Resource Scheduling Mechanism Research Articles

A Hybrid Sparse-dense Defensive DNN Accelerator Architecture against Adversarial Example Attacks

Understanding how to defend against adversarial attacks is crucial for ensuring the safety and reliability of these systems in real-world applications. Various adversarial defense methods are proposed, which aim at improving the robustness of neural networks against adversarial attacks by changing the model structure, adding detection networks, and adversarial purification network. However, deploying adversarial defense methods in existing DNN accelerators or defensive accelerators leads to many key issues. To address these challenges, this article proposes sDNNGuard , an elastic heterogeneous DNN accelerator architecture that can efficiently orchestrate the simultaneous execution of original ( target ) DNN networks and the detect algorithm or network. It not only supports for dense DNN detect algorithms, but also allows for sparse DNN defense methods and other mixed dense-sparse (e.g., dense-dense and sparse-dense) workloads to fully exploit the benefits of sparsity. sDNNGuard with a CPU core also supports the non-DNN computing and allows the special layer of the neural network, and used for the conversion for sparse storage format for weights and activation values. To reduce off-chip traffic and improve resources utilization, a new hardware abstraction with elastic on-chip buffer/computing resource management is proposed to achieve dynamical resource scheduling mechanism. We propose an extended AI instruction set for neural networks synchronization, task scheduling and efficient data interaction. Experiment results show that sDNNGuard can effectively validate the legitimacy of the input samples in parallel with the target DNN model, achieving an average 1.42× speedup compared with the state-of-the-art accelerators.

Integrated Sensing, Communication, and Computing for Cost-effective Multimodal Federated Perception

Federated learning (FL) is a prominent paradigm of 6G edge intelligence (EI), which mitigates privacy breaches and high communication pressure caused by conventional centralized model training in the artificial intelligence of things (AIoT). The execution of multimodal federated perception (MFP) services comprises three sub-processes, including sensing-based multimodal data generation, communication-based model transmission, and computing-based model training, ultimately competitive on available underlying multi-domain physical resources such as time, frequency, and computing power. How to reasonably coordinate the multi-domain resources scheduling among sensing, communication, and computing, therefore, is vital to the MFP networks. To address the above issues, this article explores service-oriented resource management with integrated sensing, communication, and computing (ISCC). Specifically, employing the incentive mechanism of the MFP service market, the resources management problem is defined as a social welfare maximization problem, where the concept of “expanding resources” and “reducing costs” is used to enhance learning performance gain and reduce resource costs. Experimental results demonstrate the effectiveness and robustness of the proposed resource scheduling mechanisms.

On-Demand Centralized Resource Allocation for IoT Applications: AI-Enabled Benchmark

The development of emerging information technologies, such as the Internet of Things (IoT), edge computing, and blockchain, has triggered a significant increase in IoT application services and data volume. Ensuring satisfactory service quality for diverse IoT application services based on limited network resources has become an urgent issue. Generalized processor sharing (GPS), functioning as a central resource scheduling mechanism guiding differentiated services, stands as a key technology for implementing on-demand resource allocation. The performance prediction of GPS is a crucial step that aims to capture the actual allocated resources using various queue metrics. Some methods (mainly analytical methods) have attempted to establish upper and lower bounds or approximate solutions. Recently, artificial intelligence (AI) methods, such as deep learning, have been designed to assess performance under self-similar traffic. However, the proposed methods in the literature have been developed for specific traffic scenarios with predefined constraints, thus limiting their real-world applicability. Furthermore, the absence of a benchmark in the literature leads to an unfair performance prediction comparison. To address the drawbacks in the literature, an AI-enabled performance benchmark with comprehensive traffic-oriented experiments showcasing the performance of existing methods is presented. Specifically, three types of methods are employed: traditional approximate analytical methods, traditional machine learning-based methods, and deep learning-based methods. Following that, various traffic flows with different settings are collected, and intricate experimental analyses at both the feature and method levels under different traffic conditions are conducted. Finally, insights from the experimental analysis that may be beneficial for the future performance prediction of GPS are derived.

