. 2004. A performance analysis of movement patterns. In Proceedings of the 4th International Conference on Computational Science (ICCS) (Krakow, Poland, Jun.). 954--961.
• 40: Sas, C., Reilly, R., and O'Hare, G. 2003. A connectionist model of spatial knowledge acquisition in a virtual environment. In Proceedings of the 2nd Workshop on Machine Learning, Information Retrieval and User Modelling (MLIRUM) (Johnstown, PA, Jun.). 40--48.
• 41: Shanker, M., Hu, M. Y., Hung, M. S. 1996. Effect of data standardization on neural network training. OMEGA (Int. J. Manage. Sci.) 24, 4, 385--397.
• 42: Shim, K.-H. and Kim, J.-S. 2001. A dead reckoning algorithm with variable threshold scheme in networked virtual environment. In Proceedings of the IEEE International Conference on Systems, Management and Cybernetics (SMC) (Tucson, AZ, Oct.). 1113--1118.
• 43: Sandeep Singhal , Michael Zyda, Networked virtual environments: design and implementation, ACM Press/Addison-Wesley Publishing Co., New York, NY, 1999
• 44: Sudhir Srinivasan, Efficient data consistency in HLA/DIS++, Proceedings of the 28th conference on Winter simulation, p.946-951, December 08-11, 1996, Coronado, California, United States [doi>10.1145/256562.256867]
• 45: Martin R. Stytz , Sheila B. Banks, The distributed mission training integrated threat environment system architecture and design, ACM Transactions on Modeling and Computer Simulation (TOMACS), v.11 n.1, p.106-133, Jan. 2001 [doi>10.1145/379525.379529]
• 46: Chengzheng Sun , Xiaohua Jia , Yanchun Zhang , Yun Yang , David Chen, Achieving convergence, causality preservation, and intention preservation in real-time cooperative editing systems, ACM Transactions on Computer-Human Interaction (TOCHI), v.5 n.1, p.63-108, March 1998 [doi>10.1145/274444.274447]
• 47: Thurau, C., Bauckhage, C., and Sagerer, G. 2003. Combining self organizing maps and multilayer perceptrons to learn bot-behavior for a commercial game. In Proceedings of the 4th International Conference on Intelligent Games and Simulation (GAME-ON) (London, Nov.). 119--123.
• 48: Van Hook, D. J., Calvin, J. O., and Smith, J. E. 1995. Data consistency mechanisms to support distributed simulation. In Proceedings of the 12th Workshop on Standards for the Interoperability of Distributed simulations (Orlando, FL, Mar.). 797--806.
• 49: Yu, S.-J. and Choy, Y.-C. 2001. A dynamic message filtering technique for 3D cyberspaces. Comput. Commun. 24, 18, 1745--1758.
• 50: Mao-Jun Zhang , Nicolas D. Georganas, An orientation update message filtering algorithm in collaborative virtual environments, Journal of Computer Science and Technology, v.19 n.3, p.423-429, May 2004 [doi>10.1007/BF02944912]
• 51: Ingrid Zukerman , David W. Albrecht, Predictive Statistical Models for User Modeling, User Modeling and User-Adapted Interaction, v.11 n.1-2, p.5-18, 2001 [doi>10.1023/A:1011175525451]

INDEX TERMS

Primary Classification:
  C. Computer Systems Organization
  C.2 COMPUTER-COMMUNICATION NETWORKS
      C.2.4 Distributed Systems
          Subjects: Distributed applications

Additional Classification:
  I. Computing Methodologies
  I.5 PATTERN RECOGNITION
      I.5.1 Models
          Subjects: Neural nets
  I.6 SIMULATION AND MODELING
      I.6.8 Types of Simulation
          Subjects: Distributed

General Terms:
Algorithms, Performance, Theory

Keywords:
Distributed interactive applications, collaborative virtual environments, consistency, dead reckoning, distributed interactive simulation, multistep-ahead prediction, network bandwidth reduction, networked multiplayer computer games, networked virtual environments, neural networks, predictive contract mechanisms, scalability, wargames