Joseph S. Gomes

Scheduling Algorithms For Policy Driven QoS Support in HSDPA Networks

Increasing demand for high data-rate multimedia services has led to the emergence of high-speed data transfer features such as high-speed downlink packet access (HSDPA) for WCDMA networks. The role of the MAC-hs scheduler is vital in HSDPA in improving overall system performance. Using opportunistic scheduling to exploit multi-user diversity for efficient transmission of best effort services or considering user fairness constraints has been the main focus of most scheduling algorithms. However the need for strict QoS support for services such as streaming, gaming, and VoIP is growing. Service operators can enforce their own policies in meeting these QoS requirements. In this paper we introduce two QoS-aware policy driven scheduling algorithms. We developed an HSDPA system in OPNET, and implemented our scheduling algorithms along with other well-known algorithms. OPNET simulations show that unlike other schedulers, our strict and loose policy scheduling (SPS and LPS) algorithms comply with the policy constraints if allowed by radio conditions and cell capacity.

Adaptive optimization of join trees for multi-join queries over sensor streams

Data processing applications for sensor streams have to deal with multiple continuous data streams with inputs arriving at highly variable and unpredictable rates from various sources. These applications perform various operations (e.g. filter, aggregate, join, etc.) on incoming data streams in real-time according to predefined queries or rules. Since the data rate and data distribution fluctuate over time, an appropriate join tree for processing join queries must be adaptively maintained in response to dynamic changes to prevent rapid degradation of the system performance. In this paper, we address the problem of finding an optimal join tree that maximizes throughput for sliding window based multi-join queries over continuous data streams and prove its NP-Hardness. We present a dynamic programming algorithm, OptDP, which produces the optimal tree but runs in an exponential time in the number of input streams. We then present a polynomial time greedy algorithm, XGreedyJoin. We tested these algorithms in ARES, an adaptively re-optimizing engine for stream queries, which we developed by extending Jess (Jess is a popular RETE-based, forward chaining rule engine written in java). For almost all instances, trees from XGreedyJoin perform close to the optimal trees from OptDP, and significantly better than common heuristics-based XJoin algorithms.

Integrating admission control and packet scheduling for quality controlled streaming services in HSDPA networks

High-Speed Downlink Packet Access (HSDPA) uses a shared forward link packet data channel that can achieve peak data rates up to 14.4 Mbps. The newly introduced features that are key to reaching such high rates are link adaptation, Hybrid ARQ (HARQ) and fast scheduling. The decision to admit new users is still taken by the Radio Network Controller (RNC); however, the scheduling role has been moved to the base station (Node-B) for fast adaptability. Although in high speed cellular networks, opportunistic scheduling can exploit multi-user diversity to maximize throughput, with the growing need for strict QoS guarantees for services such as streaming, gaming, and VoIP, a balance should be struck between maximizing throughput and providing user satisfaction. Service operators can enforce their own policies in providing user satisfaction. In this paper, we consider a QoS-aware policy driven scheduling algorithm and its interaction with the admission control mechanism at the RNC. We developed a dynamic HSDPA network simulator in OPNET with link adaptation, HARQ, fast scheduling and quality based admission control. Our simulations show that even with the presence of an admission controller at RNC, the well-known proportional fairness (PF) algorithm dismally fails to provide user satisfaction for streaming services, whereas our Strict Policy Scheduling (SPS) algorithm substantially increases user satisfaction as intended by the admission controller while providing a significant cell capacity gain.

Cost-based Solution for Optimizing Multi-join Queries over Distributed Streaming Sensor Data

Sensors are envisioned to be at the center of distributed collaborative computing services involving time-critical decision support. Sensors are small devices with limited communication and computational capabilities that collect data on their neighboring physical world and send the data periodically to server machines. Sensors form a collaborative network with these servers, where the sensors gather information and the servers perform various operations (e.g. filter, aggregate, join etc) on the information streams in real-time according to predefined queries or rules. Sensor data streams are continuous, un-ending and have highly volatile characteristics. As a result, traditional database systems are inappropriate for handling queries for sensor streams, and several stream data management systems have been proposed in the literature. In this paper we focus on a special type of query, namely join queries, which is the most expensive query operator. Here, we address the problem of finding an optimal join tree that maximizes throughput for sliding window based multi-join queries over continuous sensor data streams. We present a polynomial time algorithm Fodp and three variants of Fodp. Our experiments in ARES show that for almost all instances, trees from Fodp and its variants perform close to the optimal trees from our exponential time algorithm OptDP (Gomes, 2006), and significantly better than existing XJoin based heuristic algorithms

A linear-time algorithm for optimal multi-channel access in Cognitive Radio Networks

