Scheduling Mechanism Research Articles

Task Scheduling Mechanism Based on Reinforcement Learning in Cloud Computing

The explosive growth of users and applications in IoT environments has promoted the development of cloud computing. In the cloud computing environment, task scheduling plays a crucial role in optimizing resource utilization and improving overall performance. However, effective task scheduling remains a key challenge. Traditional task scheduling algorithms often rely on static heuristics or manual configuration, limiting their adaptability and efficiency. To overcome these limitations, there is increasing interest in applying reinforcement learning techniques for dynamic and intelligent task scheduling in cloud computing. How can reinforcement learning be applied to task scheduling in cloud computing? What are the benefits of using reinforcement learning-based methods compared to traditional scheduling mechanisms? How does reinforcement learning optimize resource allocation and improve overall efficiency? Addressing these questions, in this paper, we propose a Q-learning-based Multi-Task Scheduling Framework (QMTSF). This framework consists of two stages: First, tasks are dynamically allocated to suitable servers in the cloud environment based on the type of servers. Second, an improved Q-learning algorithm called UCB-based Q-Reinforcement Learning (UQRL) is used on each server to assign tasks to a Virtual Machine (VM). The agent makes intelligent decisions based on past experiences and interactions with the environment. In addition, the agent learns from rewards and punishments to formulate the optimal task allocation strategy and schedule tasks on different VMs. The goal is to minimize the total makespan and average processing time of tasks while ensuring task deadlines. We conducted simulation experiments to evaluate the performance of the proposed mechanism compared to traditional scheduling methods such as Particle Swarm Optimization (PSO), random, and Round-Robin (RR). The experimental results demonstrate that the proposed QMTSF scheduling framework outperforms other scheduling mechanisms in terms of the makespan and average task processing time.

Priority switching scheduler

SummaryWe define a novel core network router scheduling architecture called priority switching scheduler (PSS), to carry and isolate time constrained and elastic traffic flows from best‐effort traffic. To date, one possible solution has been to implement a core DiffServ network with standard fair queuing and scheduling mechanisms as proposed in the well‐known “A Differentiated Services Code Point (DSCP) for Capacity‐Admitted Traffic” from RFC5865. This architecture is one of the most selected solutions by internet service provider for access networks (e.g., customer‐premises equipment) and deployed within several performance‐enhancing proxies (PEPs) over satellite communications (SATCOM) architectures. In this study, we argue that the proposed standard implementation does not allow to efficiently quantify the reserved capacity for the AF class. By using a novel credit‐based shaper mechanism called burst limiting shaper (BLS) to manage the AF class, we show that PSS can provide the same isolation for the time constrained EF class while better quantifying the part allocated to the AF class. PSS operates both when the output link capacity is fixed (e.g., wire links and terrestrial networks) or might vary due to system impairments or weather condition (e.g., wireless or satellite links). We demonstrate the capability of PSS through an emulated SATCOM scenario with variable capacity and show the AF output rate is less dependent on the EF traffic, which improves the quantification of the reserved capacity of AF, without impacting EF traffic.

Synergistic effect of complementary cleaner energy sources on controllable emission from hybrid power systems in optimal power flow framework

The increased penetration of renewable energy resources into the power system may make the system operation extremely vulnerable due to their inherent volatility and variability. Thus, optimum utilization of cleaner power generation into the power system without affecting the operational economy, voltage security and stability becomes a challenging issue. To minimize this adverse impact of intermittent renewable resources, hydro power sources may be considered as an effective option. Inclusion of hydro power may contribute towards optimal utilization of the abundant clean energy and enhance the capability to mitigate the volatile renewable power sources while forming a stable hybrid power system (HPS). In this context, an intelligent generation scheduling (IGS) mechanism is proposed to effectively mitigate these complex challenges. To further analyze these issues, multiple case studies under different operating conditions are carried out to portray the significance of incorporating the complementary behaviour of hydro-solar generation with thermal power generation facilities in environmental optimal power flow (EOPF) framework. Widely accepted IEEE 30 bus benchmark system is considered for the validation of results. Optimal operational paradigm (OOP) for the three different HPS configurations i.e. (1) Solar-Thermal (ST); (2) Hydro-Thermal (HT); and (3) Solar-Hydro-Thermal (SHT) is evaluated using Jaya algorithm (JA) while meeting the real time constraints. With the OOP, a comparative performance evaluation is carried out among different hybrid configurations in fulfilling the multiple objectives. Results show the supremacy of SHT configuration in minimizing the operating cost by 1.324×105 US$/y to 2.445×105 US$/y and emission up to 15.768 Tons/y compared to other configurations.

