Applicability of group communication for increased scalability in MMOGs

Abstract

Massive multiplayer online games (MMOGs) are today the driving factor for the development of distributed interactive applications, and they are increasing in size and complexity. Even a small MMOG supports thousands of players, the biggest support hundreds of thousands of concurrent players. Since they are typically built as strict client-server systems, they suffer from the inherent scalability problem of the architecture. Computing power and bandwidth limitations close to the server limit the possible number of players. Also, the latency of communication between players through the server will be higher than using direct communication.In the paper, we address these issues and investigate improvement options.A typical MMOG consists of a virtual world with a concept of time and space that is similar to the real world. In it, players are represented by avatars. Only subsets of these avatars interact with each other at any given time. This allows us to divide them into groups, and communication among group members becomes a multi-party communication problem. Thus, to reduce resource consumption, we compare the performance of several algorithms for group communication with the current central server approach. We use overlay multicast as the means of providing group communication, and research algorithms for creating shortest path trees, spanning trees, delay-bounded spanning trees and, more specific, applying Steiner tree heuristics.Our experimental results indicate that different approaches are useful to reduce resource consumption while achieving a good perceived quality under varying conditions, such as frequent changes in group membership and the demand for low latency.

Dynamic Group Membership Management for Distributed Interactive Applications

“…The reconfiguration time of dynamic algorithms is very low compared to that of the SPH and CT heuristics [14]. The reconfiguration time of the dynamic algorithms is on average below 10 milliseconds for group sizes up to 120 member nodes (using a Pentium4 at 1.3 GHz), while, SPH and CT are 10 and 50 times slower, respectively.…”

“…We have implemented a simulator (please see [14] for details), that mimics group communication in distributed interactive applications. It includes algorithms to create and configure groups.…”

“…The total cost of the tree is the sum of all the edge weights and acts as a metric for the total bandwidth consumed. Reducing the total cost may help the scalability of distributed interactive applications [14]. The diameter expresses the worst case latency between any pair of group members.…”

“…We have tested combinations of 13 insert and 13 remove strategies and compared them with the Steiner minimum tree heuristic shortest path heuristic (SPH) and the minimum diameter degree limited heuristic compact tree (CT) that we have investigated in earlier work [14] 1 . In this paper, we present only the evaluation for the most promising and interesting insert and remove combinations.…”

“…In this paper, we present only the evaluation for the most promising and interesting insert and remove combinations. All of the approaches 1 The CT heuristic was called MDDBST in [14]. investigated here are centralized where a well-known central server receives group change requests, which it then executes and distributes new overlay routing information.…”