Network-server architecture has become a de-facto standard for Distributed Virtual Environment (DVE) systems. In these systems, a large set of remote users share a 3D virtual scene. In order to design scalable DVE systems, different approaches have been proposed to maintain the DVE system working under its saturation point, maximizing system throughput. Also, in order to provide quality of service to avatars in a DVE systems, avatars should be assigned to servers taking into account, among other factors, system throughput and system latency. This highly complex problem is called quality of service (QoS) problem in DVE systems. This paper proposes two different approaches for solving the QoS problem, based on modern heuristics (simulated annealing and GRASP).

Distributed Virtual Environment (DVE) systems have been designed last years as a set of distributed servers. These systems allow a large number of remote users to share a single 3D virtual scene. In order to provide quality of service in a DVE system, clients should be properly assigned to servers taking into account system throughput and system latency. The latter one is composed of both network and computational delays. This highly complex problem is known as the quality of service (QoS) problem. In this paper, we study the implementation of a genetic algorithm (GA) for solving the QoS problem in DVE systems. Performance evaluation results show that, due to its ability of both finding good search paths and keeping diversity, this nature inspired technique can provide significantly better solutions than other heuristic methods while requiring shorter execution times. Therefore, the proposed implementation of GA search method can actually improve the QoS offered by DVE systems.

A load balancing scheme for massively multiplayer

As massively multiplayer online games are becoming very popular, how to support a large number of concurrent users while maintaining the game performance has become an important research topic. One way to address this problem is to employ a multi-server system to host the game. There are two main research directions on multi-server architecture, global load balancing, which is optimal but computationally very expensive, or local load balancing, which is not optimal but efficient. In this paper, we propose a hybrid load balancing approach to support massively multiplayer online gaming. Our idea is to augment a local load balancing algorithm with some global load information, which may be obtained less frequently, as we select available servers for load redistribution. We propose two methods to implement the hybrid approach. Our results show that the proposed methods reduce the frequency of server overloading and improve the overall game performance significantly.

A distributed virtual environment (DVE) consists of multiple network nodes (servers), each of which can host many users that consume CPU resources on that node and communicate with users on other nodes. Users can be dynamically migrated between the nodes, and the ultimate goal for the migration policy is to minimize the average system response time perceived by the users. In order to achieve this, the user migration policy should minimize network communication while balancing the load among the nodes so CPU resources of the individual nodes are not overwhelmed. This paper considers a multiplayer online game as an example of a DVE and presents an adaptive distributed user migration policy, which uses Reinforcement Learning to tune itself and thus minimize the average system response time perceived by the users. Performance of the self-tuning policy was compared on a simulator with the standard benchmark non-adaptive migration policy and with the optimal static user allocation policy in a variety of scenarios, and the self-tuning policy was shown to greatly outperform both benchmark policies, with performance difference increasing as the network became more overloaded. These results provide yet another demonstration of the power and generality of the methodology for designing adaptive distributed and scalable migration policies, which has already been applied successfully to several other domains [17, 18].