Average Resource Utilization Research Articles

Load Balancing Algorithm of API Gateway Based on Microservice Architecture for a Smart City

Abstract As the entrance of the computer systems, the API gateway is an indispensable part of the microservice architecture. To realize the load balancing of API gateway, this paper studies the load balancing algorithm of the API gateway based on the microservice architecture. In doing this, we analyze the microservice architecture level from the data layer, the basic layer, and other levels, take the container cloud as the carrier of the microservice architecture, combine it with the client and API gateway, and design the API gateway based on the microservice architecture. We then judge whether the microservice identifier in the request source of the API gateway client is included in the API gateway routing table and determine the service cluster to which the microservice belongs according to the microservice identifier. After retrieving the qualified backend microservice container list according to the service cluster information, it adopts a load balancing algorithm based on dynamic weight, takes central processing unit (CPU) utilization and memory utilization as parameters to evaluate the resource load of microservers, uses an extreme gradient lifting model to predict CPU utilization and memory utilization, calculates the weight of microservers based on the prediction results, selects the microserver with the highest weight value to make API gateway service requests, and initiates API gateway service calls to specific backend microservice containers, thereby completing the load balancing of the API gateway. The experimental results show that the average load balancing degree of the algorithm is about 95 %, the average network resource utilization rate is as high as 89 %, and the algorithm execution time is short.

Natural resources utilization efficiency evaluation, determinant of productivity change, and production technology heterogeneity across developed and developing G20 economies

Efficiently utilizing natural resources (NRs) and enhancing their productivity growth are crucial factors for sustainable economic growth in major global economies. Further production technologies heterogeneity among developed and developed G20 countries is vital to natural resource utilization efficiency (NRUE). To this end, the estimation of NRUE, natural resources total factor productivity, and technological gap ratio (TGR) is worth investigating. This study employed Data Envelopment Analysis (DEA) Super-SBM, Meta-frontier analysis, and the Malmquist productivity index to evaluate NRUE, TGR, and productivity changes among G20 countries from 1995 to 2020. The average Natural Resource utilization Efficiency (NRUE) among G20 countries is 0.7071, indicating an improvement potential of around 29.29% in natural resource conversion. Developed G20 economies have a natural resource utilization efficiency (NRUE) of 0.9528, higher than that of the NRUE (0.506) of developing G20 countries. Developed countries have a TGR of 0.9962, which is significantly higher than the TGR of developing countries at 0.6746, indicating a significant gap in production technology. Total factor productivity growth of 0.8 % was witnessed in developed countries while developing countries demonstrated a decline of 0.6 percent in Total Factor Productivity Change (TFPC) over the study period. Analyzing the decomposition of TFPC reveals technological change as the predominant factor influencing productivity change in G20 economies instead of efficiency changes. A Mann-Whitney U test has proved the existence of significant statistical differences in average NRUE, TGR, and technological change (TC) levels between developed and developing G20 countries.

Improved Performance and Cost Algorithm for Scheduling IoT Tasks in Fog–Cloud Environment Using Gray Wolf Optimization Algorithm

Today, the IoT has become a vital part of our lives because it has entered into the precise details of human life, like smart homes, healthcare, eldercare, vehicles, augmented reality, and industrial robotics. Cloud computing and fog computing give us services to process IoT tasks, and we are seeing a growth in the number of IoT devices every day. This massive increase needs huge amounts of resources to process it, and these vast resources need a lot of power to work because the fog and cloud are based on the term pay-per-use. We make to improve the performance and cost (PC) algorithm to give priority to the high-profit cost and to reduce energy consumption and Makespan; in this paper, we propose the performance and cost–gray wolf optimization (PC-GWO) algorithm, which is the combination of the PCA and GWO algorithms. The results of the trial reveal that the PC-GWO algorithm reduces the average overall energy usage by 12.17%, 11.57%, and 7.19%, and reduces the Makespan by 16.72%, 16.38%, and 14.107%, with the best average resource utilization enhanced by 13.2%, 12.05%, and 10.9% compared with the gray wolf optimization (GWO) algorithm, performance and cost algorithm (PCA), and Particle Swarm Optimization (PSO) algorithm.

