Focused Prefetching: Performance Oriented Prefetching Based On Commit Stalls

Loads that miss in L1 or L2 caches and waiting for their data at the head of the ROB cause significant slow down in the form of commit stalls. We identify that most of these commit stalls are caused by a small set of loads, referred to as LIMCOS (Loads Incurring Majority of COmmit Stalls). We propose simple history-based classifiers that track commit stalls suffered by loads to help us identify this small set of loads. We study an application of these classifiers to prefetching. The classifiers are used to train the prefetcher to focus on the misses suffered by LIMCOS. This, referred to as focused prefetching, results in a 9.8% gain in IPC over naive GHB based delta correlation prefetcher along with a 20.3% reduction in memory traffic for a set of 17 memory-intensive SPEC2000 benchmarks. Another important impact of focused prefetching is a 61% improvement in the accuracy of prefetches. We demonstrate that the proposed classification criterion performs better than other existing criteria like criticality and delinquent loads. Also we show that the criterion of focusing on commit stalls is robust enough across cache levels and can be applied to any prefetcher without any modifications to the prefetcher.

Modeling Finite Buffer Effects on TCP Traffic over an IEEE 802.11 Infrastructure WLAN

The network scenario is that of an infrastructure IEEE 802.11 WLAN with a single AP with which several stations (STAs) are associated. The AP has a finite size buffer for storing packets. In this scenario, we consider TCP controlled upload and download file transfers between the STAs and a server on the wireline LAN (e.g., 100 Mbps Ethernet) to which the AP is connected. In such a situation, it is known (see, for example, (3), [9]) that because of packet loss due to finite buffers at the Ap, upload file transfers obtain larger throughputs than download transfers. We provide an analytical model for estimating the upload and download throughputs as a function of the buffer size at the AP. We provide models for the undelayed and delayed ACK cases for a TCP that performs loss recovery only by timeout, and also for TCP Reno.

Enhancing 'Mobility' through Integrated Transportation and Traffic Management

During the course of preparation of a master plan for the transportation networks in Bangalore city, mapping the various initiatives and interventions planned towards addressing mobility, existing situation and implications of some of the proposed interventions was analysed. The inferences are based on existing transportation network; synthesis of various transportation related studies and proposed infrastructure initiatives (road works) in Bangalore. Broadly, they can be summarized as following five aspects: I. Need for ~Sreclassifying~T existing road networks (arterial and sub-arterial) with effective geospatial database in the back-end. II. The proposed Core Ring Road at surface grade may not be feasible. III. Current interventions encouraging more independent motorable transport by way of road widening, construction of underpasses, flyovers and grade-separators would not ease traffic congestion when addressed in isolation. IV. Factors affecting time and cost-overruns in infrastructure projects and ways to tackle are discussed. V. Initiatives required for addressing effective planning for operations recommended.

Cellular Automata Models of Traffic Behavior in Presence of Speed Breaking Structures

In this article, we study traffic flow in the presence of speed breaking structures. The speed breakers are typically used to reduce the local speed of vehicles near certain institutions such as schools and hospitals. Through a cellular automata model we study the impact of such structures on global traffic characteristics. The simulation results indicate that the presence of speed breakers could reduce the global flow under moderate global densities. However, under low and high global density traffic regime the presence of speed breakers does not have an impact on the global flow. Further the speed limit enforced by the speed breaker creates a phase distinction. For a given global density and slowdown probability, as the speed limit enforced by the speed breaker increases, the traffic moves from the reduced flow phase to maximum flow phase. This underlines the importance of proper design of these structures to avoid undesired flow restrictions.

Modeling finite buffer effects on TCP traffic over an IEEE 802.11 infrastructure WLAN

The network scenario is that of an infrastructure IEEE 802.11 WLAN with a single AP with which several stations (STAs) are associated. The AP has a finite size buffer for storing packets. In this scenario, we consider TCP-controlled upload and download file transfers between the STAs and a server on the wireline LAN (e.g., 100 Mbps Ethernet) to which the AP is connected. In such a situation, it is well known that because of packet losses due to finite buffers at the AP, upload file transfers obtain larger throughputs than download transfers. We provide an analytical model for estimating the upload and download throughputs as a function of the buffer size at the AP. We provide models for the undelayed and delayed ACK cases for a TCP that performs loss recovery only by timeout, and also for TCP Reno. The models are validated incomparison with NS2 simulations.

