A UNIFIED ALGORITHM FOR THE ESTIMATION AND SCHEDULING OF DATA FLOW GRAPHS

We consider a wireless base station serving L users through L time-varying channels. It is well known that opportunistic scheduling algorithms with full channel state information (CSI) can stabilize the system and achieve the full capacity region. However, opportunistic scheduling algorithms with full CSI may not be energy efficient when the cost of channel acquisition is high and traffic rates are low. In particular, under the low traffic rate regime, it may be sufficient and more energy-efficient to transmit data with no CSI, i.e., to transmit data blindly, since no power for channel acquisition is consumed. In general, we show that purely channel-aware or purely channel-blind strategies are not necessarily optimal, and we must consider mixed strategies. We derive a unified scheduling algorithm that dynamically chooses to transmit data with full or no CSI based on queue backlog and channel statistics. Through Lyapunov analysis, we show that the unified algorithm can stabilize the downlink with optimal power consumption.

In Static List Scheduling (SLS), initially the ALAP (As Late As Possible) algorithm is performed, followed by ASAP (As Soon As Possible) algorithm. The time interval for control steps and successor selection are the vital drawback of ASAP algorithm. Hence, in this paper, the optimized scheduling algorithm is proposed for High Level Synthesis (HLS), where the ALAP in SLS is followed by Force Directed Scheduling (FDS). The proposed scheduling algorithm is implemented in Icarus Verilog and targeted in ZC7020 FPGA board. The proposed optimized scheduling algorithm is evaluated in terms of control steps and resource utilization. The evaluation is carried out for various benchmarks such as, EW Filter, IIR filter, FIR filter, AR filter and Discrete Cosine Transform (DCT). The achieved results in terms of the control steps and resource utilization (i.e. LUT and Flip-flop) shows the proposed optimized scheduling algorithm outperforms the conventional Static List Scheduling (SLS) algorithm.

In this paper, we present a new scheduling algorithm that generates area-efficient register transfer level datapaths with multiport memories. The proposed scheduling algorithm assigns an operation to a specific control step such that maximal sharing of functional units can be achieved with minimal number of memory ports, while satisfying given constraints. We propose a measure of multiport memory cost, MAV (Multiple Access Variable) which is defined as a variable accessed at several control steps, and overall memory cost is reduced by equally distributing the MAVs throughout all the control steps. When compared with previous approaches for several benchmarks available from the literature, the proposed algorithm generates the datapaths with less memory modules and interconnection structures by reflecting the memory cost in the scheduling process.

A Unified NN Model and Algorithm for Scheduling in Manufacturing

This paper addresses the problem of scheduling real-time wireless flows under dynamic network conditions and general traffic patterns. The objective is to maximize the fraction of packets of each flow to be delivered within their deadlines, referred to as timely-throughput. The scheduling problem under restrictive frame-based traffic models or greedy maximal scheduling schemes like LDF has been extensively studied so far, but scheduling algorithms to provide deadline guarantees on packet delivery for general traffic under dynamic network conditions are very limited. We propose two scheduling algorithms using deep reinforcement learning approach to optimize timely-throughput for general traffic in dynamic wireless networks: RL-Centralized scheduling algorithm and RL-Decentralized scheduling algo-rithm. Specifically, we formulate the centralized scheduling problem as a Markov Decision Process (MDP) and a multi-environments double deep Q-network (ME-DDQN) structure is proposed to adapt to the dynamic network conditions. The decentralized scheduling problem is formulated as a Partially Observable Markov Decision Process (POMDP) and an expert-apprentice centralized training and decentralized execution (EA-CTDE) structure is designed to accelerate the training speed and achieve the optimal timely-throughput. The extensive results show that the proposed scheduling algorithms converge fast and adapt well to network dynamics with superior performance compared to baseline policies. Finally, experimental tests confirm simulation results and also show that the proposed algorithms are feasible in practice on resource limited platforms.