A robust dynamic hydrogenation network layout model considering station capacity expansion and flexible transportation modes

The development of the hydrogen-fueled vehicle industry needs a mature hydrogenation network to provide a guaranteed source of hydrogen in the future. We propose a dynamic hydrogen supply network optimization model under demand uncertainty. The model incorporates the dynamic characteristics of the network, takes into account the linkages of units within the network as well as the hydrogenation network between cycles. Hydrogenation networks can be planned over multiple cycles and allow for capacity expansion of hydrogen production and refueling stations, and shifts in the way hydrogen is transported between sites. Robust optimization is used to deal with demand uncertainty. In the results of the case study obtained, resources within the network were fully utilized, costs within the network show economies of scale; the average resource utilization rate at each site reached 85.6 %; and the rate of meeting user demand reached more than 98.5 %. A hydrogenation network with sustainable operations was formed.

The epidemiology and healthcare burden of rare diseases requiring hospitalisation among adult patients in Langkawi, Malaysia: Insights from a pilot study.

In Malaysia, rare diseases affect fewer than 1 in 4,000 people. As of 2020, 491 rare diseases have been recorded in Malaysia, but with limited epidemiological data. As the first study in Malaysia, this retrospective cohort study examined the epidemiology and admission-related healthcare costs for adult rare disease patients in Langkawi. Among the 38 patients, rheumatological rare diseases topped the list (39.5%). The annual admission rate for rare diseases was 0.9%. Langkawi patients had lengthy hospital stays (9.7 days) and a 7.9% mortality rate. 23.7% of patients defaulted to follow-up, and 7.9% were referred to a tertiary hospital due to inadequate equipment or speciality care. Admission costs were Malaysian Ringgits (MYR) 244,598.63 (~US Dollars (USD) 51,280), with 80.2% from medication. The average healthcare resource utilisation was MYR 6,436.81/ patient/year (~USD 1,350/patient/year).

An Efficient Hybrid Optimizer for Resource Reuse in a Cloud Environment

In a cloud context, merging complimentary numerous virtual machines (VMs) on an existing physical machine (PM) is the primary method for optimizing physical resources. One well-known area of research concentrates on making better use of VM migration resources when taking into account the dynamically changing resource demands of VMs. Finding the ideal balance between the complexity and performance of the VM migration optimization is the problem here. On the one hand, effective resource reuse is achieved through VM migration planning, and on the other, VM migration frequency is decreased to improve migration efficiency. On the other hand, a cloud data centre’s enormous PM and VM population typically makes migration planning more challenging, which impedes the VM migration decision-making process. By reducing the number of VM migration options to make VM migration planning easier and address these issues, this study recommend a hybrid Ant Colony and Genetic Algorithm (AGO) resource pool architecture. Then, establishing this model as a base, we develop the hybrid resource-reuse optimization method, which maximizes resource utilization with a minimal number of VM migrations. Finally, we evaluate hybrid AGO using simulation testing and real-world trials on a working cloud platform. Compared to similar methods, the findings show that hybrid AGO increases average resource utilization by 15%, reduces the use of PMs by 15%, and decreases the average number of migrations by 30%.

Efficient task scheduling on the cloud using artificial neural network and particle swarm optimization

SummaryA difficult problem in the service‐oriented computing paradigm is improving task scheduler policy or resource provisioning.In order to increase the performance of cloud applications, this article primarily focuses on tasks for resource mapping policy optimization. With the aim of reducing makespan and execution overhead and increasing the average resource utilization, we suggested an efficient independent task scheduler employing supervised neural networks in this paper. The suggested ANN‐based scheduler uses the status of the cloud environment and incoming tasks as inputs to determine the optimal computing resource for a given assignment as a result that assembles our goal. We proposed a novel algorithm in this paper that uses a hybrid methodology based on a swarm intelligence algorithm (PSO) in combination with a machine learning technique (ANN). PSO is used to prepare the train and test dataset for the neural network. Results clearly state that suggested work achieves significant improvement to considered algorithms in makespan (45%–55%), average VM utilization (15%–20%), and execution overhead(20%–30%).

Optimizing Cloud Computing Applications with a Data Center Load Balancing Algorithm

Delivering scalable and on-demand computing resources to users through the usage of the cloud has become a common paradigm. The issues of effective resource utilisation and application performance optimisation, however, become more pressing as the demand for cloud services rises. In order to ensure efficient resource allocation and improve application performance, load balancing techniques are essential in dispersing incoming network traffic over several servers. The workload balancing in the context of cloud computing, particularly in the Infrastructure as a Service (IaaS) model, continues to be difficult. Due to available virtual machines and the limited resources, efficient job allocation is essential. To prevent prolonged execution delays or machine breakdowns, cloud service providers must maintain excellent performance and avoid overloading or underloading hosts. The importance of task scheduling in load balancing necessitates compliance with Service Level Agreement (SLA) standards established by cloud developers for consumers. The suggested technique takes into account Quality of Service (QoS) job parameters, VM priorities, and resource allocation in order to maximise resource utilisation and improve load balancing. The proposed load balancing method is in line with the results in the body of existing literature by resolving these problems and the current research gap. According to experimental findings, the Dynamic LBA algorithm currently in use is outperformed by an average resource utilisation of 78%. The suggested algorithm also exhibits excellent performance in terms of accelerated Makespan and decreased execution time.

