Distributed Resource Management Research Articles

Price-Discrimination Game for Distributed Resource Management in Federated Learning

Price-Discrimination Game for Distributed Resource Management in Federated Learning

Distributed Resource Management in Cloud Computing: A Review of Allocation, Scheduling, and Provisioning Techniques

This review paper provides an in-depth examination of distributed resource management in cloud computing, focusing on the critical elements of allocation, scheduling, and provisioning. Cloud computing, characterized by its dynamic and scalable nature, necessitates efficient resource management techniques to optimize performance, cost, and service. The study encompasses a comprehensive analysis of various strategies in resource allocation, scheduling methodologies, and provisioning techniques within the cloud computing paradigm. Through comparative analysis, this paper aims to highlight the synergies and trade-offs inherent in these methods, offering a holistic view of distributed resource management. It contributes to the field by bridging the gap in existing literature, presenting a critical, comparative analysis of current strategies and their interplay in distributed cloud environments.

ADVANCED METHODS FOR MAINTAINING AND MANAGING THE LIFE CYCLE OF CLOUD ENVIRONMENTS: SURVEY

Resource management is a fundamental concept in cloud computing and virtualization, encompassing the allocation, release, coordination, and monitoring of cloud resources to optimize efficiency. The complexity arises from the virtualized, heterogeneous, and multi-user nature of these resources. Effective governance is challenging due to uncertainty, large-scale infrastructures, and unpredictable user states. This paper presents a comprehensive taxonomy of resource management technologies, offering a detailed analysis of design architecture, virtualization, and cloud deployment models, along with capabilities, objectives, methods, and mechanisms. In a cloud computing environment, deploying application-based resource management techniques necessitates understanding the system architecture and deployment model. This paper explores centralized and distributed resource management system architectures, providing a review of effective resource management techniques for both, accompanied by a comparative analysis. The evolution of cloud computing from a centralized to a distributed paradigm is examined, emphasizing the shift towards distributed cloud architectures to harness the computing power of smart connected devices at the network edge. These architectures address challenges like latency, energy consumption, and security, crucial for IoT-based applications. The literature proposes various methods for distributed resource management, aligning with the distributed nature of these architectures. Resource management in cloud computing involves discovery, provisioning, allocation, and monitoring functions, with sub-functions like mapping and scheduling. Integrated approaches to consolidation and resource management have been explored in numerous studies. This paper summarizes and analyzes existing research on resource management functions, focusing on identification, provisioning, allocation planning, and monitoring, based on their objectives and methods.

Distributed Resource Management and Task Scheduling in MEC Networks Against Intelligent Eavesdropping Jammer

Distributed Resource Management and Task Scheduling in MEC Networks Against Intelligent Eavesdropping Jammer

RETRACTED: Distributed IoT services placement in fog environment using optimization-based evolutionary approaches

Fog computing is a promising computing paradigm for the processing and storage of massive data generated by Internet of Things (IoT) devices. Fog computing devices have limited resources compared to the cloud. Meanwhile, the dynamism and heterogeneity of applications requested from IoT devices require quick decisions on where to process services on the fog, the cloud, or the hybrid. This problem is known as Fog Service Placement (FSP), which is a computationally NP-hard problem. Therefore, the efficient allocation of fog resources to IoT services by non-deterministic algorithms is emphasized. In this paper, a Quality of Service (QoS)-aware deployment scheme is proposed using an evolutionary approach to address the FSP problem. Here, several new evolutionary approaches such as Teaching Learning-Based Optimization (TLBO), Honey Badger Algorithm (HBA) and Harris Hawks Optimizer (HHO) are analyzed to solve the problem. We improve the evolutionary approach used to solve the FSP problem with a shared parallel architecture and perform distributed fog resource management. In addition, we bring the processing closer to the fog network by considering the priority of service execution. Here, we formulate a multi-objective function as an optimization problem that simultaneously considers delay cost, delay violation, service cost and fog utilization. All the parameters needed to configure the objective function are collected based on the incoming traffic. The simulations show the superiority of HBA for solving the FSP problem. The evaluation results show that the proposed placement scheme improves the cost and delay compared to the best existing method by 2.6% and 2.8%, respectively.