Research on Online Temperature Prediction Method for Office Building Interiors Based on Data Mining

Indoor environmental parameters are closely related to the energy consumption and indoor thermal comfort of office buildings. Predicting these parameters, especially indoor temperature, can contribute to the management of energy consumption and thermal comfort levels in office buildings. An accurate indoor temperature prediction model is the basis for implementing this process. To this end, this paper first discusses the input and output parameters of the model, and then it compares the prediction effects of mainstream prediction model algorithms based on data mining under the same data conditions. The superiority of the XGBoost integrated learning algorithm is verified, and a further XGBoost-based indoor temperature online prediction method is designed. The effectiveness of the method is validated using actual data from a commercial office building in Haidian District, Beijing. Finally, optimization methods for the prediction method are discussed with regard to the scheduler mechanism proposed in this paper. Overall, this work can assist building operators in optimizing HVAC equipment running strategies, thus improving the indoor thermal comfort and energy efficiency of the building.

Research on Real-Time Dynamic Scheduling Mechanism of Intelligent Manufacturing System Based on Agent

Research on Real-Time Dynamic Scheduling Mechanism of Intelligent Manufacturing System Based on Agent

Enhancing Congestion Control and QoS Scheduling Using Novel Rate Aware-Neuro-Fuzzy Algorithm in MANET

Mobile Ad Hoc Networks (MANET) provides a vibrant atmosphere wherein data may be substituted deprived of the necessity of human authority or a centralized server, as long as nodes work together for routing. As long as security throughout the multipath routing protocol and data transfer over many routes in a MANET is a difficult problem, this work offers a message security technique. This study presents the congestion control and QoS scheduling mechanism. The goal of this study is to examine standardized MAC protocols on MANET, to measure performance under various node densities and MAC protocols. Initially, this work presents the Centralized Congestion Detection method to detect congestion with baseline parameters. Accordingly, the congestion is avoided using Novel Rate Aware-Neuro-Fuzzy based Congestion Controlling strategy. This method effectively controls the congestion in the Network. This mechanism has been proposed which defines three levels of congestion based on which the data rate, throughput, overhead and delay. However, after controlling the congestion, the optimal routes are given to the packets by proposing an Ambient Intelligence-based Ant colony optimization quality-aware energy routing protocol (AIACOAR). This method finds the most efficient route to a destination and decreases the time and energy required. Accordingly, for securing the network against malicious attacks, an Elliptic Curve Cryptography (ECC) encryption mechanism is presented. Consequently, the multihop scheduler performs QoS-based scheduling in MANET. Schedulers in MANET take into account various QoS parameters such as end-to-end packet delay, packet delivery ratio, flow priority, etc. The proposed method is implemented using Matlab software, and the evaluation metrics are PDR, jitter, congestion detection time, delay, route selection time, and throughput. The performance of the proposed method is compared to the existing AIFSORP and LF-SSO techniques. While compared to these methods, the proposed method’s performance is improved in terms of PDR, delay, throughput, etc. The PDR value of the proposed method reaches approximately 99%, and it produces a very low delay. This produces reliable route discovery, optimized congestion control, and better QoS scheduling, therefore, these improve the system performance. In future, a recent bio-inspired technique is presented to even more minimize energy consumption and further improve the system's performance.

