A novel bio-inspired approach for VM load balancing and efficient resource management in cloud

In order to provide users timely and reliable services, resources and facilities in cloud data centers are often more than actual needs, which leads to low resource utilization and high operating costs. However, controling the quantity of resources and facilities may cause low throughput. Therefore, many researches are devoted to increasing resource utilization, improving jobs throughput and reducing operating costs through effective cloud resource management. The cloud resource management in cloud data center can be regarded as a multi-resource demand job allocation problem. This paper proposed an allocation algorithm of jobs based on deep reinforcement learning. The algorithm allocates waiting jobs to clusters respectively, so as to optimize throughput and improve resource utilization. The algorithm is implemented in cloud data center simulation model CloudSim. The experimental results show that the method based on Deep Reinforcement Learning is better than traditional method in multi-resource job allocation problem.

A cloud resource management framework for multiple online scientific workflows using cooperative reinforcement learning agents

Enterprise application performance determines business success levels because these systems enable decisive operational functions and decision processes. Cloud computing is an innovative management solution that provides adaptable systems, scalable abilities, and affordable operational costs for enterprise applications. Maximizing cloud benefits requires proper management of cloud resources to take complete advantage. The paper evaluates significant cloud resource management approaches, including auto-scaling, load balancing, resource optimization, and AI technology to handle performance issues. Multiple best practices are delivered that help achieve top application performance, reduced costs, and reliable operation. This text investigates modern cloud resource management patterns through edge computing analysis, serverless architecture, and sustainable cloud environment approaches for future cloud resource management frameworks. The adopted strategies shield applications from interruptions while creating adaptability and efficiency, allowing enterprises to meet their upcoming operational requirements.

Introduction. The competitiveness of land use within a market economy is determined by the equation of capital expenditures, labor power that integrates land into a single engineering procedure, as well as natural and anthropogenic means with the help of which land resources are leveraged, and soil fertility is restored by rational organization of the system of adaptive-landscape specific agriculture. Therefore, the relevance of research of environmental efficiency of land resources management as the basis of sustainable rural development is beyond any reasonable doubt.Purpose. The purpose of the article is to investigate the environmental efficiency of land resources management and its impact on sustainable rural development.Results. Based on the research findings of the totality of indicators of environmental efficiency of land resources management, we will distinguish those ones that make important analysis findings at the national level for such land resources agents as micro agents; mini-agents; general agents; the state; local agents; global agents. Among all the test items of environmental efficiency of land resources management, the agent of land interests “the state” responds to 26 indicators. In addition to the existing indicators, a number of multiplicative metrics has been added for analysis. By expertise, among the presented indicators we have selected 15 under three criteria – anthropogenic impact, reproduction, harmonization. At the same time, in the author's opinion, the environmental efficiency of land resources management of the rural economic sector is to ensure the efficient land use as a constituent of the environment. With provision for expert estimation, we have offered a set of evaluative criteria for the level of environmental efficiency of land resources management of the rural economic sector.Originality. There has been proposed the map of forecast impacts of indicators of environmental efficiency of land resources management, which shows an extremely high level of influence of environmental component of sustainable development on the integral estimation of land resources management, in particular indicators of the amount of used agricultural chemicals per 1 ha of area under crops, land resources usage per a unit of gross production, proportion of sunflower and bird rape in cropping system. A computer program was used to predict the change in the value of integrated efficiency of land resources management using the proposed methodological approach. This computer program, taking into account interinfluences, makes it possible to calculate the predictive influence ranking of indicators on the assessment of the integrated efficiency of land resources management.Conclusion. The article deals with the possibilities of land resources management within the framework of sustainable development of rural territories. The criteria for environmental efficiency of land resources management include: anthropogenic impact – the main indicator – the usage of agricultural chemicals per 1 ha of area under crops; reproduction – environmental and agrochemical assessment of soils; harmonization – the relative gravity of eroded lands acreage in the structure of agricultural fields. Multiplicative indicators, the essence of which is to assess the intensity and efficiency of the parties to land relations, are taken into account for each type of efficiency of land resources management. We have implemented the matrix of forecasts of integral efficiency of land resources management in the rural economic sector in reliance on the method of criterion diagnostics, which is based on the use of a program that takes into account maps of forecast impacts of indicators of environmental efficiency of conditional, relative and absolute input indicators. The practical importance of the obtained research results is that we not only have calculated the predictive rating of the impact of the criterion indicators on the assessment of the integrated efficiency of land resources management, but also the results of the change to 1 conditional score of the input indicator. This technique permitted to reveal the most significant influence on the effectiveness of specific environmental indicators – livestock density and specific gravity of the area under crops, fertilized with organic fertilizers, which indicates the impossibility of effective land use without livestock-raising development.

