Hemant Chaskar

Fair scheduling with tunable latency: a round-robin approach

Weighted fair queueing (WFQ)-based packet scheduling schemes require processing at line speeds for tag computation and tag sorting. This requirement presents a bottleneck for their implementation at high transmission speeds. In this paper, we propose an alternative and lower complexity approach to packet scheduling, based on modifications of the classical round-robin scheduler. Contrary to conventional belief, we show that appropriate modifications of the weighted round-robin (WRR) service discipline can, in fact, provide tight fairness properties and efficient delay guarantees to multiple sessions. Two such modifications are described: 1) list-based round robin, in which the server visits different sessions according to a precomputed list which is designed to obtain the desirable scheduling properties and 2) multiclass round robin, a version of hierarchical round robin with controls designed for good scheduling properties. The schemes considered are compared with well-known WFQ schemes and with deficit round robin (a credit-based WRR), on the basis of desirable properties such as bandwidth guarantees, fairness in excess bandwidth sharing, worst-case fairness, and efficiency of latency (delay guarantee) tuning. The scheduling schemes proposed and analyzed here operate with fixed packet sizes, and hence can be used in applications such as cell scheduling in ATM networks, time-slot scheduling on wireless links as in GPRS air interface, etc. A credit-based extension of the proposed schemes to handle variable packet sizes is also possible.

Fair scheduling with tunable latency: a round robin approach

Much of the previous research in packet scheduling for high speed routers is focused around the weighted fair queuing (WFQ) paradigm. In WFQ schemes, the transmission schedule is determined by sorting the tags of the packets contending for the link. This requires processing at line speeds for tag computation and tag sorting. We propose an alternative and lower complexity approach to packet scheduling, based on modifications of the classical round robin scheduler. Contrary to conventional belief, we show that appropriate modifications of the weighted round robin (WRR) service discipline can, in fact, provide tight fairness properties and efficient delay guarantees to multiple sessions. Two such modifications are described: (i) list-based round robin, in which the server visits different sessions according to a precomputed list which is designed to obtain the desirable scheduling properties and, (ii) multiclass round robin, a version of hierarchical round robin with controls designed for good scheduling properties. The schemes considered are compared with well known WFQ schemes and with the deficit round robin (a credit-based weighted round robin), on the basis of desirable properties such as bandwidth guarantees, fairness in excess bandwidth sharing, worst-case fairness and efficiency of latency (delay guarantee) tuning.

Providing end-to-end location privacy in IP-based mobile communication

As Internet protocol (IP)-based protocols move toward becoming the prevalent means for providing new forms of communication, for example, using IP for communication traditionally done via public Switched telephone network (PSTN), location privacy of mobile end users becomes an important problem to address. In an IP network, each packet carries IP addresses corresponding to the source (sender) and the destination (receiver) of the packet. Mobile hosts (laptop computers, PDAs, mobile phones etc.) usually acquire temporary IP addresses from the address spaces allocated to the access networks where they are currently connected to the Internet, and use these addresses for communication over the Internet. Due to a strong correlation between the address spaces used by the access networks and the geographic location of the access networks, location privacy of mobile users is compromised. If the recipient or an intermediate network node in the path of the packet analyzes the packet, the location of the sender of the packet is revealed. This may affect the widespread acceptance of IP based protocols. In this paper we present a novel protocol called LocPriv that preserves the location privacy in an IP based mobile communication network. The protocol works by employing an IP address encapsulation/swapping scheme at the access nodes to conceal the IP address of the mobile host, without affecting the route that the packets should follow in the network. We compare the protocol with existing techniques for providing location privacy and also analyze the effect of the protocol on the complexity of routing elements.

A framework for quality of service differentiation on 3G CDMA air interface

In this paper, we develop a framework for quality of service (QoS) differentiation on the CDMA air interface. Unlike many QoS schemes for the CDMA air interface which focus on satisfying the needs of specific applications such as voice and packet data, our framework is based on the paradigm of service classes. Each class is defined by a group behavior, which is implemented using power control and spreading control. Using this framework the 3G operators can define their own set of service classes, choose the preferred way of implementing the group behavior, and offer a class-based pricing scheme. Our work provides a flexible and practical QoS framework that can be used to support a variety of 3G services.

Wireless link shaping for service guarantees

Providing quality of service (QoS) guarantees on heterogeneous networks with both wireless and wireline networks involves accounting for the statistical fluctuations on wireless channels, in addition to the traffic fluctuations of interest in a purely wireline setting. We develop a detailed framework for QoS provisioning for delay constrained (real time) applications over a Rayleigh faded wireless downlink. Forward error correction (FEC) coding based link layer error recovery with interleaving is used for link shaping (i.e., for converting a link with high symbol error rates and correlations of symbol errors into a link with almost wireline characteristics). Tradeoffs between choice of code rate and interleaving depth, and the buffering used at the wireless-wireline interface, are examined. In addition to considering static bandwidth sharing as in conventional time division multiplexed (TDM) systems, we provide two mechanisms for statistical multiplexing that lead to significant capacity gains.