Empirical investigation of factors influencing function as a service performance in different cloud/edge system setups

Experimental data can aid in gaining insights about a system operation, as well as determining critical aspects of a modeling or simulation process. In this paper, we analyze the data acquired from an extensive experimentation process in a serverless Function as a Service system (based on the open source Apache Openwhisk) that has been deployed across 3 available cloud/edge locations with different system setups. Thus, they can be used to model distribution of functions through multi-location aware scheduling mechanisms. The experiments include different traffic arrival rates, different setups for the FaaS system, as well as different configurations for the hardware and platform used. We analyze the acquired data for the three FaaS system setups and discuss their differences presenting interesting conclusions with relation to transient effects of the system, such as the effect on wait and execution time. We also demonstrate interesting trade-offs with relation to system setup and indicate a number of factors that can affect system performance and should be taken under consideration in modeling attempts of such systems.

Edge Trusted Sharing: Task-Driven Decentralized Resources Collaborate in IoT

6G is committed to providing a fully connected world. The deployment and application of 6G technology in the Internet of Things (IoT) can efficiently collaborate IoT resources and realize resource sharing, which mainly encourages IoT development. However, due to the lack of trust between IoT resources, security and privacy become the main challenges. As an emerging technology, blockchain can solve the trust-absence issues and provide more benefits, but the introduction of blockchain also brings problems for IoT resource collaboration and sharing. This article first proposes a blockchain-enabled edge resource sharing (BEERS) architecture by combining blockchain and edge computing technology. Then, based on a typical resource sharing and collaboration scenario, the joint optimization problem of resource scheduling and task assignment (JRSTA) is constructed. We decompose JRSTA into a primal problem and a master problem and design a greedy-based task assignment (GBTA) algorithm to solve the primal problem. Based on the GBTA algorithm, the resource scheduling and task assignment (RSTA) algorithm is developed. Next, we design a layered parallel edge resource scheduling and task assignment (LPRSTA) mechanism to improve practicability. Finally, we analyze the security and the performance of our proposed architecture and algorithms. The results show that the proposed architecture can support the secure collaboration of IoT resources, and the proposed algorithm can achieve effective resource scheduling and task assignment.

A hybrid discrete differential evolution – genetic algorithm approach with a new batch formation mechanism for parallel batch scheduling considering batch delivery

Scheduling is an important decision-making problem in production planning and the resulting decisions have a direct impact on reducing waste, including energy and idle capacity. Batch scheduling problems occur in various industries from automotive to food and energy. This paper introduces the parallel p-batch scheduling problem with batch delivery, content-dependent loading/unloading times and energy-aware objective function. The problem has been motivated by a real system used for freezing products in a food processing company. A mixed-integer linear programming model (MILP) has been developed and explained through a numerical example. As it is not practical to solve large-size instances via a mathematical model, the discrete differential evolution algorithm has been improved (iDDE) and hybridised with the genetic algorithm (GA). A release-oriented vector generation procedure and a heuristic batch formation mechanism have been developed to efficiently solve the problem. The performance of the proposed approach (iDDEGA) has been compared with CPLEX, iDDE and GA through a comprehensive computational study. A case study was conducted based on real data collected from the freezing process of the company, which also verified the practical use and advantages of the proposed methodology.

Towards the Exploration of Task and Workflow Scheduling Methods and Mechanisms in Cloud Computing Environment

Cloud computing sets a domain and application-specific distributed environment to distribute the services and resources among users. There are numerous heterogeneous VMs available in the environment to handle user requests. The user requests are defined with a specific deadline. The scheduling methods are defined to set up the order of request execution in the cloud environment. The scheduling methods in a cloud environment are divided into two main categories called Task and Workflow Scheduling. This paper, is a study of work performed on task and workflow scheduling. Various feature processing, constraints-restricted, and priority-driven methods are discussed in this research. The paper also discussed various optimization methods to improve scheduling performance and reliability in the cloud environment. Various constraints and performance parameters are discussed in this research.

