The performance of cluster computing depends on how concurrent jobs share multiple data center resource types like CPU, RAM and disk storage. Recent research has discussed efficiency and fairness requirements and identified a number of desirable scheduling objectives including so-called dominant resource fairness (DRF). We argue here that proportional fairness (PF), long recognized as a desirab...

This paper assumes each user has more than one queue, derives a new packet dependent proportional fairness power allocation pattern based on the sum of weight capacity and the packet’s priority in users’ queues, and proposes 4 new schemes of cross-layer packet dependent OFDM scheduling for heterogeneous classes of traffic based on proportional fairness. Scenario 1, scenario 2 and scenario 3 lea...

Some recent papers [5, 9] have shown that congestion control based on additive increase and multiplicative decrease tends to share bandwidth according to proportional fairness. Proportional fairness is a form of fairness which distributes bandwidth with a bias in favour of ows using a smaller number of hops; this is in contrast with max-min fairness, which gives absolute priority to small ows. ...

This paper proposes two scheduling algorithms for subcarrier allocation of OFDM relay system, enhanced two-hop adaptive proportional fairness (E-THAPF) and user-number-dynamic two-hop adaptive proportional fairness (UND-THAPF), aiming to improve the performance of the traditional two-hop proportional fairness (THPF) scheduling algorithm. By modifying the priority of the two hops in THPF in an a...

Integration of multicast and unicast data in future radio access networks will be necessary in order to improve the resource efficiency and provide new services. Such integration requires new and efficient resource sharing mechanisms. These mechanisms need to be optimized to provide the best possible trade-off between resource efficiency and fairness. In this paper, we consider a case where str...

We compare the performance of three usual allocations, namely max-min fairness, proportional fairness and balanced fairness, in a communication network whose resources are shared by a random number of data flows. The model consists of a network of processorsharing queues. The vector of service rates, which is constrained by some compact, convex capacity set representing the network resources, i...

The capacity region of a channel consists of all achievable rate vectors. Picking a particular point in the capacity region is synonymous with rate allocation. The issue of fairness in rate allocation is addressed in this paper. We review several notions of fairness, including max-min fairness, proportional fairness and Nash bargaining solution. Their efficiencies for general multiuser channels...