Macroscopic model of city traffic using bond graph modelling

Modelling of city traffic involves capturing of all the dynamics that exist in real-time traffic. Probabilistic models and queuing theory have been used for mathematical representation of the traffic system. This paper proposes the concept of modelling the traffic system using bond graphs wherein traffic flow is based on energy conservation. The proposed modelling approach uses switched junctions to model complex traffic networks. This paper presents the modelling, simulation and experimental validation aspects.

The effect of traffic shaping in efficiently providing end-to-end performance guarantees

This paper reports new results concerning the capabilities of a family of service disciplines aimed at providing per-connection end-to-end delay (and throughput) guarantees in high-speed networks. This family consists of the class of rate-controlled service disciplines, in which traffic from a connection is reshaped to conform to specific traffic characteristics, at every hop on its path. When used together with a scheduling policy at each node, this reshaping enables the network to provide end-to-end delay guarantees to individual connections. The main advantages of this family of service disciplines are their implementation simplicity and flexibility. On the other hand, because the delay guarantees provided are based on summing worst case delays at each node, it has also been argued that the resulting bounds are very conservative which may more than offset the benefits. In particular, other service disciplines such as those based on Fair Queueing or Generalized Processor Sharing (GPS), have been shown to provide much tighter delay bounds. As a result, these disciplines, although more complex from an implementation point-of-view, have been considered for the purpose of providing end-to-end guarantees in high-speed networks. In this paper, we show that through ''proper'' selection of the reshaping to which we subject the traffic of a connection, the penalty incurred by computing end-to-end delay bounds based on worst cases at each node can be alleviated. Specifically, we show how rate-controlled service disciplines can be designed to outperform the Rate Proportional Processor Sharing (RPPS) service discipline. Based on these findings, we believe that rate-controlled service disciplines provide a very powerful and practical solution to the problem of providing end-to-end guarantees in high-speed networks.

Queuing strategies for qos management of traffic between lans interconnected by low-speed wan links

We provide a comparative performance evaluation of packet queuing and link admission strategies for low-speed wide area network Links (e.g. 9600 bps, 64 kbps) that interconnect relatively highspeed, connectionless local area networks (e.g. 10 Mbps). In particular, we are concerned with the problem of providing differential quality of service to interLAN remote terminal and file transfer sessions, and throughput fairness between interLAN file transfer sessions. We use analytical and simulation models to study a variety of strategies. Our work also serves to address the performance comparison of connectionless vs. connection-oriented interconnection of CLNS LANS. When provision of priority at the physical transmission level is not feasible, we show, for low-speed WAN links (e.g. 9600 bps), the superiority of connection-oriented interconnection of connectionless LANs, with segregation of traffic streams with different QoS requirements into different window flow controlled connections. Such an implementation can easily be obtained by transporting IP packets over an X.25 WAN. For 64 kbps WAN links, there is a drop in file transfer throughputs, owing to connection overheads, but the other advantages are retained, The same solution also helps to provide throughput fairness between interLAN file transfer sessions. We also provide a corroboration of some of our modelling results with results from an experimental test-bed.

Saturation throughput analysis of an input queueing ATM switch with multiclass bursty traffic

In this paper we consider an N x N non-blocking, space division ATM switch with input cell queueing. At each input, the cell arrival process comprises geometrically distributed bursts of consecutive cells for the various outputs. Motivated by the fact that some input links may be connected to metropolitan area networks, and others directly to B-ISDN terminals, we study the situation where there are two classes of inputs with different values of mean burst length. We show that when inputs contend for an output, giving priority to an input with smaller expected burst length yields a saturation throughput larger than if the reverse priority is given. Further, giving priority to less bursty traffic can give better throughput than if all the inputs were occupied by this less bursty traffic. We derive the asymptotic (as N --> infinity) saturation throughputs for each priority class.

Reinforcement Learning With Function Approximation for Traffic Signal Control

We propose, for the first time, a reinforcement learning (RL) algorithm with function approximation for traffic signal control. Our algorithm incorporates state-action features and is easily implementable in high-dimensional settings. Prior work, e. g., the work of Abdulhai et al., on the application of RL to traffic signal control requires full-state representations and cannot be implemented, even in moderate-sized road networks, because the computational complexity exponentially grows in the numbers of lanes and junctions. We tackle this problem of the curse of dimensionality by effectively using feature-based state representations that use a broad characterization of the level of congestion as low, medium, or high. One advantage of our algorithm is that, unlike prior work based on RL, it does not require precise information on queue lengths and elapsed times at each lane but instead works with the aforementioned described features. The number of features that our algorithm requires is linear to the number of signaled lanes, thereby leading to several orders of magnitude reduction in the computational complexity. We perform implementations of our algorithm on various settings and show performance comparisons with other algorithms in the literature, including the works of Abdulhai et al. and Cools et al., as well as the fixed-timing and the longest queue algorithms. For comparison, we also develop an RL algorithm that uses full-state representation and incorporates prioritization of traffic, unlike the work of Abdulhai et al. We observe that our algorithm outperforms all the other algorithms on all the road network settings that we consider.