An Adaptive Scheduling Mechanism Optimized for V2N Communications over Future Cellular Networks

Automated driving requires the support of critical communication services with strict performance requirements. Existing fifth-generation (5G) schedulers residing at the base stations are not optimized to differentiate between critical and non-critical automated driving applications. Thus, when the traffic load increases, there is a significant decrease in their performance. Our paper introduces SOVANET, a beyond 5G scheduler that considers the Radio Access Network (RAN) load, as well as the requirements of critical, automated driving applications and optimizes the allocation of resources to them compared to non-critical services. The proposed scheduler is evaluated through extensive simulations and compared to the typical Proportional Fair scheduler. Results show that SOVANET’s performance for critical services presents clear benefits.

ECKN: An Integrated Approach for Position Estimation, Packet Routing, and Sleep Scheduling in Wireless Sensor Networks.

Network lifetime and localization are critical design factors for a number of wireless sensor network (WSN) applications. These networks may be randomly deployed and left unattended for prolonged periods of time. This means that node localization is performed after network deployment, and there is a need to develop mechanisms to extend the network lifetime since sensor nodes are usually constrained battery-powered devices, and replacing them can be costly or sometimes impossible, e.g., in hostile environments. To this end, this work proposes the energy-aware connected k-neighborhood (ECKN): a joint position estimation, packet routing, and sleep scheduling mechanism. To the best of our knowledge, there is a lack of such integrated solutions to WSNs. The proposed localization algorithm performs trilateration using the positions of a mobile sink and already-localized neighbor nodes in order to estimate the positions of sensor nodes. A routing protocol is also introduced, and it is based on the well-known greedy geographic forwarding (GGF). Similarly to GGF, the proposed protocol takes into consideration the positions of neighbors to decide the best forwarding node. However, it also considers node residual energy in order to guarantee the forwarding node will deliver the packet. A sleep scheduler is also introduced in order to extend the network lifetime. It is based on the connected k-neighborhood (CKN), which aids in the decision of which nodes switch to sleep mode while keeping the network connected. An extensive set of performance evaluation experiments was conducted and results show that ECKN not only extends the network lifetime and localizes nodes, but it does so while sustaining the acceptable packet delivery ratio and reducing network overhead.

A Double Auction Mechanism for Task Scheduling of An EOS Constellation

This study investigates the task scheduling problem for an earth observation satellite (EOS) constellation. The EOS constellation needs to collaboratively complete a set of observation tasks, but each EOS should satisfy the observation order specification described by a task graph due to its motion constraints. The goal is to maximize the total number of observation tasks by the constellation, for which repeated observations are counted only for once. Firstly, the task scheduling problem is formulated as an exact potential game and the goal of the task scheduling problem is converted to find a Nash equilibrium (NE). Secondly, a double auction strategy is proposed to solve for an NE iteratively and a sieving scheme is presented for the buyer to build its candidate set. It is proved that our algorithm converges to an NE in finite steps.

CD-MSA: Cooperative and Deadline-Aware Scheduling for Efficient Multi-Tenancy on DNN Accelerators

With DNN turning into the backbone of AI cloud services and propelling the emergence of INFerence-as-a-Service (INFaaS), DNN-specific accelerators have become the indispensable components of cloud inference systems. Due to the conservative “one-task-at-a-time” working mode and deadline blindness of those accelerators, implementing multi-tenancy that aims to improve the cost-effectiveness and meet SLA requirements is intractable. Recent studies including the temporal and spatial approaches, employ manifold scheduling mechanisms and sophisticated architecture innovations to address the challenge. However, these researches either still neglect the deadline awareness or render inevitable and expensive hardware overheads such as switches and storage. In this paper, we present <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Cooperative and Deadline-aware Multi-Systolic-Array scheduling</i> (CD-MSA), a low-cost solution for the cloud inference that utilizes the real time mechanism and task-level parallelism to enable efficient multi-tenancy. Based on our preemptive multi-systolic-array accelerator architecture supporting the simultaneous task co-location, we first construct a fine-grained DNN execution model to lay the groundwork for the lightweight preemption. Second, we design a cooperative, deadline- and laxity-aware scheduler in conjunction with an efficient schedulability test method for better QoS guarantee without introducing additional hardware cost. Finally, to further promote the overall throughput, we propose <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">dynamic task fusion</i> , a software approach that fuses different tasks into the logically “multi-threading” tasks at runtime. We compare CD-MSA with several state-of-the-art researches across three multi-DNN workloads. The evaluation results show CD-MSA improves the latency-bounded throughput, SLA satisfaction rate and weighted system throughput by up to 62%, 63% and 27%, respectively.

