Empirically measuring the QoS sensitivity of interactive online game players

It is widely assumed that highly interactive online games require a minimum quality of service (QoS) from the network, which suggests that offering premium IP service quality for game players may be a new source of revenue for Internet service providers (ISPs). In order to offer such services, ISPs must know the upper bounds of the performance metrics players are willing to tolerate. This paper reports on our preliminary attempts to experimentally establish performance bounds for different types of online games. First we placed a group of players in a controlled network environment, where artificial network delay and loss is introduced during their games. We logged objective measures (game performance indicators from the game server) and used a questionnaire to establish a subjective measure of user perceived quality as a function of different network conditions. Our paper concludes with an analysis of our results and a comparison with previous work based on indirect measurements.