We consider the problem of designing a joint congestion control and scheduling algorithm for multihop wireless networks. The goal is to maximize the total utility and achieve low end-to-end delay simultaneously. Assume that there are M flows inside the network, and each flow m has a fixed route with H m hops. Further, the network operates under the one-hop interference constraint. We develop a new congestion control and scheduling algorithm that combines a window-based flow control algorithm and a new distributed rate-based scheduling algorithm. For any e, e m ∈ (0, 1), by appropriately choosing the number of backoff mini-slots for the scheduling algorithm and the window-size of flow m, our proposed algorithm can guarantee that each flow m achieves throughput no smaller than r m (1 ™ e)(1 − e m ), where the total utility of the rate allocation vector ƒr = [r m ] is no smaller than the total utility of any rate vector within half of the capacity region. Furthermore, the end-to-end delay of flow m can be upper bounded by H m /(r m (1 − e)e m ). Since a flow-m packet requires at least H m time slots to reach the destination, the order of the per-flow delay upper bound is optimal with respect to the number of hops. To the best of our knowledge, this is the first fully-distributed joint congestion-control and scheduling algorithm that can guarantee order-optimal per-flow end-to-end delay and utilize close-to-half of the system capacity under the one-hop interference constraint. The throughput and delay bounds are proved by a novel stochastic dominance approach, which could be of independent value and be extended to general interference constraints. Our algorithm can be easily implemented in practice with a low per-node complexity that does not increase with the network size.

We consider the scheduling problem in a new slotted optical network called TWIN. The TWIN architecture possesses interesting properties, which may offer solutions for next-generation optical networks. Besides, TWIN has the ability to support quality of service (QoS) by controlling two important parameters: queueing delay and delay variance. However, to the best of our knowledge, the existing scheduling algorithms in TWIN focused mainly on maximizing the throughput and ignored the consideration of QoS. We formulate the scheduling problem into an integer linear programming problem and propose a heuristic--virtual topology-based dynamic scheduling (VTBDS) algorithm to solve it fast and efficiently. Besides, we derive an analytical model for TWIN and investigate the performance of VTBDS in it. By means of simulations, we demonstrate that our model approximates the TWIN network very well, and VTBDS incurs smaller queueing delay and delay variance, which are advantageous for guaranteeing better QoS.

More and more applications of grid have been achieved. How to support Quality of Service (QoS) to meet different users' demand has raised an outstanding challenge. Currently, several QoS policies of resource have been widely used in Grid. Thus, how to use them freely and efficiently is a serious problem. In this study, we illustrated three QoS policies of resources: best effort, real time, and competing, and explain their mechanisms. Following this, we proposed a new QoS policy, namely Free QoS policy, to help the user who is not very familiar with QoS polices. The first step is that we can get the matrix of QoS parameters of each resource from the Policy Pool in which all the information about QoS policies of resources in “virtual organizations” could be obtained. Second, we will calculate every resource's P adjugment value by a comparison algorithm. Finally, the QoS policy matching the maximum value of P adjugment value is the user's decision. After choosing a suitable resource with a clear QoS policy, the next question is how to achieve an optimum quality under the given policy, which is the problem of scheduling. Min_Min algorithm has been widely used as a higher efficiency and simple algorithm. However, it has a serious problem: load unbalance. In order to solve the problem, we propose a novel task scheduling algorithm, called the Heuristic task scheduling algorithm based on Min-Min and Max-Min (H-MM) in the best effort of the QoS policy, which is merged with the high efficiency of the traditional Min-Min scheduling algorithm and the load balance of the traditional Max-Min scheduling algorithm. Through plenty of experiments, we know that the performance of Max-Min is better than that of Min-Min in the condition that the values of ETC are not uniform, and the performance of Min-Min is a priority to Max-Min when there are many tasks in which the value of ETC are uniform. In this paper, we take the relative standard deviation value of ETC matrix's Min_Time as the criterion to judge whether the set of tasks is uniform or not. Finally, the scheduler selects the Max-Min or Min-Min to assign tasks. The experiments have shown that the H-MM algorithm overweighs traditional algorithms a lot in the makespan and the scalability of the scheduling algorithm.