Cognitive Radio Networks (CRNs) aim to maximize the utilization of existing wireless channels by allowing secondary users (SUs) to transmit when licensed primary users (PUs) are not using the same channels. An SU monitors the CRN channels, sensing PU presence to avoid interference and estimating the link quality before transmitting. It stops when one or more available channels with satisfactory link quality are found. Algorithms for making the optimal decision regarding when to stop exploring the channels and start transmitting are expensive in terms of time and space, which are both scarce in hardware-constrained SUs, such as mobile devices. In this paper, we propose a low-complexity algorithm, which utilizes link quality and PU-activity statistics of the CRN channels to pre-compute a set of decision thresholds that will aid the channel exploration phase in maximizing SU-throughput. Our algorithm takes quadratic time and space for offline computations and linear time and space for online processing, which makes it very suitable for space and energy constrained mobile SUs. Our extensive simulation study and analytical model matching the simulation results demonstrate our solutions validity by showing the closeness of throughput and delay performances with the optimum solution as well as solutions by the well-known backward induction method, which often runs in exponential time for offline computations.

Uplink Resource Management Design in Multi-access Wireless Networks

In this paper, we develop a new uplink resource management scheme in heterogeneous networking environments that support multiple radio access technologies (RATs). A common radio resource management (CRRM) model is utilized to handle uplink traffic in multi-access radio networks. To evaluate the effect and performance of CRRM, a simulation study is conducted on scenarios where different scheduling algorithms are applied with and without vertical handoffs through the aid of CRRM.

A Hybrid Reconfiguration Algorithm for Fast Continuous Query Processing

With increasing hardware capabilities and network capacity, applications operating on streams of data are becoming more prevalent in the computing industry. Used in areas from security such as packet-sniffing intrusion detection software packages to the financial world attempting to model the stock market to map out future trends, algorithms for processing these unbounded streams are growing in necessity. Traditional database management systems fall short, as they are limited to bounded data. Therefore, stream management systems are required, as well as algorithms to efficiently process these data streams. Furthermore, these algorithms must be agile, adaptive and suitable for a wide range of operating conditions. In this paper, we design a hybrid algorithm to find optimized join trees for continuous stream queries. Our experimental results show that this hybrid algorithm can generate more efficient join trees than its components under a wide range of varied conditions.

Maximizing Throughput for Queries over Streaming Sensor Data

Sensors are becoming ubiquitous, and increasingly integrated with our lives. Sensors usually send sampled data periodically using wireless connections to server machines. The servers perform various operations (e.g. filter, aggregate, join etc) on this data in real-time according to predefined queries or rules. In this paper, we address the problem of finding an optimal join tree that maximizes throughput for sliding window based multi-join queries over continuous sensor data streams. We develop a dynamic programming algorithm OptDP, that produces an optimal tree but runs in an exponential time in the number of input streams. We then present a polynomial time greedy algorithm XGreedyJoin. Our experiments in ARES show that for almost all instances, trees from XGreedyJoin perform close to the optimal trees from OptDP, and significantly better than existing XJoin based heuristic algorithms

Policy Driven Scheduling to Provide Differentiated QoS for Delay Sensitive Services in HSDPA

Increasing demand for high data-rate multimedia real time services has led to the use of asynchronous time shared channels in the forward link for real-time services in 3G wireless networks, such as HSDPA, EV-DO and EV-DV. While network service providers would like to impose operational policies on the packet schedulers based on QoS requirements by real-time services to maximize profit, existing schedulers are not capable to deal with such challenge due to time varying channel conditions and constraints on the total forward link transmit power. In this paper, we consider the problem of scheduling users on the forward link in a multiuser system where multiple users can be scheduled during each interval. We introduce a delay aware policy driven scheduling algorithm SPS-Delay (Strict Policy Scheduling for Delay) to support differentiated QoS requirements in the form of tolerable latency specified by the user applications. We developed an HSDPA system in OPNET, and implemented our scheduling algorithm along with other well- known algorithms. Our simulations show that SPS-Delay reduces packet drop rate by as much as 80% and increases the number of satisfied users by as much as 32% when compared to PF.

Finding Optimal Join Tree forMulti-Join Stream Queries in a Production System

Data Stream Management Systems (DSMS) handle a particular type of database applications that involve multiple continuous data streams with inputs arriving at highly variable and unpredictable rates. Since data rate fluctuates over time in this type of applications the appropriate join tree is crucial for maintaining high system throughput. We consider the problem of finding optimal join tree for performing count based sliding window multi-joins over continuous streams. We use a unit-time based cost model to evaluate the expected performance for a given join tree. We materialize all intermediate results assuming there is enough main memory to store all partial results and window buffers. We give a polynomial time algorithm that finds the optimal join tree under our cost model for a given noncommuting (single permutation) order of streams. This algorithm can be used in conjunction with any linear order producing heuristic to give the optimal tree for that order. Our algorithm is implemented in the Jess rule engine and an extensive experimental evaluation is provided.