No abstract

Simulating the realistic behavior of large crowds of autonomous agents is still a challenge for the computer graphics community. In order to handle large crowds, some scalable architectures have been proposed. Nevertheless, the effective use of distributed systems requires the use of partitioning methods that can properly assign different sets of agents to the existing distributed resources.In this paper, we propose the improvement of the partitioning method for distributed crowd simulations by using irregular shape regions. Concretely, we propose the partition of the virtual world using convex hulls. The performance evaluation results show that the Convex Hull method outperforms the rest of the considered methods in terms of both fitness function values and execution times, regardless of the movement pattern followed by the agents. These results show that the shape of the regions in the partition can improve the performance of the partitioning method, rather than the heuristic method used.

In recent years, Distributed Virtual Environments (DVEs) have become one of the major network applications, mainly due to the enormous popularity of multiplayer online games in the entertainment industry. Although the workload generated by avatars in a DVE system has already been characterized, the actual network traffic requirements of multiplayer online games are usually limited (hidden) by the available network bandwidth.In this paper, we propose the measurement of the network traffic requirements of the most popular MOGs by monitoring the network traffic generated by different game tournaments in a LAN Party. The network infrastructure was explicitely designed and implemented for that event by a Network Service Provider, achieving a sustained bandwidth of 100 Mbps for each network interface. Therefore, the potential bandwidth bottleneck was moved from the network to another element of the system or application. The results show that the aggregated bandwidth required by these applications is not higher than 1600 Kbps. Also, the results show identical variations in the network traffic sent to some of the clients by the game server. These results can be used as a basis for an efficient design of MOGs infrastructure.

Crowd simulations require both rendering visually plausible images and managing the behavior of autonomous agents. Therefore, these applications need an efficient design that allow them to simultaneously tackle these two requirements. Although several proposals have focused on the software architectures for these systems, no proposals have focused on the computer systems supporting them.In this paper, we analyze the computer architectures used in the literature to support virtual environments. Also, we propose a distributed computer architecture efficient enough to support simulations of thousand of autonomous agents. This proposal consists of a cluster of computers in order to improve flexibility and robustness, as well as a hierarchical software architecture that efficiently provides consistency. Performance evaluation results show that the trade-off between flexibility and consistency allows to efficiently manage thousands of autonomous agents.

No abstract