Cloud management faces with great challenges, due to the diversity of Cloud resources and ever-changing management requirements. For constructing a management system to satisfy a specific management requirement, a redevelopment solution based on existing management systems is usually more practicable than developing the system from scratch. However, the difficulty and workload of redevelopment are also very high. As the architecture-based runtime model is causally connected with the corresponding running system automatically, constructing an integrated Cloud management system based on the architecture-based runtime models of Cloud resources can benefit from the model-specific natures, and thus reduce the development workload. In this paper, we present an architecture-based approach to managing diverse Cloud resources. First, manageability of Cloud resources is abstracted as runtime models, which could automatically and immediately propagate any observable runtime changes of target resources to corresponding architecture models, and vice versa. Second, a customized model is constructed according to the personalized management requirement and the synchronization between the customized model and Cloud resource runtime models is ensured through model transformation. Thus, all the management tasks could be carried out through executing programs on the customized model. The experiment on a real-world cloud demonstrates the feasibility, effectiveness and benefits of the new approach to integrated management of Cloud resources

The trend of adopting Internet of Things (IoT) in healthcare, smart cities, Industry 4.0, and so on is increasing by means of cloud computing, which provides on-demand storage and computation facilities over the Internet. To meet specific requirements of IoT applications, the cloud has also shifted its service offering platform to its next-generation models, such as fog, mist, and dew computing. As a result, the cloud and IoT have become part and parcel of smart applications that play significant roles in improving the quality of human life. In addition to the inherent advantages of advanced cloud models, to improve the performance of IoT applications further, it is essential to understand how the resources in the cloud and cloud-influenced platforms are managed to support various phases in the end-to-end IoT deployment. Considering this importance, in this article, we provide a brief description, a systematic review, and possible research directions on every aspect of resource management tasks, such as workload modeling, resource provisioning, workload scheduling, resource allocation, load balancing, energy management, and resource heterogeneity in such advanced platforms, from a cloud perspective. The primary objective of this article is to help early researchers gain insight into the underlying concepts of resource management tasks in the cloud for IoT applications.

FT-Aurora: A highly available IaaS cloud manager based on replication

The rapid evolution of cloud technologies has transformed the way enterprises manage their IT infrastructure and services. As organizations increasingly adopt cloud-based solutions, the need for efficient lifecycle management of cloud resources has become critical. Microservices architecture has emerged as a powerful solution to enhance automation within cloud lifecycle management. This approach enables the decomposition of complex, monolithic systems into smaller, independently deployable services, which can be orchestrated and managed seamlessly in the cloud environment. By leveraging microservices, organizations can build scalable, resilient, and agile systems that improve the flexibility of API-driven automation processes. In this paper, we explore the application of microservices architecture for API-driven automation in cloud lifecycle management. We examine how microservices provide a modular approach to the creation, deployment, and management of cloud resources by offering independent services that communicate via APIs. These services can be dynamically orchestrated to automate key aspects of cloud lifecycle management, including provisioning, scaling, monitoring, and decommissioning resources. The paper also discusses the integration of microservices with various cloud platforms and tools to enable continuous delivery, real-time monitoring, and improved governance. Through this exploration, we aim to highlight the advantages of using microservices in automating cloud lifecycle processes, emphasizing the potential for increased efficiency, cost savings, and reduced operational complexity. The findings underscore how microservices, when paired with API-driven automation, can drive significant improvements in cloud resource management, empowering organizations to better align their infrastructure with evolving business needs

Enterprise risk forecasting in human resource management in cloud computing using cascaded block visual modelling, artificial hummingbird guided graph attention networks

This study addresses the critical need for effective resource management through software container migration in cloud data centers. It emphasizes its role in avoiding resource shortages and reducing energy consumption in cloud environments. This study introduces a novel multi-objective integer linear programming (ILP) approach for software container replacements, complemented by a specialized algorithm designed to migrate software containers between over- and underutilized hosts to enhance efficiency compared to traditional optimization methods. The simulation results demonstrate the algorithm's effectiveness, validating its potential for optimizing energy usage and resource allocation in cloud environments. Statistical analyses confirm the proposed model's and algorithm's superiority over benchmark approaches, highlighting their potential for enhancing resource management in cloud computing systems.