Statistical Learning-Based Adaptive Network Access for the Industrial Internet of Things

Industrial Internet-of-Things (IIoT) applications generate data in varying amounts with diverse quality of service requirements. The adaptive network access approach and distributed resource management in IIoT networks can reduce the communication overheads caused by centralized resource management approaches. In this regard, statistical learning is a promising tool for addressing decision-making problems in a dynamic environment. This paper considers uplink dominant IIoT networks in which massive devices generate delay-sensitive and delay-tolerant data and communicate over shared radio resources. We propose a novel grant-free access scheme using a statistical learning approach that enables IIoT entities to perform delay-sensitive and delay-tolerant transmissions over dynamically partitioned resources in a prioritized manner. In order to improve utilization of available radio resources, we design an adaptive network access mechanism operating in a semi-distributed manner. This mechanism enables end devices to use their transmission history to choose between static and dynamic resource allocation-based grant-free schemes in a dynamic environment. Simulation results show that average latency and resource utilization vary in grant-free access schemes employing static and dynamic resource allocations. Thus, compared to a single transmission scheme, the proposed adaptive network access offers better channel utilization while meeting the application-specific latency bound in IIoT networks.

基于LSTM Dueling Double DQN的车联网分布式资源管理算法

基于LSTM Dueling Double DQN的车联网分布式资源管理算法

Coordinated parallel resource allocation for integrated access and backhaul networks

The architecture of integrated access and backhaul (IAB) endows 5G and beyond networks with the capabilities of both centralized and distributed resource management: a centralized node, IAB-donor, can efficiently coordinate resources with a network-wide view, and other distributed nodes, IAB-nodes, can quickly react to local traffic bursts multiple hops away from the IAB-donor. However, existing efforts on IAB networking mostly focus on either the centralized or distributed capability of IAB networks and lack the studies on handling bursty traffic. In this paper, a Coordinated Parallel Resource allocation scheme (CPReal) is developed to handle both bursty and non-bursty traffic. Its key feature is that it consists of both a centralized scheme at the IAB-donor for efficient coordination of resource allocation and a distributed scheme at each IAB-node for quick response to short-term bursty traffic. CPReal is standard-compliant and considers the strict parent-to-child relation between IAB-nodes specified in 5G standards. In CPReal, with the assistance from their parent nodes, IAB-nodes can quickly reach an agreement on resource allocation in a distributed and conflict-free way for traffic bursts. Extensive simulations show that CPReal outperforms existing schemes in throughput by 67.3% under bursty traffic and in end-to-end delay by up to 34.4% under various scenarios.

Distributed Deep Reinforcement Learning-Based Spectrum and Power Allocation for Heterogeneous Networks

This paper investigates the problem of distributed resource management in two-tier heterogeneous networks, where each cell selects its joint device association, spectrum allocation, and power allocation strategy based only on locally-observed information without any central controller. As the optimization problem with devices’ quality-of-service (QoS) constraints is non-convex and NP-hard, we model it as a Markov decision process (MDP). Considering the fact that the network is highly complex with large state and action spaces, a multi-agent dueling deep-Q network-based algorithm combined with distributed coordinated learning is proposed to effectively learn the optimized intelligent resource management policy, where the algorithm adopts dueling deep network to learn the action-value distribution by estimating both the state-value and action advantage functions. Under the distributed coordinated learning manner and dueling architecture, the learning algorithm can rapidly converge to the optimized policy. Simulation results demonstrate that the proposed distributed coordinated learning algorithm outperforms other existing learning algorithms in terms of learning efficiency, network data rate, and QoS satisfaction probability.

Distributed Orchestration of Service Function Chains for Edge Intelligence in the Industrial Internet of Things

Network virtualization techniques are promising to overcome the obstacle of applying and expanding costly traditional networks in the industrial Internet of things (IIoT). Artificial intelligence (AI)-enhanced distributed resource management in edge networks has aroused researchers’ widespread attention. However, dynamically arrived service requests and limited edge resources complicate the service scheduling issue. In this article, we establish a dynamic network virtualization technique enabled service function chain (SFC) orchestration framework in IIoT, formulate the joint optimization problem to maximize total utility and decompose it into two subproblems, i.e., SFC selection and dynamic SFC orchestration. A dynamic orchestration of SFC (DOS) scheme, consisting of resource-aware matching algorithm and averaged multistep double deep q-network algorithm, is designed to embed SFC requests distributedly on the optimal virtualized network function chains. At last, we validate the superiority of our proposed DOS scheme by experimental results.