Enabling Distributed and Optimal RDMA Resource Sharing in Large-Scale Data Center Networks: Modeling, Analysis, and Implementation

Remote Direct Memory Access (RDMA) suffers from unfairness issues and performance degradation when multiple applications share RDMA network resources. Hence, an efficient resource scheduling mechanism is urged to optimally allocates RDMA resources among applications. However, traditional Network Utility Maximization (NUM) based solutions are inadequate for RDMA due to three challenges: 1) The standard NUM-oriented algorithm cannot deal with coupling variables introduced by multiple dependent RDMA operations; 2) The stringent constraint of RDMA on-board resources complicates the standard NUM by bringing extra optimization dimensions; 3) Naively applying traditional algorithms for NUM suffers from scalability issues in solving a large-scale RDMA resource scheduling problem. In this paper, we present how to optimally share the RDMA resources in large-scale data center networks with a distributed manner. First, we propose Distributed RDMA NUM (DRUM) to model the RDMA resource scheduling problem as a new variation of the NUM problem. Second, we present distributed algorithms to efficiently solve the large-scale, interdependent RDMA resource sharing problem for different RDMA use cases. Through theoretical analysis, the convergence and parallelism of proposed algorithms are guaranteed. Finally, we implement the algorithms as a kernel-level indirection module in the real-world RDMA environment, so as to provide end-to-end resource sharing and performance guarantee. Through extensive evaluations by large-scale simulations and testbed experiments, we show that our method significantly improves applications’ performance under resource contention, achieving <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$1.7-3.1\times$</tex-math> </inline-formula> higher throughput, and in a dynamic context, the largest performance improvement reaches <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$98.1\%$</tex-math> </inline-formula> and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$64.1\%$</tex-math> </inline-formula> in terms of latency and throughput, respectively.

RLPTO: A Reinforcement Learning-Based Performance-Time Optimized Task and Resource Scheduling Mechanism for Distributed Machine Learning

RLPTO: A Reinforcement Learning-Based Performance-Time Optimized Task and Resource Scheduling Mechanism for Distributed Machine Learning

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.

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.

A dynamic even distribution resource scheduling mechanism combined with network coding for inter‐LEO satellite networks

SummaryResource scheduling mechanism of LEO satellite networks is the key to determining communication efficiency. Facing the LEO satellite networks with the dynamic topology changes, varying service requirements, and intermittent inter‐satellite links (ISLs), the state‐of‐the‐art cannot achieve high resource efficiency under both heavy and burst traffic loads, and the applicability of parameters design is insufficient under intermittent ISLs. Considering this, we propose a dynamic even distribution mechanism combined with network coding DENC. This novel mechanism obtains the service requirements and allocates resources dynamically through the even distribution algorithm to balance network maintenance overhead and resource waste and improves the success probability of transmission based on network coding to balance retransmission and redundancy. In this paper, we establish performance analysis models to optimize the parameters such as maintenance frequency and coding coefficient. Besides, we construct a system‐level simulation platform. Mathematical and simulation results indicate that the resource efficiency of EMNC can be improved by more than 48% compared with SAHN‐MAC, ICSMA, CSMA‐TDMA, and HTM when all nodes have service needs, and the ISL outage rate is 20%. As the outage probability of ISL increases and the proportion of nodes with service requirements decreases, the performance advantage of EMNC becomes more apparent.

