A large-scale multimedia storage system (LMSS), which consists of a single server or multiple servers, manages the storage and retrieval of multimedia data from disk media. As a networked multimedia service is expected to serve a large pool of clients, it is impossible for a single server to meet all multimedia requirements such as continuous-time presentation, network bandwidth, etc. In a large-scale multimedia storage system where client requests for different multimedia objects may have different demands, the placement and replication of the objects is an important factor, as it may result in an imbalance in server loading across the system. Generally each object storage server responds to the requests that come from the centralized servers independently and has no communication with other OSSs in the system. But in this distributed load balancing strategy for LMSS, in which OSSs can cooperate to achieve higher performance. Such OSS system can replicate the objects to and balance the requests among other servers to achieve a near-optimal average waiting time (AWT) of the requests in the system.