Performance evaluation of a switch using priority-based dynamic capacity allocation scheme

WDM-PONs deploying tunable lasers enable incremental bandwidth upgrade to more efficiently meet the long-term growth of user demand. We propose in this paper two dynamic wavelength allocation schemes which allow total sharing and fair sharing of the tunable wave-lengths, respectively, in such WDM-PONs. We also develop an exact analytical model based on a multi-dimensional Markov chain to evaluate the packet dropping probability under these two schemes. Validated by simulations, the analytical model is used to compare the performance of the two schemes under different traffic loads and buffer capacities, and demonstrate the efficacy of the scheme allowing fair sharing.

This paper presents a framework for allocating radio resources to the Access Points (APs) introducing an Access Point Controller (APC). Radio resources can be either time slots or subchannels. The APC assigns subchannels to the APs using a dynamic subchannel allocation scheme. The developed framework evaluates the dynamic subchannel allocation scheme for a downlink multicellular Orthogonal Frequency Division Multiple Access (OFDMA) system. In the considered system, each AP and the associated Mobile Terminals (MTs) are not operating on a frequency channel with fixed bandwidth, rather the channel bandwidth for each AP is dynamically adapted according to the traffic load. The subchannels assignment procedure is based on quality estimations due to the interference measurements and the current traffic load. The traffic load estimation is realized with the measurement of the utilization of the assigned radio resources. The reuse partitioning for the radio resources is done by estimating mutual Signal to Interference Ratio (SIR) of the APs. The developed dynamic subchannel allocation ensures Quality of Service (QoS), better traffic adaptability, and higher spectrum efficiency with less computational complexity.

In video-on-demand (VOD) systems, as the size of the buffer allocated to user requests increases, initial latency and memory requirements increase. Hence, the buffer size must be minimized. The existing static buffer allocation scheme, however, determines the buffer size based on the assumption that the system is in the fully loaded state. Thus, when the system is in a partially loaded state, the scheme allocates a buffer larger than necessary to a user request. This paper proposes a dynamic buffer allocation scheme that allocates to user requests buffers of the minimum size in a partially loaded state as well as in the fully loaded state. The inherent difficulty in determining the buffer size in the dynamic buffer allocation scheme is that the size of the buffer currently being allocated is dependent on the number of and the sizes of the buffers to be allocated in the next service period. We solve this problem by the predict-and-enforce strategy, where we predict the number and the sizes of future buffers based on inertia assumptions and enforce these assumptions at runtime. Any violation of these assumptions is resolved by deferring service to the violating new user request until the assumptions are satisfied. Since the size of the current buffer is dependent on the sizes of the future buffers, the size is represented by a recurrence equation. We provide a solution to this equation, which can be computed at the system initialization time for runtime efficiency. We have performed extensive analysis and simulation. The results show that the dynamic buffer allocation scheme reduces initial latency (averaged over the number of user requests in service from one to the maximum capacity) to 1 ÷ 29.4 n 1 ÷ 11.0 of that for the static one and, by reducing the memory requirement, increases the number of concurrent user requests to 2.36 ∼ 3.25 times that of the static one when averaged over the amount of system memory available. These results demonstrate that the dynamic buffer allocation scheme significantly improves the performance and capacity of VOD systems.

This article investigates resource allocation in ATM networks and emphasizes bandwidth allocation. Resource allocation methods are categorized, and static and dynamic allocation strategies are compared. Dynamic allocation uses actual traffic behavior, while static allocation uses only the reference traffic condition given a priori. Examples of dynamic allocation strategies are available bit rate flow control, dynamic connection admission control, and dynamic VP bandwidth control. Dynamic resource allocation is shown to be promising for situations where the a priori reference model is unclear.

