Resource Requests Research Articles

Exploring communication media options in an inter-organizational disaster response coordination network using agent-based simulation

Large-scale disasters require rapid, well-coordinated responses from many organizations. This coordination involves extensive communication about specific needs, resource availability, optimal sizes and packaging of goods, and location and timing of deliveries. Faster, more accurate communication within the disaster response network translates to more effective response at the disaster site. This article presents a modeling project that assessed the effects of distinct communication media on response times within a centralized network. In the United States, the Federal Emergency Management Agency (FEMA) provides support and coordination among numerous responding agencies. An initial agent-based simulation model incorporated data from participant interviews and FEMA documentation about communication processes among response organization representatives. This model tracked effects of meetings, meeting scheduling, and bulletins on time required to complete the processing of requests. Following a second round of interviews and detailed observations during a national disaster exercise, we built a second agent-based simulation model that varied usage of email, phone, and face-to-face communications alongside a centralized information system and tracked the processing of anticipated, standard, and non-standard resource requests. Results show significant effects of different combinations of communication media on response times. Recommendations based on the study include: resist the temptation to schedule more than one meeting per day; use bulletins to disseminate information updates; supplement the centralized information system with direct interpersonal communication media such as email; and for unusual or difficult requests enable representatives to have in-person conversations or the closest alternative such as video teleconferencing with screen-sharing.

Efficient jobs scheduling approach for big data applications

Abstract The MapReduce framework has become a leading scheme for processing large-scale data applications in recent years. However, big data applications executed on computer clusters require a large amount of energy, which costs a considerable fraction of the data center’s overall costs. Therefore, for a data center, how to reduce the energy consumption becomes a critical issue. Although Hadoop YARN adopts fine-grained resource management schemes for job scheduling, it doesn’t consider the energy saving problem. In this paper, an Energy-aware Fair Scheduling framework based on YARN (denoted as EFS) is proposed, which can effectively reduce energy consumption while meet the required Service Level Agreements (SLAs). EFS not only can schedule jobs to energy-efficiency nodes, but also can power on or off the nodes. To do so, the energy-aware dynamic capacity management with deadline-driven policy is used to allocate the resources for MapReduce tasks in terms of the average execution time of containers and users request resources. And then, Energy-aware fair based scheduling problem is modeled as multi-dimensional knapsack problem (MKP) and the energy-aware greedy algorithm (EAGA) is proposed to realize tasks fine-grained placement on energy-efficient nodes. Finally, the nodes which have been kept in idle state for the threshold duration are turned off to reduce energy costs. We perform extensive experiments on the Hadoop YARN clusters to compare the energy consumption and executing time of EFS with some state-of-the-art policies. The experimental results show that EFS can not only keep the proper number of nodes in on states to meet the computing requirements but also achieve the goal of energy savings.

Efficient utilization of energy consumption in cloud environment

In the tremendous growth of the cloud computing, server consolidation plays a vital role. It gives more benefits also it gives the pollution towards the nature. Inspite of avoiding this, saving of energy in the data center or the cluster is more important. In this regard this paper proposes a method of which reduces the energy consumption. This is done by identifying the active physical machines and the remaining machines were kept in the sleep or off mode according to the user’s availability. Here Virtual Machines (VMs) are grouped under the particular types. Based on this type the customer’s resource request can be maintained.

Novel Node-Ranking Approach and Multiple Topology Attributes-Based Embedding Algorithm for Single-Domain Virtual Network Embedding

Network virtualization (NV) is a promising approach to remove the ossification of current Internet. Virtual network embedding (VNE) is the key issue in NV which efficiently and effectively maps various of virtual networks (VNs), with different node and link resource requests, onto the shared substrate network(s) with finite underlying resources. Previous VNE algorithms in the literature are mostly heuristic. Single network topology attribute and each node’s local resources are assisted to rank nodes in most heuristic algorithms, leading to inefficient resource utilization of substrate network in the long run. To deal with this issue, we propose the network topology attribute and network resource-considered algorithm (VNE-NTANRC). The VNE-NTANRC algorithm adopts a novel node-ranking approach to rank all substrate and virtual nodes before embedding each given VN. The novel node-ranking approach has two subapproaches and considers five important network topology attributes and global network resources altogether. One subapproach is able to calculate all node values (NoV) directly. The other subapproach, stimulating from the Google PageRank website algorithm, enables to calculate NoVs in a stable state. Simulation results reveal that VNE-NTANRC algorithm outperforms typical and latest heuristic algorithms, only considering single network topology attribute and local resources.

Deadline scheduling algorithm for sustainable computing in Hadoop environment

Cloud computing is popular choice for processing and analyzing large amounts of data. Organizations can easily manage and deploy powerful clusters that run different software environments and enable distributed processing. Scheduling is an important part of distributed computing that allows users to leverage the available resources for a faster computation time. In this paper we propose a generic scheduling algorithm that takes deadline constraints into consideration. We develop a cost model that estimates the remaining work load which allows the scheduler to properly prioritize jobs according to their upcoming deadlines. The cost model works with generic abstract resources requests such as virtual cores, memory and containers and determines the remaining running time based on the completed tasks. We validate the cost model and measure the performance of the scheduler by running several experiments on a cluster on Amazon EC2 and our algorithm performs as expected under different scenarios.