Slicing Resource Allocation Based on Dueling DQN for eMBB and URLLC Hybrid Services in Heterogeneous Integrated Networks

In 5G/B5G communication systems, network slicing is utilized to tackle the problem of the allocation of network resources for diverse services with changing demands. We proposed an algorithm that prioritizes the characteristic requirements of two different services and tackles the problem of allocation and scheduling of resources in the hybrid services system with eMBB and URLLC. Firstly, the resource allocation and scheduling are modeled, subject to the rate and delay constraints of both services. Secondly, the purpose of adopting a dueling deep Q network (Dueling DQN) is to approach the formulated non-convex optimization problem innovatively, in which a resource scheduling mechanism and the ϵ-greedy strategy were utilized to select the optimal resource allocation action. Moreover, the reward-clipping mechanism is introduced to enhance the training stability of Dueling DQN. Meanwhile, we choose a suitable bandwidth allocation resolution to increase flexibility in resource allocation. Finally, the simulations indicate that the proposed Dueling DQN algorithm has excellent performance in terms of quality of experience (QoE), spectrum efficiency (SE) and network utility, and the scheduling mechanism makes the performance much more stable. In contrast with Q-learning, DQN as well as Double DQN, the proposed algorithm based on Dueling DQN improves the network utility by 11%, 8% and 2%, respectively.

Prioritized Energy Efficient Resource Scheduling in Cloud Computing

Resource scheduling in cloud computing is one of the impactful area of research. Cloud service providers maintain its efficacy through proper resource management schemes. Users experience seamless cloud services when cloud service provider manages its resources efficiently. Another aspect in resource management is energy efficient schemes. Energy efficiency largely depends on employment of minimum number of resource servers. This article discusses energy efficient resource scheduling mechanism on multi-layer prioritized resource requests. Resource requests are segregated into three categories and those are scheduled on resource servers based on their fast availability. The work focuses on scheduling resource requests on previously active servers as much as possible before activating any idle servers. Proposed scheduling scheme has been tested on a standard benchmark datasets and performance of the proposed method establishes its efficacy.*

Efficient and Fair Multi-Resource Allocation in Dynamic Fog Radio Access Network Slicing

Future wireless networks should meet heterogeneous service requirements of diverse applications, including interactive multimedia, augmented reality, and autonomous driving. The fog radio access network (Fog-RAN) is a novel architecture that enables efficient and flexible allocation of network resources to end users. However, guaranteeing application-specific service requirements while maximizing resource utilization is an open challenge in Fog-RANs. This article proposes a multiresource Fog-RAN slicing scheme that maximizes network resource utilization and satisfies important economic properties: Pareto-optimality, envy freeness, and sharing incentive. The proposed solution considers both heterogeneous resources (i.e., bandwidth, storage, and computing) and the different service levels defined in 5G networks. Accordingly, a two-level resource scheduling mechanism is devised to jointly allocate Fog-RAN resources to slices in two stages: 1) a broker allocates resources to slices at fog nodes over a given time window and 2) a slice hypervisor then allocates slice-specific resources at each fog node to users with a much shorter time scale. An extensive evaluation based on real-world data sets demonstrates that the proposed solution significantly increases the monetary gain of service providers, namely, by 32%–60% compared to the state of the art, including dynamic hierarchical resource allocation and dynamic slicing with proportional allocation.

Time Effective Cloud Resource Scheduling Method for Data-Intensive Smart Systems

The cloud computing platforms are being deployed nowadays for resource scheduling of real time data intensive applications. Cloud computing still deals with the challenge of time oriented effective scheduling for resource allocation, while striving to provide the efficient quality of service. This article proposes a time prioritization-based ensemble resource management and Ant Colony based optimization (ERM-ACO) algorithm in order to aid effective resource allocation and scheduling mechanism which specifically deals with the task group feasibility, assessing and selecting the computing and the storage resources required to perform specific tasks. The research outcomes are obtained in terms of time-effective demand fulfillment rate, average response time as well as resource utilization time considering various grouping mechanisms based on data arrival intensity consideration. The proposed framework when compared to the present state-of-the-art methods, optimal fitness percentage of 98% is observed signifying the feasible outcomes for real-time scenarios.