In wavelength division multiplexing broadcast‐and‐select star networks, the all‐to‐all transmission schedule is suitable for the uniform traffic pattern. The system performance is seriously degraded for the non‐uniform traffic patterns. Based on the demand assignment control, a dynamic packet allocation algorithm is proposed for the all‐to‐all transmission schedule. The algorithm decomposes the traffic matrix into a transmission matrix, and a residual matrix with a simple procedure. The transmission matrix is with most entries to approach the uniform traffic matrix. Within the transmission matrix, the idle time slots could be shared with the heavy‐load input nodes to increase the packet transmission. The simulation results show that the system with applying the algorithm could efficiently promote the performance on throughput, packet delay and buffer size for non‐uniform traffic patterns. Copyright © 2006 AEIT

This paper proposes a new backward‐type speech coding system (ADPCM‐AB) for wideband (7 kHz) speech and sound signals. In this system, a split‐band adaptive predictive coding scheme with gradient PARCOR lattice filter and a dynamic bit allocation scheme are employed, where quantization bits are dynamically allocated over the subbands (frequency), the subintervals (time), and the channels (stereo) in accordance with the distribution of the residual energies. They serve to remove the redundancies due to the periodic concentration of the prediction residual energy and the nonuniform nature of the speech spectrum. The ADPCM‐AB needs neither longer delay time than 4 ms nor transmission of side information parameters because the parameters for predictive coding and dynamic bit allocation are calculated with the locally decoded signals. It is clarified that the ADPCM‐AB system has the best speech quality among the conventional backward‐type coding systems. It is also shown that this system provides speech quality subjectively equivalent to 11‐bit linear PCM (176 kb/s) at 64 kb/s.

Presents the results of an evaluation of several agent-based dynamic task allocation strategies which we have developed for information systems spread over the Internet or other wide area networks (WANs). These strategies are based on the cooperation of agents organized in one community of reactive agents and another community of allocator agents, and on the learning skills of the allocator agents. Reactive agents represent the services available on WANs such as Internet. Allocator agents are able to cooperate and to learn about the states of the reactive agents. We compare our multi-agent-based strategies with negotiation-based dynamic task allocation strategies, by simulation. The results of this evaluation show that our strategies reduce the amount of message sending.

To improve the service efficiency of planar automated multi-storey parking systems, a nonlinear dynamic slot allocation strategy is proposed, considering both vehicle dwell time and the balance of slot distribution. A long short-term memory (LSTM) neural network, with hyperparameters tuned by Bayesian optimization, is employed to predict the dwell times of vehicles parked in the system. Combining predicted dwell times with slot occupancy attributes, a fuzzy-theory-based partitioning rule is established, enabling nonlinear regional allocation based on dwell time and slot occupancy density. Additionally, a balance-detection algorithm and an adjacent-slot migration strategy are designed to assess the balance of slot utilization and dynamically adjust partitioned slot occupancy. Using the average running energy consumption and average service time of the rail-guided vehicle (RGV), which performs vehicle storage and retrieval operations, as system efficiency metrics, a tabu search algorithm is applied to optimize the selection of vacant slots within each partition. Results show that, compared with the nearest-slot allocation strategy commonly used in engineering practice, the proposed method reduces the average service time by 14.3%, the average energy consumption by 23.8%, and the standard deviation of slot-occupancy balance by 90.28%, demonstrating the effectiveness of the dynamic slot allocation strategy that accounts for vehicle dwell time and balanced slot distribution.

For tandem queueing networks with generally distributed service times, decomposition often is the only feasible solution method besides simulation. The network is partitioned into individual nodes which are analysed in isolation. In existing decomposition algorithms for continuous-time networks, the output of a queue is usually approximated as a renewal process, which serves as the arrival process to the next queue. In this paper, the internal traffic processes are described as semi-Markov processes (SMPs) and Markov modulated Poisson processes (MMPPs). Thus, correlations in the traffic streams, which are known to have a considerable impact on performance, are taken into account to some extent. A two-state MMPP, which arises frequently in communications modeling, serves as input to the first queue of the tandem network. For tandem networks with infinite or finite buffers, stationary mean queue lengths at arbitrary time computed quasi-promptly by the decomposition component of the tool TimeNET are compared to simulation.KeywordsQueue LengthRenewal ProcessArrival ProcessLoss ProbabilityBusy PeriodThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