Cyclic transmission window-based bandwidth allocation scheme for asynchronous time-sensitive industrial applications in TDM-PON

The industrial Internet has become an important application scenario for time-division multiplexing passive optical networks (TDM-PONs). Time-sensitive (TS) industrial applications, such as control-to-control communications, require a TDM-PON to have deterministic transmission capability. Traditional bandwidth allocation schemes are unable to fulfill this capability; thus we proposed a time-aware deterministic bandwidth allocation (TA-DetBA) scheme to guarantee deterministic delay and jitter in our previous work. TA-DetBA allocates appropriate transmission windows (TWs) to each TS industrial flow in a supercycle based on the flow’s arrival time, cycle, delay, and jitter requirements. However, “awaring” the arrival time of flow relies on precise time synchronization between the TDM-PON and industrial devices, which makes TA-DetBA unsuitable for those TS industrial applications that are asynchronous to the TDM-PON. In addition, the diversity of flow cycles may make the size of the supercycle and the number of allocated TWs large, thus increasing the complexity of the TW scheduling algorithm. To this end, we propose a cyclic TW-based deterministic bandwidth allocation (CTW-DetBA) scheme for asynchronous industrial applications. First, we design cyclic TWs with appropriate cycle and size for TS industrial flows, which not only improves the schedulability of TWs (i.e., the ratio of the number of successfully scheduled TWs to the total number of TWs) but also reduces the complexity of the algorithm. Then, we construct a TW scheduling model based on the satisfiability model theory to schedule the TWs in the PON upstream frame. Simulation results show that the CTW-DetBA guarantees the deterministic transmission of TS industrial flows that are asynchronous to the TDM-PON system. Compared with the fixed bandwidth allocation scheme, the average schedulability of the CTW-DetBA can be increased by up to 62.03%, and the average resource utilization efficiency can be increased by up to 20.4%.

Optimal Worker Allocation of Food Manufacturing System using Simulation and Data Envelopment Analysis

This study suggests employing simulation and data envelopment analysis to support decision making for determining the optimal worker allocation for a food manufacturing production line. The simulation model for food production is based on a real-world example from the food industry, focusing on a manufacturing company. The challenge faced by the company involves a constrained number of workers allocated to four processes. The imbalance number of workers in each process will affect the productivity of the company. Through simulation modeling of the actual systems, it was discovered that the filling process presents a bottleneck due to its significantly higher average waiting time compared to the other processes. A valid simulation model was subsequently employed to generate potential improvements. Nineteen improvement models were proposed and assessed based on various selection criteria, including average total production time, average number of entities still in the system, total production, and average resource utilization. Among the nineteen improvement models, Improvement Model 11 (IM11) emerged as the best improvement model. The optimal worker allocation alternative involves assigning two workers to each process, leading to anticipated increases in total production and average resource utilization. Utilizing simulation and data envelopment analysis can help the management of the company to make better decisions in determining the optimal worker allocation.

Network Resource Allocation Algorithm Using Reinforcement Learning Policy-Based Network in a Smart Grid Scenario

The exponential growth in user numbers has resulted in an overwhelming surge in data that the smart grid must process. To tackle this challenge, edge computing emerges as a vital solution. However, the current heuristic resource scheduling approaches often suffer from resource fragmentation and consequently get stuck in local optimum solutions. This paper introduces a novel network resource allocation method for multi-domain virtual networks with the support of edge computing. The approach entails modeling the edge network as a multi-domain virtual network model and formulating resource constraints specific to the edge computing network. Secondly, a policy network is constructed for reinforcement learning (RL) and an optimal resource allocation strategy is obtained under the premise of ensuring resource requirements. In the experimental section, our algorithm is compared with three other algorithms. The experimental results show that the algorithm has an average increase of 5.30%, 8.85%, 15.47% and 22.67% in long-term average revenue–cost ratio, virtual network request acceptance ratio, long-term average revenue and CPU resource utilization, 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.