We consider the problem of scheduling all-to-all personalized connections (AAPC) in WDM rings. Scheduling one connection for every source-destination pair in a network of limited connectivity provides a way to reduce routing control and guarantee throughput. For a given number of wavelengths K and a given number of transceivers per node T, we first determine the lower bound (LB) on the schedule length, which depends on both K and T. To achieve the LB, either the network bandwidth, the I/O capacity, or both should be fully utilized. This approach first constructs and then schedules circles, each of which is formed by up to four non-overlapping connections and can fully utilize the bandwidth of one wavelength. The proposed circle construction and scheduling algorithms can achieve the LB if K/spl les/T<N-1 or T=N-1, and closely approach or achieve the LB otherwise. In addition, we determine the appropriate values of T and K for the cost-effective designs in WDM rings through analysis of the schedule length and network throughput.

Many applications involve the concepts of scheduling, such as communications, packet routing, production planning [Zhai et al., 2006], classroom arrangement [Mathaisel & Comm, 1991], aircrew scheduling [Chang, 2002], nurse scheduling [Ohki et al., 2006], food industrial [Simeonov & Simeonovova, 2002], control system [Fleming & Fonseca, 1993], resource-constrained scheduling problem [Chen, 2007] and grid computing. There are many different types of scheduling problems such as real-time, job-shop, permutation flow-shop, project scheduling and other scheduling problems have been studied intensively. However, in this work, the studied grid task scheduling problem is much more complex than above stated classic task scheduling problems. Restated, a grid application is regarded as a task scheduling problem involving tasks with inter-communication and distributed homogeneous or heterogeneous resources, and can be represented by a task interaction graph (TIG). Grid is a service for sharing computing power and data storage capacity over the Internet. The grid systems outperform simple communication between computers and aims ultimately to turn the global network of computers into one vast computational resource. Grid computing can be adopted in many applications, such as high-performance applications, large-output applications, data-intensive applications and community-centric applications. These applications major concern to efficiently schedule tasks over the available multi-processor environment provided by the grid. A grid is a collaborative environment in which one or more tasks can be submitted without knowing where the resources are or even who owns the resources [Foster et al., 2001]. The efficiency and effectiveness of grid resource management greatly depend on the scheduling algorithm [Lee et al., 2007]. Generally, in the grid environment, these resources are different over time, and such changes will affect the performance of the tasks running on the grid. In grid computing, tasks are assigned among grid system [Salman, 2002]. The purpose of task scheduling in grid is to find optimal task-processor assignment and hence minimize application completion time (total cost). Most scheduling problems in these applications are categorized into the class of NP-complete problems. This implies that it would take amount of computation time to obtain an optimal solution, especially for a large-scale scheduling problem. A variety of approaches have been applied to solve scheduling problems, such as

Online decision-making in the presence of uncertain future information is abundant in many problem domains. In the critical problem of energy generation scheduling for microgrids, one needs to decide when to switch energy supply between a cheaper local generator with startup cost and the costlier on-demand external grid, considering intermittent renewable generation and fluctuating demands. Without knowledge of future input, competitive online algorithms are appealing as they provide optimality guarantees against the optimal offline solution. In practice, however, future input, e.g., wind generation, is often predictable within a limited time window, and can be exploited to further improve the competitiveness of online algorithms. In this paper, we exploit the structure of information in the prediction window to design a novel prediction-aware online algorithm for energy generation scheduling in microgrids. Our algorithm achieves the best competitive ratio to date for this important problem, which is at most $3-2/(1+\mathcal{O}(\frac{1}{w})),$ where $w$ is the prediction window size. We also characterize a non-trivial lower bound of the competitive ratio and show that the competitive ratio of our algorithm is only $9\%$ away from the lower bound, when a few hours of prediction is available. Simulation results based on real-world traces corroborate our theoretical analysis and highlight the advantage of our new prediction-aware design.