Decision variable contribution based adaptive mechanism for evolutionary multi-objective cloud workflow scheduling

Workflow scheduling is vital to simultaneously minimize execution cost and makespan for cloud platforms since data dependencies among large-scale workflow tasks and cloud workflow scheduling problem involve large-scale interactive decision variables. So far, the cooperative coevolution approach poses competitive superiority in resolving large-scale problems by transforming the original problems into a series of small-scale subproblems. However, the static transformation mechanisms cannot separate interactive decision variables, whereas the random transformation mechanisms encounter low efficiency. To tackle these issues, this paper suggests a decision-variable-contribution-based adaptive evolutionary cloud workflow scheduling approach (VCAES for short). To be specific, the VCAES includes a new estimation method to quantify the contribution of each decision variable to the population advancement in terms of both convergence and diversity, and dynamically classifies the decision variables according to their contributions during the previous iterations. Moreover, the VCAES includes a mechanism to adaptively allocate evolution opportunities to each constructed group of decision variables. Thus, the decision variables with a strong impact on population advancement are assigned more evolution opportunities to accelerate population to approximate the Pareto-optimal fronts. To verify the effectiveness of the proposed VCAES, we carry out extensive numerical experiments on real-world workflows and cloud platforms to compare it with four representative algorithms. The numerical results demonstrate the superiority of the VCAES in resolving cloud workflow scheduling problems.

PROSE: Multi-round fair coflow scheduling without prior knowledge

Coflow scheduling plays a crucial role in enhancing network-level performance in datacenter applications. Existing works on coflow scheduling predominantly concentrate on clairvoyant schedulers, which assume prior knowledge of coflow sizes before transmission. However, this assumption is often unrealistic in practical scenarios like pipelined computation. Consequently, research on non-clairvoyant schedulers has garnered increasing attention. Most studies on non-clairvoyant schedulers focus on either improving efficiency or promoting fairness, with limited emphasis on striking a balance between the two objectives. Additionally, for non-cooperative environments like multi-tenant datacenter networks, it is essential to ensure strategy-proofness in coflow scheduling. Without adequate measures, tenants may manipulate their reported requirements to gain an unfair advantage in resource allocation. Ideally, in non-cooperative environments, a coflow scheduler should achieve efficiency, fairness, and strategy-proofness, all without prior knowledge of coflow sizes. However, few existing efforts have managed to simultaneously achieve these objectives.To fill this gap, we develop PROSE, a non-clairvoyant scheduler for non-cooperative environments. PROSE divides the scheduling time into multiple rounds and employs a two-stage scheduling mechanism based on these rounds. In the first stage, PROSE estimates the sizes of the coflows with unknown sizes by transmitting the probe flows, using a policy that combines coflow competition with batch processing. Once the information about coflow sizes is obtained, PROSE prioritizes coflows among tenants for bandwidth allocation in the second stage, aiming to accelerate coflow completion within each round. Furthermore, PROSE ensures optimal isolation guarantee by fairly limiting the total data transfer for each tenant and dynamically adjusts the scheduling order of coflows in a round-robin manner across multiple rounds. PROSE prevents tenants from attempting to consume excessive network resources through manipulative actions that deceive the scheduler. Trace-driven simulations demonstrate that PROSE outperforms the fair scheduler, achieving up to a 2.37× reduction in average coflow completion time, indicating substantial efficiency improvements.