A new fuzzy-based dynamic power allocation strategy is designed for wireless sensor networks to optimize the lifetime in heterogeneous network environments. The dynamical strategy allocates the available energy resources using the residual energy of a specific node, the distance to the base station, and the intensity of the data traffic of the fuzzy system. The proposed strategy provides real-time decisions on the transmission power, routing paths, and sleep/wake cycles. The system with different network conditions has been demonstrated against traditional static schemes with the standard network lifetime. The fuzzy-based strategy shows a 15% improvement in packet delivery rate and a 20% reduction in end-to-end delay. The proposed adaptive approach provides a good energy conservation capability, especially for the change in node density under different network conditions. The fuzzy-based dynamic power allocation strategy makes WSNs more efficient and extends their lifetime in IoT applications.

In this paper, we introduce an uplink transmission model with mobile users, where each user maximizes his/her utility to achieve the best performance. We propose a power allocation scheme for each mobile user when all channel information is available. Moreover, we illustrate that one user would expect to predict the aggregate interference to maximize the utility when the channel information is incomplete. It is shown that this approach forms a game with incomplete information. We demonstrate the prediction rules that can help the mobile users dynamically adjust predictions and apply the Kalman filter to tackle measurement noises. We also illustrate the theoretical bound for the difference between the utility with prediction and that with complete information. Moreover, applying dynamic programming from control theory, we give a dynamic power allocation scheme based on the predictions. Simulation results indicate that our power allocation scheme with complete information and dynamic power allocation with predictions give better performance compared with the scheme with even power allocation. In addition, results under our dynamic power allocation scheme are close to those under the power allocation with complete information.

A dynamic power allocation scheme is proposed to maximise the energy efficiency (EE) for multi-antenna transmissions when both the imperfect channel estimation and feedback are considered. The lower bounded ergodic EE is given by the temporal correlation analysis from the Kalman estimation and the differential codebook-based feedback of the Gauss–Markov channel, based on which both the powers of data and training are adaptively optimised. Simulations show that the proposed dynamic power allocation scheme outperforms the traditional power allocation schemes.

Grid computing systems are a cost-effective alternative to traditional high-performance computing systems. However, the computing resources of a grid are usually far apart and connected by Wide Area Networks resulting in considerable communication delays. Hence, efficient allocation of jobs to computing resources for load balancing is essential in these grid systems. In this paper, two price-based dynamic job allocation schemes for computational grids are proposed whose objective is to minimize the execution cost for the grid users' jobs. One scheme tries to provide a system-optimal solution so that the expected price for the execution of all the jobs in the grid system is minimized, while the other tries to provide a job-optimal solution so that all the jobs in the system of the same size will be charged approximately the same expected price independent of the computers allocated for their execution to provide fairness. The performance of the proposed dynamic schemes is compared with static job allocation schemes using simulations.

Active Queue Management (AQM) is an effective mechanism to support end-to-end traffic congestion control in modern high-speed networks. The selection of different dropping functions and threshold values required for this scheme plays a critical role on its effectiveness. This paper proposes an analytical performance model for AQM using various dropping functions. The model uses a well-known Markov-Modulated Poisson Process (MMPP) to capture traffic burstiness and correlations. Extensive analytical results have indicated that exponential dropping function is a good choice for AQM to support efficient congestion control.

In this paper, we present the modelling of the dynamic behaviour of an ATM-based, multi-service UMTS core network with calls that belong to one of four service classes and arrive randomly. Arriving calls are granted service based on specific service class, required maximum and minimum bandwidth, and available network resources. Performance of priority-based dynamic capacity allocation, suitable for the wireless system supporting ATM-like traffic is analysed. Scheduling of the ATM cell transmission in each uplink TDMA frame is based on a priority scheme. GoS (blocking probability) and QoS (throughput) parameters for bandwidth sharing policy (BSP) are considered, and partial overlapped transmission link (POL) is implemented. In the modelling, the clustering procedure is developed based on Markov reward models (MRMs), enhanced by the self-organising vector quantification (VQ) and neural modelling. The optimal link occupancy probability distribution is calculated using the neural network, trained with Kohonen rules. Simulation and numerical results are shown.