Optimized task scheduling and preemption for distributed resource management in fog-assisted IoT environment

Optimized task scheduling and preemption for distributed resource management in fog-assisted IoT environment

Radio and Energy Resource Management in Renewable Energy-Powered Wireless Networks With Deep Reinforcement Learning

In this paper, we study radio and energy resource management in renewable energy-powered wireless networks, where base stations (BSs) are powered by both on-grid and renewable energy sources and can share their harvested energy with each other. To efficiently manage those resources, we propose a hierarchical and distributed resource management framework based on deep reinforcement learning. The proposed framework minimizes the on-grid energy consumption while satisfying the data rate requirement of each user. It is composed of three different policies in a distributed and hierarchical way. An intercell interference coordination policy constrains the transmission power at each BS to coordinate the intercell interference among the BSs. Under the power constraints, a distributed radio resource allocation policy of each BS determines its own user scheduling and power control. Lastly, an energy sharing policy manages the energy resources of the BSs by sharing the harvested energy via power lines between them. Through the simulation, we demonstrate that the proposed framework can effectively reduce the on-grid energy consumption while satisfying the data rate requirements.

Edge security in smart inverters: Physical invariants based approach

The endeavour towards making power distribution systems (PDSs) smarter has made the interdependence on communication network indispensable. Further, prospective high penetration of intermittent renewable energy sources in the form of distributed energy resources (DERs) has resulted in the necessity for smart controllers on such DERs. Inverters are employed for the purpose of DC to AC power conversion in the distribution network where the present standards require these inverters to be smart. In general, distributed energy resource management systems (DERMS) calculate and send set points/operating points to these smart inverters using protocols such as smart energy profile (SEP) 2.0. Given the nature of sites at which such DERs are installed i.e., home area networks with a pool of IoT(Internet-of-Things) devices, the opportunity for a malicious actor to sabotage the operation is typically higher than that for a transmission system. National Electric Sector Cyber-security Organization Resource (NESCOR) has described several failure scenarios and impact analyses in case of cyber attacks on DERs. One such failure scenario concerns attacks on real/reactive power control commands. In this paper, it is demonstrated that physical invariant based security on the edge devices, i.e. smart controllers deployed in DER inverters, is an effective approach to minimize the impact of cyber attacks targeting reactive power control in DER inverters. The proposed defense is generic and can also be extended to attacks on real-power control. The proposed defense is validated on a co-simulation platform (OpenDSS and MATLAB/SIMULINK).

Distributed Resource Management Framework for IoS Against Malicious Jamming

The internet of satellites (IoS), containing multiple low earth orbit (LEO) satellite constellations, can support tremendous traffic, massive connectivity, and vast coverage. But it also puts forward higher demands for resource management due to the high dynamics of the IoS networks, especially in the malicious jamming environment, where the jammers launch jamming attacks to reduce the efficiency and reliability. Thus, this paper investigates the problem of resource management in malicious jamming environment for IoS, which is divided into three sub-problems: traffic prediction problem, anti-jamming decision problem and resource matching problem. To solve these problems, we proposed a distributed resource management framework (DRMF), which consists of three sub-algorithms. Firstly, the traffic prediction algorithm (TPA) is proposed to deeply mine and accurately predict the traffic rule. Meanwhile, the dynamic anti-jamming algorithm (DAA) is developed to make anti-jamming decision autonomously. Then, based on the outputs obtained by TPA and DAA, the distributed resource matching algorithm (DRMA) is proposed for IoS, and the satellites with insufficient resource can apply for assistance from neighboring satellites with excess resource, thereby improving the safety and efficiency of the entire IoS network. Finally, experiment results and algorithm analysis verify the proposed scheme has better performance than the existing algorithms.

Multi-agents based optimal energy scheduling technique for electric vehicles aggregator in microgrids

This paper presents multi-agents based optimal energy scheduling technique at microgrid level, aiming to minimize overall costs allied with the domestic energy consumption and electric vehicles charging during the particular market price and battery degradation costs. Firstly, agents-based optimal technique is presented for the distributed resource management, where local agents operate and accomplish their tasks autonomously that making the microgrid system more intelligent and reliable. Secondly, to model the actual grid voltage and price uncertainties, the proposed technique is applied in a low distribution network considering the upper and lower limits of the grid prices instead of the average/estimated prices. The problem is solved by linear programming considering the generation capabilities of the renewable energy resources and electric vehicle state of charge during the day-ahead period of 24 h. Besides, to deal with the domestic load and electric vehicles state of charge uncertainties, the simulation is carried out based on their energy consumption periods during the day while the electric vehicles initial state of charges is estimated on their daily mileage. For validation, the proposed technique is employed at a low voltage residential area and compared, which shows that the proposed technique total profit raised by 16.92% and 5.60% in comparison with the uncoordinated and stochastic techniques respectively, and guarantee the optimal energy scheduling that satisfies the consumers load demands efficiently.