Healthcare resource utilization of patients with mitochondrial disease in an outpatient hospital setting

Background and objectivesMitochondrial diseases present as multi-system disorders requiring a comprehensive multidisciplinary approach. The data on healthcare resource utilization associated with mitochondrial diseases and the clinical drivers of these costs are limited including for the out-patient setting where the majority of the clinical care for mitochondrial disease patients occurs. We performed a cross-sectional retrospective study of out-patient healthcare resource utilization and costs for patients with a confirmed diagnosis of mitochondrial disease.MethodsWe recruited participants from the Mitochondrial Disease Clinic in Sydney and stratified them into three groups: those with mitochondrial DNA (mtDNA) mutations (Group 1), those with nuclear DNA (nDNA) mutations and the predominant phenotype of chronic progressive external ophthalmoplegia (CPEO) or optic atrophy (Group 2) and those without a confirmed genetic diagnosis but clinical criteria and muscle biopsy findings supportive of a diagnosis of mitochondrial disease (Group 3). Data was collected through retrospective chart review and out-patient costs were calculated using the Medicare Benefits Schedule.ResultsWe analyzed the data from 91 participants and found that Group 1 had the greatest average out-patient costs per person per annum ($838.02; SD 809.72). Neurological investigations were the largest driver of outpatient healthcare costs in all groups (average costs per person per annum:—Group 1: $364.11; SD 340.93, Group 2: $247.83; SD 113.86 and Group 3: $239.57; SD 145.69) consistent with the high frequency (94.5%) of neurological symptoms. Gastroenterological and cardiac-related out-patient costs were also major contributors to out-patient healthcare resource utilization in Groups 1 and 3. In Group 2, ophthalmology was the second-most resource intensive specialty ($136.85; SD 173.35). The Group 3 had the greatest average healthcare resource utilization per person over the entire duration of out-patient clinic care ($5815.86; SD 3520.40) most likely due to the lack of a molecular diagnosis and a less customized management approach.ConclusionThe drivers of healthcare resource utilization are dependent on the phenotype–genotype characteristics. Neurological, cardiac, and gastroenterological costs were the top three drivers in the out-patient clinics unless the patient had nDNA mutations with predominant phenotype of CPEO and/or optic atrophy wherein ophthalmological-related costs were the second most resource intensive driver.

Cooperative-Aware Radio Resource Allocation Scheme for 5G Network Slicing in Cloud Radio Access Networks.

The 5G network is designed to serve three main use cases: enhanced mobile broadband (eMBB), massive machine-type communications (mMTC), and ultra-reliable and low-latency communications (uRLLC). There are many new technological enablers, including the cloud radio access network (C-RAN) and network slicing, that can support 5G and meet its requirements. The C-RAN combines both network virtualization and based band unit (BBU) centralization. Using the network slicing concept, the C-RAN BBU pool can be virtually sliced into three different slices. 5G slices require a number of Quality of service (QoS) metrics, such as average response time and resource utilization. In order to enhance the C-RAN BBUs utilization while protecting the minimum QoS of the coexisting three slices, a priority-based resource allocation with queuing model is proposed. The uRLLC is given the highest priority, while eMBB has a higher priority than mMTC services. The proposed model allows the eMBB and mMTC to be queued and the interrupted mMTC to be restored in its queue to increase its chance to reattempt the service later. The proposed model's performance measures are defined and derived using a continuous-time Markov chain (CTMC) model and evaluated and compared using different methodologies. Based on the results, the proposed scheme can increase C-RAN resource utilization without degrading the QoS of the highest-priority uRLLC slice. Additionally, it can reduce the forced termination priority of the interrupted mMTC slice by allowing it to re-join its queue. Therefore, the comparison of the results shows that the proposed scheme outperforms the other states of the art in terms of improving the C-RAN utilization and enhancing the QoS of eMBB and mMTC slices without degrading the QoS of the highest priority use case.

