DIstributed SImulation & Online gaming Workshop

Research Article

An architecture supporting large scale MMOGs

  • @INPROCEEDINGS{10.4108/ICST.SIMUTOOLS2010.8731,
        author={Chandana  Ghosh and R. Paul  Wiegand and Brian  Goldiez and Troy  Dere},
        title={An architecture supporting large scale MMOGs},
        proceedings={DIstributed SImulation \& Online gaming Workshop},
        publisher={ACM},
        proceedings_a={DISIO},
        year={2010},
        month={5},
        keywords={Distributed Simulation MMOG Partitioning Redundancy},
        doi={10.4108/ICST.SIMUTOOLS2010.8731}
    }
    
  • Chandana Ghosh
    R. Paul Wiegand
    Brian Goldiez
    Troy Dere
    Year: 2010
    An architecture supporting large scale MMOGs
    DISIO
    ICST
    DOI: 10.4108/ICST.SIMUTOOLS2010.8731
Chandana Ghosh1,*, R. Paul Wiegand1,*, Brian Goldiez1,*, Troy Dere2,*
  • 1: Institute for Simulation & Training, 3100 Technology Pkwy, Orlando, FL 32826
  • 2: RDECOM-STTC, 12423 Research Pkwy, Orlando, Fl 32826
*Contact email: cghosh@ist.ucf.edu, wiegand@ist.ucf.edu, bgoldiez@ist.ucf.edu, troy.dere@us.army.mil

Abstract

The growing popularity of large-scale, highly interactive virtual reality systems such as massively multiplayer online games (MMOGs) necessitates highly robust and efficient architectures. Distributed implementations are common, but they must deal with challenges such as supporting very large numbers of closely interacting users, the need to maintain robustness in the face of hardware failure, balancing the processing load, reducing user latency, and minimizing thrashing effects caused by movement between servers. Although a number of existing techniques address each of these independently, there are no unified methods that attack these problems cohesively.

We present methods to simultaneously address these critical challenges---a novel approach and associated software design intended for distributed high performance computing facilities in which the world is divided into a regular lattice of overlapping cells (providing redundancy), which are dynamically assigned to servers within the High Performance Computing (HPC) (facilitating load balancing). We believe this architecture can be applied to non-spatial cells. This architecture is currently being implemented in a test bed for further experimentation.