Scalable Data Processing for Prediction, Batch Computation and Analysis and Response Times using Google BigQuery

Computing a complex dataset analysis is tedious task because distributed resource management is difficult task. Google disperses the registering utilized by BigQuery across process assets powerfully which implies that we don't need to oversee figure asset, for example, bunches, register motor, stockpiling structure. Fighting commitments customarily require custom estimating (and esteeming) of unequivocal procedure gatherings, and this can change after some time which can be trying. Since Google logically assigns resources, costs are dynamic too. Google offers both a compensation all the more just as costs emerge elective where you pay for the data brought into BigQuery and subsequently per question costs. Since BigQuery is a totally managed organization, the backend game plan and tuning is managed by Google. This is much more direct than battling plans that anticipate that you should pick a number and sort of gatherings to make and to administer after some time. BigQuery consequently recreates information between zones to empower high accessibility. It additionally naturally load adjusts to give ideal execution and to limit the effect of any equipment disappointments. So getting benefits of BigQuery we did complex data analysis in huge amount of data set within a friction of second. Our result is showing the capability of our research work in the field of scalable data processing.

Design and Implementation of Distributed Resource Management and Platform Deployment Based on Logical Clock

Design and Implementation of Distributed Resource Management and Platform Deployment Based on Logical Clock

Resource Scalability and Security Using Entropy Based Adaptive Krill Herd Optimization for Auto Scaling in Cloud

Cloud Computing has changed the way we are thinking about computer security and the way how corporations organize their internal processes. Therefore the Cloud computing is a new paradigm to convey computing architecture and assistance in acquiring the chances and difficulties in the region of distributed resources management. Resource scalability and security are the two major issues under Infrastructure as a Service (IaaS) of resource allocation. In this manner, the Entropy-based Adaptive Krill herd optimization for auto-scaling in the cloud is proposed. Here, auto-scaling is a significant cloud computing feature under IaaS, which is utilized to dynamically assign computational resources to applications to coordinate their present loads absolutely, in this way removing resources that would diversely stay idle and waste power. In the first stage, the task is monitored by determining the trust-based anomaly detection objectives such as Frequency Value, Trust Hypothesis Statistics, trust factor value, and trust policy. At that point, the given task is scheduled to find the task status. Then it is scaled using the execution time and workload calculation. After that, the scaled data is optimized utilizing the entropy-based krill herd algorithm. At long last, the comparisons of the proposed and existing methods are evaluated.

Energy-efficient task-resource co-allocation and heterogeneous multi-core NoC design in dark silicon era

To address power limitation issues in dark silicon era for multi-core systems-on-chip and chip multiprocessors, run time task-resource and voltage co-allocation with reconfigurable network-on-chip (NoC) framework for energy efficiency (higher performance/watt) is proposed in this work. Distributed resource managers strategy dynamically reconfigures the voltage/frequency-levels of the NoC links and routers and dynamically power-gates the resources depending on the traffic demands and utilization of the resources. A mapping heuristic, namely MinEnergy, has been proposed to minimize overall chip power and energy hotspots in large-scale NoC. We have formulated the mapping and configuration problem into a linear optimization model for the optimal solution and implemented a state-of-the-art Minimum-Path contiguous mapping for comparisons. Simulations are carried out under real-world benchmarks and platforms to demonstrate the effectiveness and efficiency of the proposed schemes and results show that the energy, power, and performance of the proposed dynamic mapping and configuration solution are significantly better (more than 50%) than those of minimum-path mapping solution, while the energy and power consumption of the proposed solution are more than 90% close to the optimal solution.

Resource Management for Secure Computation Offloading in Softwarized Cyber–Physical Systems

The evolution of the Internet of Things (IoT) makes an increased emphasis on extending their computing and storage capabilities by relying particularly on the cloud/edge computing (EC) for cyber-physical systems (CPSs). Especially, in software-defined CPS (SD-CPS), different software-defined networking (SDN) controllers share information and cooperate to make global decisions. To further enhance system security during the information sharing process, we introduce blockchain technology into SD-CPS. However, because many security-related decisions are sensitive to latency, it is vital to minimize the system latency in blockchain-empowered SD-CPS. In this article, a blockchain-empowered distributed SD-CPS framework is proposed to realize consensus and distributed resource management by offloading data in a hybrid network paradigm that combines cloud computing and EC. Moreover, to adaptively implement offloading and control strategies while guaranteeing data security, we design a resource management scheme for reducing system latency and provide the flexibility of cooperation. To foster intelligence, we formulate the joint communication, computation, and consensus problems as a Markov decision process and use deep reinforcement learning to balance resource allocation, reduce latency, and guarantee data security. Compared with other schemes, simulation results verify the effectiveness of the proposed scheme, which performs better on self-adaptation decision making and system delay reduction.