Neural network inspired differential evolution based task scheduling for cloud infrastructure

In recent years, cloud computing has become an essential technology for businesses and individuals alike. Task scheduling is a critical aspect of cloud computing that affects the performance and efficiency of cloud infrastructure. During this pandemic where most of the healthcare services like COVID-19 sampling, vaccination process, patient management and other services are dependent on cloud infrastructure. These services come with huge clients and server load in a small instance of time. These task loads can only be managed at cloud infrastructure where an efficient resource management algorithm plays an important role. The optimal utilization of cloud infrastructure and optimization algorithms plays a vital role. The cloud resources rely on the allocation policy of the tasks on cloud resources. Simple static, dynamic, and meta-heuristic techniques provide a solution but not the optimal solution. In such a scenario machine learning and evolutionary algorithms are only the solution. In this work, a hybrid model based on meta-heuristic technique and neural network is proposed. The presented neural network inspired differential evolution hybrid technique provides an optimal assignment of the tasks on cloud infrastructure. The performance of the DE-ANN hybrid approach is performed using performance metrics, average start time(ms), average finish time(ms), average execution time(ms), total completion time(ms), simulation time(ms), and average resource utilization respectively. The proposed DE-ANN approach is validated against BB-BC, and Genetic approaches. It outperforms the existing meta-heuristic techniques i.e. Genetic approach, and Big-Bang Big-Crunch. The performance is evaluated using two configuration scenarios using 5 virtual machines and 10 virtual machines with varying tasks from 1000 to 4500. Experimental results show that the DE-ANN technique significantly improves task scheduling performance compared to other traditional techniques. The technique achieves an average improvement of 19.15% in total completion time(ms), 32.23% in average finish time(ms), 51.95% in average execution time(ms), and 33.24% in average resource utilization respectively. The DE-ANN technique is also effective in handling dynamic and uncertain environments, making it suitable for real-world cloud infrastructures.

Time-aware deterministic bandwidth allocation scheme in TDM-PON for time-sensitive industrial flows

A programmable logic controller deployed in the cloud or edge cloud (cloud PLC) contributes to flexible and scalable industrial manufacturing processes. For the industrial Internet, a time-division multiplexing passive optical network is a promising access technology for connecting cloud PLC and industrial devices. Time-sensitive (TS) industrial applications such as motion control and mobile robotics impose strict delay and jitter requirements, pursuing deterministic transmission capability, that is, guaranteeing that the upper bounds on delay and jitter of the TS industrial flow meet its requirements. However, traditional bandwidth allocation schemes aim to leverage statistical multiplexing to improve bandwidth resource utilization efficiency, so it guarantees only the “average delay/jitter” of the service and cannot meet the deterministic requirements of the TS industrial flow. This paper presents a time-aware deterministic bandwidth allocation (TA-DetBA) scheme to satisfy the deterministic transmission of TS industrial flows. To this purpose, first, we constrain the position of the transmission window (i.e., bandwidth) allocated by optical line termination to the optical network unit according to the arrival characteristics (i.e., flow arrival time and flow cycle) and requirements (i.e., delay and jitter) of the flow. Subsequently, we propose an integer linear programming scheduling model and a greedy-based time slot equalization heuristic scheduling algorithm to improve schedulability and reduce the average delay of best-effort flows. Simulation results show that our proposed TA-DetBA scheme guarantees the deterministic delay and jitter of TS industrial flow. Compared with the fixed bandwidth allocation (FBA) scheme, the average resource utilization efficiency of the TA-DetBA scheme is improved by up to 20.6% higher than FBA.

Container‐based data‐intensive application scheduling in hybrid cloud‐edge collaborative environment

AbstractContainer virtualization technology represented by Docker has been widely used in the industry due to its advantages of lightweight, fast deployment, and easy portability. It can bring convenience to system deployment, operation, and maintenance. This article considers the implementation of AI‐based IoT applications based on Docker and container technology in a cloud‐edge collaborative environment. Three typical data‐intensive applications, preprocessing, training, and inference in machine learning, are deployed using Docker containers. For these three types of tasks, this article proposes a container‐based data‐intensive application scheduling framework. Using an attribute‐based data‐driven method, a new scheduling approach considering multiple weighting factors is proposed, which is called DICS‐OPT. The cloud nodes and edge nodes are scored and sorted uniformly. The container is scheduled to the node with the highest score, and then the task data is transmitted to the node to execute the task. NSGA‐III‐based genetic algorithm has been proposed to search for the optimal weighting factors. This article introduces the implementation of the prototype system and builds a cloud‐edge collaborative testbed consisting of Raspberry Pis and PCs. The performance evaluation results indicates that the proposed scheduling approach outperforms existing approaches. Compared with existing approaches, DICS‐OPT improves the average edge resource utilization by 10.05% to 69.04%, and saves the cloud resource cost by 16.02% to 36.68%.