A scheduling mechanism for hybrid flow shops with reworks under general queue time limits

This study addresses multi-stage hybrid flow shop scheduling in which a job is reworked if the queue time between two arbitrary stages exceeds an upper limit. The problem is to determine the allocations of jobs to machines at each stage and the start times of jobs and rework setups/operations when incurred. A mixed integer programming model is proposed for each of the makespan and the total tardiness measures. Then, because the problem is NP-hard, a scheduling mechanism is proposed that consists of three phases: (a) filtering the jobs to be delayed; (b) searching the jobs to be reworked; and (c) dispatching non-delayed and delayed jobs sequentially. Simulation results show that the mechanism proposed in this study outperforms the conventional dispatching approach in the high rework setup time case for the makespan problem and low/high setup time cases for the tardiness problem. The best priority rules of the mechanism under each of the measures are also reported.

Deep Reinforcement Learning-Based Joint Scheduling of 5G and TSN in Industrial Networks

5th-Generation (5G) and Time-Sensitive Networking (TSN) are regarded as competitive new technologies for future industrial networks; 5G-TSN collaboration transmission has drawn more attention because it can provide a guarantee of low-latency, ultra-reliable and deterministic transmission for time-critical automation applications. However, the methodologies of resource scheduling mechanisms in 5G and Time-Sensitive Networking (TSN) are quite different, which may lead to an inefficient Quality of Service (QoS) guarantee for deterministic transmission across 5G and TSN. Therefore, an efficient 5G-TSN joint scheduling algorithm based on Deep Deterministic Policy Gradient (DDPG) is proposed and analyzed in this article. The proposed algorithm takes both 5G radio channel information and the Gate Control List (GCL) state in the TSN domain into consideration, aiming to provide a latency guarantee for time-triggered applications across 5G and TSN as well as a throughput guarantee for video applications in 5G systems. The simulation results compare the latency and throughput performance of the proposed joint scheduling algorithm with several traditional 5G scheduling algorithms; meanwhile, several GCL setting methods are given to verify the impacts on latency and throughput performance within the proposed algorithm. The simulation results demonstrate that the proposed DDPG-based joint scheduling algorithm can significantly enhance the multi-application-carrying capability of 5G-TSN collaboration architecture.

An efficient multi-agent approach to order picking and robot scheduling in a robotic mobile fulfillment system

This paper presents a Multi-Agent System (MAS) for optimizing the scheduling and routing of mobile robots and human pickers in a Robotic Mobile Fulfillment System (RMFS). The RMFS is a system designed for e-commerce warehousing where autonomous mobile robots are used to fetch inventory pods, also referred to as racks, from the storage area and transport them to the appropriate picking station where human pickers pick the required number of goods. The system requires the solution of several hard decision problems like: the order-to-picking station assignment and sequencing, the pod selection, and the multi-robot task allocation. The proposed solution approach employs decentralized scheduling mechanisms, i.e. auctions and dispatching rules, to communicate and distribute picking and retrieval tasks among the agents. Various dispatching rules are identified and analyzed over a wide set of problem instances of the RMFS with varying numbers of mobile robots, picking stations, and order sizes. The proposed MAS framework shows promising results and requires only a fraction of the computation time compared to a centralized scheduling algorithm. The MAS also includes both unidirectional and bidirectional lanes. Although additional complexity in collision avoidance is introduced when using bidirectional lanes, it allows for better system performance.

Research on path selection and flow scheduling of time-sensitive networks for power substations

In view of the problem that the flow of intelligent substation traffic scheduling increases, resulting in the transmission delay also increases, this paper proposed a joint optimization method of Time Sensitive Network (TSN) path selection and scheduling, which combines the resource sensing K-Shortest Path Algorithm (KPA) path selection algorithm and the constraint based gating method. This method can select an optimal transmission path for TT flows and plan the transmission path for non TT flows. Based on the scheduling mechanism of TSN, constraints and optimization objective functions are established, and a gating scheduling method based on constraints is proposed. Finally, the test and verification platform of the scheme is designed and built. Through the test and verification platform, the data stream transmission delay and delay jitter of the scheme are analyzed, and the algorithms are compared and analyzed from the aspects of running time and schedulability. With the continuous evolution of the follow-up TSN technology and the in-depth promotion of the power industry, more and more TSN key technologies will be applied to the smart grid.