Scheduling and Optimization of Wireless Virtual Network Resources Based on Reinforcement Learning

With the booming and proliferation of 5G wireless network services in the future, a large number of wireless virtual network resources will emerge, and the densification and heterogeneity of the wireless communication networks that provide services for them will become the trend of development. To this end, a wireless virtual network resource scheduling model based on user satisfaction is constructed, and a reinforcement learning-based wireless virtual network resource scheduling mechanism, IRSUP, is proposed. IRSUP is designed with an intelligent optimization module for user service preferences to address the personalized needs of user service customization, and a reinforcement learning-based intelligent scheduling module is designed to address the challenge of joint optimization of multistar resources. Simulation results show that IRSUP can effectively improve resource scheduling rationality and link resource utilization and user satisfaction, among which service capacity is improved by 30% to 60% and user satisfaction is more than doubled.

Community Environmental Detection and Community Outdoor Space Health Promotion Based on Cloud Resource Scheduling Mechanism.

In the context of rapid economic growth, people's living standards are improving day by day, and China's urbanization process is also gradually accelerating. Urban renewal is a very complex project. The renewal and expansion of most cities in the country usually involve demolishing and rebuilding. This way of urban renewal only pays attention to the renewal efficiency of cities and towns, and ignores the health needs of residents, which will make community residents lack a sense of security, pleasure, comfort, and belonging to the community, and greatly reduce the quality of life and physical fitness of community residents. Building a healthy city is an important goal of today's society, and community is the basic unit of a city, so it is urgent to build a health-promoting community. We should pay attention to and study the social environment, the external space environment of residential areas, and the interaction between them, so as to make develop them in a healthy direction and create a healthy and positive community. Therefore, it is an urgent task to improve the community residents' attention to the above problems and build community outdoor space, which has very important practical significance. In this paper, we use the cloud resource scheduling mechanism and the Internet of things to study the healthy role of community outdoor space planning. Through the transplantation of embedded Linux system, the development of communication interface and the external acquisition sensing device, we collect the information of working status and running status, and transmit it to the database built in the cloud through the 4G module on the motherboard. Then, HTML + java script + CSS + JSON + Ajax technology is used to write the display interface and logical relationship, so that the data can be displayed on the mobile terminal and PC, which can provide a useful technical exploration for outdoor space planning. The community Internet of Things technology realizes the intelligent community environment detection, and the community cloud resource scheduling mechanism combined with the community Internet of Things can obtain the residents' help information in time and allocate the community outdoor resources in real time, which can not only meet the health needs of community members but also be conducive to the sustainable development of a health-promoting community. In addition, the cloud resource scheduling mechanism and the Internet of things also provide new ideas for the study of the health promotion research of community outdoor space planning.

Quality of service enabled resource scheduling for cooperative driving provision in the internet of vehicles

Road traffic efficiency may be improved by developing an integrated network for cooperative driving provision (CDP) among vehicles on the road. In a dance urban traffic scenario, the quality of service may be compromised when required bandwidth is not provided by the existing network architecture that impacts negatively on the cooperative behaviour of the vehicles. To solve these problems, a network architecture with better scheduling of resources that meet the quality of service (QoS) is required. So, we proposed a fifth-generation (5G) technology-based network architecture that provides the required QoS for CDP. The proposed architecture consists of a resource scheduling mechanism within the 5G network and a scheme for cooperative behaviour among the vehicles on the road. The implementation of the proposed network architecture is done by incorporating it into a well-known vehicular clustering algorithm. The performance of the proposed architecture is compared with existing schemes that show improvement.

A comparative study on efficient cloud security, services, simulators, load balancing, resource scheduling and storage mechanisms

There are applications in software that can process the user or customer records in hospitals, education sector, government sector, social media and mail communication, etc., which require accessing a single or set of records in a database consisting of millions of records. A basic requirement of those applications is that, the need to access a few data required in a secured manner from the data sets which are very large but simple in structure. Cloud computing provides the computing requirements for these kinds of the new generation of applications involving very large data sets that cannot possibly be handled efficiently without understanding the available cloud computing infrastructures. The objective is to find the cloud security, services, simulators, load balancing, resource scheduling and storage mechanisms which can best suite the need of the cloud environment chosen in an efficient way. This survey would act as a catalyst for the design of cloud environment over the very large data set in the future.