Abstract: Online resource management in cloud computing must respond to rapidly changing demand and system conditions, often exceeding the adaptability of static or periodically recomputed optimisation plans. This study formulates cloud resource management as a Markov decision process (MDP) and investigates deep reinforcement learning (DRL) as an approximate dynamic programming (ADP) approach for deriving adaptive control policies. The system state encompasses workload, capacity utilisation, and performance indicators, while actions govern virtual machine placement, scaling, and server power-state transitions. Reward functions combine energy and operating costs with penalties associated with service-level agreement violations. DRL algorithms, including deep Q-networks, advantage actor–critic, and proximal policy optimization, are implemented in PyTorch and trained through interaction with a CloudSim-based simulation environment calibrated to realistic load and power profiles. The learned policies are evaluated against deterministic and scenario-based stochastic optimisation baselines using metrics such as average cost, energy consumption, SLA violations, and robustness to non-stationary demand. Results show that DRL policies can approach or surpass the performance of stochastic optimisation solutions in highly dynamic scenarios, while maintaining feasible control actions. The study demonstrates how DRL can be positioned within an OR/ADP framework and highlights conditions under which learning-based methods offer significant advantages for online cloud control. Keywords: deep reinforcement learning, approximate dynamic programming, cloud computing, Markov decision processes, online resource management, energy-aware control, PyTorch, simulation

Optimal resource management in cloud computing

Efficient cloud resource management is vital, as it ensures the accurate selection and allocation of resources to diverse workloads or applications. This entails real-time balancing of workload performance, compliance, and cost to achieve optimization. Since there are many cloud users involved in scheduling tasks, or cloudlets, the scheduling process becomes complex. It involves selecting appropriate data centers, servers (hosts), and virtual machines (VMs). There are several bioinspired algorithms that are effective and popular for solving the NP-complete problem of cloudlet scheduling. By using these algorithms, cloudlets can be efficiently allocated to achieve faster execution times, better resource utilization, and a shorter waiting time. This study presents a hybrid technique that combines the strengths of both ant colony optimization and locust-inspired algorithm (HACO-LA), which have been shown to outperform other bio-inspired algorithms in cloud computing environments. Implementing this technique will lead to a decrease in the average response time, while also increasing the utilization of VMs and servers. The method was evaluated using the Cloud Sim toolbox with authentic data. It was compared to the preexisting Artificial Bee Colony Optimization (ABC) algorithm and Particle Swarm Optimization (PSO) algorithm. The findings demonstrated that HACO-LA surpassed both methods, leading to notable enhancements in server utilization, increased reliability, and decreased average response time.

The proliferation of the Internet of things (IoT) has enabled the penetration of many smart devices in order to enhance the life quality of people. The IoT devices generate unprecedented amounts of data, and IoT services mandate faster processing of those generated data. Current explorations use cloud computing as a foundation to process latency-sensitive IoT applications. Nevertheless, cloud environment has limitations in terms of geographical centralized architecture, multi-hop distance from the data source which adversely affects the latency sensitivity of the IoT services. To combat this issue, the fog computing has emerged as a promising paradigm that provides cloud-like elastic services to the close proximity of end devices. Hence, fog-assisted cloud computing environments can be used to execute the time-critical IoT applications. However, the fog environment includes the large number of fog devices which are typically resource-constrained, heterogeneous, distributed, dynamic, and less energy-efficient than the centralized cloud. Hence, the efficient secure resource management in fog is still a challenging issue. Quantum computing techniques can be envisioned as an effective means of providing secure and efficient resource management solutions in fog environments. Therefore, this paper discusses the concerns and challenges associated with the quantum computing-based fog resource management approaches and highlights the promising future research directions.KeywordsFog computingCloud computingInternet of thingsQuantum computing

Multiprotocol Label Switching (MPLS) and Differentiated Services (DiffServ) play a vital role for minimizing the congestion by efficient load balancing and management of the network resources used to support Quality of Service (QoS).The lower network delay and efficient forwarding mechanism enhancing the speed of packet transfer make it more suitable for implementing real-time applications such as Voice and Video Conferencing.This paper evaluates the performance measures such as Packet Delay Variation (PDV) and end-to-end delay when applying some case studies comprising numbers of routers serving different number of clients.Both (PDV) and (End-to-End Delay) are determined using combination of Open Shortest Path First (OSPF), DiffServ and MPLS protocols.The results may lead to the measures of selection of the appropriate protocol.