ObjectivesAiming at the operation support scheduling of carrier-based aircraft, this paper proposes a scheduling optimization algorithm based on apprenticeship learning which can quickly generate a operation support schedule for a carrier-based aircraft fleet. MethodsUsing the apprenticeship learning method, the executed and unexecuted tasks in expert demonstrations are compared in pairs to construct a sample set, and the support task scheduling classifier is trained based on the deck features of aircraft carrier. On this basis, a support task apprenticeship learning algorithm for a carrier-based aircraft fleet is designed and compared with the traditional genetic algorithm （GA） in terms of solving solution, solving time and resource allocation. ResultsThe results show that the operation support schedule obtained by the apprenticeship scheduling algorithm is equivalent to that by the traditional GA, but the rate of convergence is increased nearly fourfold, and the support resources are more evenly distributed. ConclusionsThe apprenticeship scheduling algorithm proposed in this paper can adequately learn from expert experiences and solve the problem of static single-objective carrier-based aircraft support scheduling. As such, this study provides references for further research in the field of dynamic multi-objective carrier-based aircraft support scheduling.

A new evolutionary algorithm for scheduling and allocation algorithm is developed for an elliptic filter. The elliptic filter is scheduled and allocated in the proposed work which is then compared with the different scheduling algorithms like As Soon As Possible algorithm, As Late As Possible algorithm, Mobility Based Shift algorithm, FDLS, FDS and MOGS. In this paper execution time and resource utilization is calculated using different scheduling algorithm for an Elliptic Filter and reported that proposed Scheduling and Allocation increases the speed of operation by reducing the control step. The proposed work to analyse the magnitude, phase and noise responses for different scheduling algorithm in an elliptic filter.

This paper presents a high-level synthesizer to map a complete program efficiently on a dynamically reconfigurable processor (DRP). Initially, we introduce our DRP architecture, which is suitable for control-intensive programs since it has a stand-alone finite state machine that switches “contexts” consisting of many processing elements (PEs). Then, we propose three new techniques optimized for our DRP. Firstly, we explain how synthesized control steps are mapped onto the contexts. Several control steps are combined as a context to utilize PEs efficiently since each control step does not require the same amount of operational units. Secondly, we describe a modulo scheduling algorithm for loop pipelining, considering both spatial and time dimensions of our DRP. Lastly, we explain a scheduling technique to optimize clock frequency, which can take advantage of multiplexer, wire and routing switch delays. We have demonstrated a JPEG-based image decoder example to evaluate our methods. Experimental results show that high area efficiency is achieved by balancing the number of PEs between contexts. Despite an overall increase in performance on pipelining of 3.6 times that without pipelining, the number of operational units increased by a factor of 2.2. The clock frequency is maximized with accurate delay estimation.

In recent years, people have paid more and more attention to traditional manufacturing's environmental impact, especially in terms of energy consumption and related emissions of carbon dioxide. Except for adopting new equipment, production scheduling could play an important role in reducing the total energy consumption of a manufacturing plant. Machine tools waste a considerable amount of energy because of their underutilization. Consequently, energy saving can be achieved by switching machines to standby or off when they lay idle for a comparatively long period. Herein, we first introduce the objectives of minimizing non-processing energy consumption, total weighted tardiness and earliness, and makespan into a typical production scheduling model-the job shop scheduling problem, based on a machine status switching framework. The multi-objective genetic algorithm U-NSGA-III combined with MME (a heuristic algorithm combined with the MinMax (MM) and Nawaz-Enscore-Ham (NEH) algorithms) population initialization method is used to solve the problem. The multi-objective optimization algorithm can generate a Pareto set of solutions so that production managers can flexibly select a schedule from these non-dominated schedules based on their priorities. Three sets of numerical experiments have been carried out on the extended Taillard benchmark to verify this three-objective model's effectiveness and the multi-objective optimization algorithm. The results show that U-NSGA-III has obtained better Pareto solutions in most test problem instances than NSGA-II and NSGA-III. Furthermore, the non-processing energy consumption is reduced by 46%-69%, which is 13-83% of the total energy consumption.