Recommendations for driver licensing and traffic law enforcement in India aiming to improve road safety

During the last decade, developing countries such as India have been exhibiting rapid increase in human population and vehicles, and increase in road accidents. Inappropriate driving behaviour is considered one of the major causes of road accidents in India as compared to defective geometric design of pavement or mechanical defects in vehicles. It can result in conditions such as lack of lane discipline, disregard to traffic laws, frequent traffic violations, increase in crashes due to self-centred driving, etc. It also demotivates educated drivers from following good driving practices. Hence, improved driver behaviour can be an effective countermeasure to reduce the vulnerability of road users and inhibit crash risks. This article highlights improved driver behaviour through better driver education, driver training and licensing procedures along with good on-road enforcement; as an effective countermeasure to ensure road safety in India. Based on the review and analysis, the article also recommends certain measures pertaining to driver licensing and traffic law enforcement in India aimed at improving road safety.

Throughput Maximization of Delay-Constrained Traffic in Wireless Energy Harvesting Sensors

A wireless Energy Harvesting Sensor (EHS) needs to send data packets arriving in its queue over a fading channel at maximum possible throughput while ensuring acceptable packet delays. At the same time, it needs to ensure that energy neutrality is satisfied, i.e., the average energy drawn from a battery should equal the amount of energy deposited in it minus the energy lost due to the inefficiency of the battery. In this work, a framework is developed under which a system designer can optimize the performance of the EHS node using power control based on the current channel state information, when the EHS node employs a single modulation and coding scheme and the channel is Rayleigh fading. Optimal system parameters for throughput optimal, delay optimal and delay-constrained throughput optimal policies that ensure energy neutrality are derived. It is seen that a throughput optimal (maximal) policy is packet delay-unbounded and an average delay optimal (minimal) policy achieves negligibly small throughput. Finally, the influence of the harvested energy profile on the performance of the EHS is illustrated through the example of solar energy harvesting.

Analytical models for energy consumption in infrastructure WLAN STAs carrying TCP traffic

We develop analytical models for estimating the energy spent by stations (STAs) in infrastructure WLANs when performing TCP controlled file downloads. We focus on the energy spent in radio communication when the STAs are in the Continuously Active Mode (CAM), or in the static Power Save Mode (PSM). Our approach is to develop accurate models for obtaining the fraction of times the STA radios spend in idling, receiving and transmitting. We discuss two traffic models for each mode of operation: (i) each STA performs one large file download, and (ii) the STAs perform short file transfers. We evaluate the rate of STA energy expenditure with long file downloads, and show that static PSM is worse than just using CAM. For short file downloads we compute the number of file downloads that can be completed with given battery capacity, and show that PSM performs better than CAM for this case. We provide a validation of our analytical models using the NS-2 simulator.

Modeling urban traffic planning thro' strategic decisions- A case from Bangalore, India

This paper deals with reducing the waiting times of vehicles at the traffic junctions by synchronizing the traffic signals. Strategies are suggested for betterment of the situation at different time intervals of the day, thus ensuring smooth flow of traffic. The concept of single way systems are also analyzed. The situation is simulated in Witness 2003 Simulation package using various conventions. The average waiting times are reduced by providing an optimal combination for the traffic signal timer. Different signal times are provided for different times of the day, thereby further reducing the average waiting times at specific junctions/roads according to the experienced demands.

Reinforcement learning with average cost for adaptive control of traffic lights at intersections

We propose for the first time two reinforcement learning algorithms with function approximation for average cost adaptive control of traffic lights. One of these algorithms is a version of Q-learning with function approximation while the other is a policy gradient actor-critic algorithm that incorporates multi-timescale stochastic approximation. We show performance comparisons on various network settings of these algorithms with a range of fixed timing algorithms, as well as a Q-learning algorithm with full state representation that we also implement. We observe that whereas (as expected) on a two-junction corridor, the full state representation algorithm shows the best results, this algorithm is not implementable on larger road networks. The algorithm PG-AC-TLC that we propose is seen to show the best overall performance.