Invasive weed optimization based scheduling for digital microfluidic biochip operations

Digital Microfluidic Biochips (DMFBs) based on electro-wetting-on-dielectric (EWOD) technology are a class of lab-on-a-chip (LOC) devices. DMFBs can efficiently carry out biochemical analysis and have many advantages over the traditional laboratory system. DMFBs offer miniaturization, automation, and programmability. Resource-constrained scheduling is the first and vital step of fluidic-level synthesis of DMFBs while the other two are placement and routing of droplets. Scheduling DMFB operations is a constrained optimization problem which is NP-Complete. We propose an invasive weed optimization (IWO) algorithm based scheduling for the synthesis of DMFBs. The IWO algorithm is a nature-inspired meta-heuristic algorithm. Proposed algorithm can be used for the offline synthesis of DMFBs, where solution quality is more important than execution time. Each weed in the proposed algorithm represents a potential candidate solution for the scheduling problem. To calculate the fitness of individual weeds, we proposed an algorithm based on Heterogeneous Earliest Finish Time (HEFT), which incorporates resource binding, scheduling, and greedy module selection mechanism for bio-assay operations. Weeds (solutions) update their positions (priorities) by colonization behavior of weeds. Simulation results show that proposed IWO outperforms iterative improvement based algorithms and optimal ILP based algorithms which are existing for the offline synthesis of DMFBs.

Research on Resource Scheduling of Cloud Computing Based on Improved Genetic Algorithm

In order to solve the problem that the resource scheduling time of cloud data center is too long, this paper analyzes the two-stage resource scheduling mechanism of cloud data center. Aiming at the minimum task completion time, a mathematical model of resource scheduling in cloud data center is established. The two-stage resource scheduling optimization simulation is realized by using the conventional genetic algorithm. On the technology of the conventional genetic algorithm, an adaptive transformation operator is designed to improve the crossover and mutation of the genetic algorithm. The experimental results show that the improved genetic algorithm can significantly reduce the total completion time of the task, and has good convergence and global optimization ability.

A novel priority-based resource scheduling mechanism for containerised clouds

With the growing adaption of the containerisation idea, cloud environments are being stuffed with the containers to gain the business, technical and user benefits of both the cloud idea and the containerisation paradigm. Due to the lightweight nature of containers, a cloud centre comprises millions or even billions of containers. This rapid growth of containers in cloud poses several operational and management challenges. The other key problem is to know how optimally allocate different containers for all kinds of incoming tasks on a timely basis. This paper has been prepared based on priority-based resource scheduling approach to fulfil the varying resource requests for business workloads by continuously monitoring the Docker container performance, health condition, and security. Further on, when there is a stream of new tasks waiting for resources, there is also a challenge of how resources can be optimally identified and scheduled in order to fulfil task requests.

A machine-learning based time constrained resource allocation scheme for vehicular fog computing

Through integrating advanced communication and data processing technologies into smart vehicles and roadside infrastructures, the Intelligent Transportation System (ITS) has evolved as a promising paradigm for improving safety, efficiency of the transportation system. However, the strict delay requirement of the safety-related applications is still a great challenge for the ITS, especially in dense traffic environment. In this paper, we introduce the metric called Perception-Reaction Time (PRT), which reflects the time consumption of safety-related applications and is closely related to road efficiency and security. With the integration of the incorporating information-centric networking technology and the fog virtualization approach, we propose a novel fog resource scheduling mechanism to minimize the PRT. Furthermore, we adopt a deep reinforcement learning approach to design an on-line optimal resource allocation scheme. Numerical results demonstrate that our proposed schemes is able to reduce about 70% of the RPT compared with the traditional approach.