We apply the two-stage reliable and scalable SIP server architecture proposed in [1] for presence. The first stage proxies the requests to one of second stage server groups based on the event header and destination user identifier. The destination user identifier is based on presentity’s URI. Such a system achieves uniform load sharing on the servers on an average. However, in certain cases the...

Figure 10: Intrusiveness on the LANs for the distributed algorithm with a heterogeneous load. 7 Conclusions We have shown that existing approaches to load sharing do not scale while supporting a rich set of policies and satisfying bounds on intrusiveness. Further, we have argued that in an owner-based distributed system , it is not sucient to choose a load sharing algorithm which typically indu...

A two-dimensional fracture model where the interaction among elements is modeled by an anisotropic stress-transfer function is presented. The influence of anisotropy on the macroscopic properties of the samples is clarified, by interpolating between several limiting cases of load sharing. Furthermore, the critical stress and the distribution of failure avalanches are obtained numerically for di...

We consider networks of workstations which are not only timesharing, but also heterogeneous with a large variation in the computing power and memory capacities of different workstations. Many load sharing schemes mainly target sharing CPU resources, and have been intensively evaluated in homogeneous distributed environments. However, the penalties of data accesses and movement in modern compute...

Load sharing among distributed generation systems (DGS) is one of the most important topics in wireless-enabled smart microgrids, where a set of power inverters at different geographical locations work coordinately and collaboratively through wireless networks to meet the load requirement. Parallel power inverters operated in distributed generation systems rely on the underlying wireless commun...

Muscles crossing a joint usually outnumber its degrees of freedom, which renders the motor system underdetermined. Typically, optimization laws are postulated to cope with this redundancy. A natural question then arises whether all muscular load sharing patterns can be regarded as results of optimization. To answer it we propose a method of constructing an objective function whose minimization ...

Networks of workstations (NOWs) can be used for parallel processing by using public domain software like PVM. There are significant differences between a real parallel system and a NOW-based system. As a result, load sharing on a NOW can be different from that on a parallel machine. Therefore, it is important to understand the factors that influence the performance of load sharing algorithms on...

As a number of wireless networks, such as the cellular networks (e.g., GSM, GPRS, EDGE, UMTS, HSDPA), wireless local area networks (IEEE 802.11a/b/g), and wireless broadband networks (WiMAX) all become deployed, integrating these networks in order to overflow traffic between them makes sense. A number of papers have shown the benefits of load sharing traffic between various wireless networks fr...

This paper is a survey of existing policies and mechanisms for load sharing in loosely-coupled distributed computing systems, where user machines are personal workstations interconnected by a local area network. We are interested only in centralized operating systems providing mechanisms for remote process communication, thus we do not study distributed operating systems in which load balancing...