Secure data storage and access for fish monitoring in cloud environment

Cloud computing (CC) refers to the on-demand availability of computer system resources, specifically data storage and computational power, without the user's direct active administration. Large cloud functions are usually split across multiple sites, each of which is a data center. Improve the security howerver, these method possess some disadvantages such as access time, resource utilization, limited computation and storage capacity. To overcome these challenges trapdoor-based NDSGA-II AC (Non-Dominated Sorting Genetic Algorithm Access Control) is proposed, In the proposed technique trapdoor has been used which reduces the energy consumption when compared to the existing systems. With the help of trapdoor access control and NDSGA-II, this paper stores water tank parameters in the cloud. A stream cipher algorithm (SCA) is utillize to encrypt the input data based on the water tank parameters collected with sensors. It is possible to store encrypted data in the cloud once the encrypting process is complete. To decrease energy consumption, average resource utilization, and access time, the trapdoor-based NDSGA-II access control is used. In this paper, Number Theory Research Unit (NTRU) cryptosystem, CP-ABE, and RBAC are used to analyze the performance of the proposed method. This proposed method reduces the encryption time by 11%, 16%, and 23% compared to the current method, and the access time by 8% and 15% compared to CP-ABE and RBAC.

Optimization Design and Performance Evaluation of U-Shaped Area Operation Procedures in Complex Apron

In view of the common U-shaped apron structure of large- and medium-sized airports at home and abroad, this study considered the optimization design and performance evaluation of the U-shaped apron operation procedure. First, by analyzing the physical structure characteristics and traffic operation characteristics of the U-shaped area, exclusive, partition-shared, and global-shared operation procedures of the U-shaped area were designed, and differentiated apron-operation rules and traffic models were constructed for different types of operation procedures. Then, from the perspectives of safety, efficiency, and environmental protection, a multi-dimensional evaluation index system of U-shaped area operation performance is established, and a classification measurement and comprehensive evaluation method based on critique is proposed. Finally, a traffic simulation model was established based on airport network topology modeling. We used Monte Carlo methods for the simulation in Python 3.6, and the experimental results show that, in the scenario of high-density traffic operation, compared with exclusive and partition-shared procedures, the implementation effect of the global shared procedure is very significant, and the apron operation capacity increased by 14.8% and 5.0%, respectively. The probability of aircraft conflict decreased by 32.2% and 11.8%, respectively, and the time of single conflict relief decreased by 16.1 s and 10.6 s, respectively. The average resource utilization in each U-shaped area increased by 66% and 25%, respectively, while the average daily carbon emissions of a single aircraft were reduced by 16.7 kg and 11.0 kg and the average daily fuel consumption of a single aircraft were reduced by 3.6 kg and 2.4 kg, respectively. The proposed method is scientific and effective and can provide theoretical and methodological support for optimizing the configuration of the scene operation mode of complex airports and for improving flight operation efficiency.

A Strategy of Multi-edge Collaborated Task Offloading Based on Edge Servers Placement in Metropolitan Area Networks

At present, multi-access edge computing is applied to “cloud-edge-terminal” collaborative computing, in which the task of computing offloading is used to unload the computing tasks of “terminal” to “edge”, i. e. edge servers, but the placement of edge servers is often not considered, resulting in low efficiency of computing offloading. Therefore, this paper proposes a multi-edge collaborative task unloading strategy for the effective placement of edge servers in 5G metropolitan area networks (MAN). First, the strategy weights the average user delay, the average edge server load and the average edge server resource utilization, and improves the firefly algorithm (FA) to optimize the number and effective location of edge servers. Secondly, a multi-edge collaborative task unloading architecture is presented. The computing tasks in this architecture can be executed locally, on a local server, on a remote server or in the “cloud”. The delay and energy consumption of the four unloading modes are modeled respectively. Thirdly, a new variable, i. e. the maximum cooperation cost that the “terminal” can bear, is introduced to attract more remote edge servers to cooperate to complete the calculation of the “terminal” task. Furthermore, the immune particle swarm optimization (IPSO) algorithm was designed to solve the problems of the traditional PSO algorithm. The simulation results show that the improved firefly algorithm can find the optimal coordinates of the edge server, and then carry out the task unloading of the multi-edge server. Compared with the local offload strategy, immune algorithm (IA) and PSO, the total cost of the proposed IPSO algorithm is reduced by 66.7%, 54% and 45.5%, respectively. Therefore, the algorithm in this paper can improve the execution efficiency of computing tasks and effectively reduce the total cost of the whole system.