Stability Analysis on Resource Matching in Crowdsourced Manufacturing

Abstract Recently, the crowdsourced manufacturing concept attracts attention. In the crowdsourced manufacturing, each participant shares their manufacturing resources to improve asset efficiency. To realize this concept, it is important how to make matching between resource requests and offers which achieves high efficiency in fair way. In the view of fairness, matching stability is important. In this paper, we propose two stability indices: ‘number of blocking pairs’ and ‘loss caused by blocking pairs’. We evaluate the productivity efficiency and the matching stability of some representative optimization methods. The computational results show importance of resource matching selection considering features of crowdsourced manufacturing system.

An improved design of P4P based on distributed tracker

The P4P architecture is mainly composed of appTracker, iTracker and peer. The single appTracker manages sharing resources in the different ISP domains. Every peer registers with appTracker when joining the network, and then requests resources from appTracker. In this architecture, there is too much workload for the single appTracker, thus, the bottleneck problem often appears when the scale of the network is enlarged in this centralised structure. An improved design of P4P based on distributed tracker is proposed to solve the overload problem of single appTracker server. In the improved P4P system, a distributed tracker overlay network replaces the appTracker to manage the resources in the different ISP domains. The functions of iTracker arranged by ISP are extended and the info interfaces of the iTracker are designed in detail in order to realise sharing the resources among the different iTrackers. The experiments prove that the P4P framework based on the distributed tracker can solve the server bottleneck problem and improve the scalability and stability while maintaining the characteristics of locality and transmission capacity.

Matching Theory for Over-the-Top Service Provision in 5G Networks

Modern over-the-top (OTT) applications can be accessed via Internet connections over cellular networks, possibly shared and managed by multiple mobile network operators (MNOs). The OTT service providers (OSPs) need to interact with MNOs, requesting resources for serving users of different categories and with different quality-of-service requirements. For this purpose, OSPs need OTT application flow prioritization in resource allocation, while the network resource scheduling should respect network neutrality that forbids OSP prioritization. OSPs also need to request resources periodically, according to their performance goals, i.e., grade-of-service (GoS) level (blocking probability), causing delay in flows’ accommodation due to: 1) the time required for information exchange between OSPs and MNOs, affected by network congestion, and 2) the time required for flows to receive resources, affected by the number of concurrently active flows. Acknowledging the lack of OSP-oriented resource management approaches, we: 1) introduce a novel matching theoretic flow prioritization (MTFP) algorithm that respects network neutrality and 2) design analytical models that enable the thorough investigation of the GoS and delay performance in various scenarios. Our results (analytical and simulation) show that MTFP improves both metrics compared to the best effort approach, whereas its performance is affected by the number of flows and the resource allocation frequency.

An improved design of P4P based on distributed tracker

The P4P architecture is mainly composed of appTracker, iTracker and peer. The single appTracker manages sharing resources in the different ISP domains. Every peer registers with appTracker when joining the network, and then requests resources from appTracker. In this architecture, there is too much workload for the single appTracker, thus, the bottleneck problem often appears when the scale of the network is enlarged in this centralised structure. An improved design of P4P based on distributed tracker is proposed to solve the overload problem of single appTracker server. In the improved P4P system, a distributed tracker overlay network replaces the appTracker to manage the resources in the different ISP domains. The functions of iTracker arranged by ISP are extended and the info interfaces of the iTracker are designed in detail in order to realise sharing the resources among the different iTrackers. The experiments prove that the P4P framework based on the distributed tracker can solve the server bottleneck problem and improve the scalability and stability while maintaining the characteristics of locality and transmission capacity.

Dealing With Deans and Academic Medical Center Leadership: Advice From Leaders

The 2017 Association of Pathology Chairs Annual Meeting included a session for department chairs and other department leaders on “how to deal with deans and academic medical center leadership.” The session was focused on discussing ways to foster positive relationships with university, medical school, and health system leaders, and productively address issues and opportunities with them. Presentations and a panel discussion were provided by 4 former pathology chairs who subsequently have served as medical deans and in other leadership positions including university provost, medical center CEO, and health system board chair. There was a strong consensus among the participants on how best to deal with superiors about problems, conflicts, and requests for additional resources and authority. The importance of teamwork and accountability in developing a constructive and collaborative relationship with leaders and peers was discussed in detail. Effectiveness in communication, negotiation, and departmental advocacy were highlighted as important skills. As limited resources and increased regulations have become growing problems for universities and health systems, internal stress and competition have increased. In this rapidly changing environment, advice on how chairs can interact most productively with institutional leaders is becoming increasingly important.

Unevenness measurement using the support vector machine and dynamic multiservice load balancing with modified genetic algorithm in cloud-based multimedia system

Cloud computing is the most concerned and growing field in the real world, which is used by various fields to handle and manage the multimedia application due to availability of more amount of resources. At the time of multiple multimedia requests entering into the cloud server, fining and provisioning the required resources for the incoming multimedia requests of different king would be a more difficult task. In the existing system centralised hierarchical cloud-based multimedia system (CMS) is introduced which consists of elements such as resource manager, cluster head and server clusters. This word can assign the user required resources effectively with reduced cost. Also, existing research overcomes the load balancing problem which might occur at the time of multiple multimedia services with different characteristics entering into the system and allocating them in the server without considering their load capacity level using genetic algorithm. However, genetic algorithm would fail to find the optimal resource with optimal load level due to local search optimisation problem. A, load balancing cannot be done effectively in case of arrival of multimedia tasks with varying characteristics. This problem is resolved in the proposed research methodology by introducing the novel load balancing system in which both task unevenness problems and the genetic algorithms local search optimisation problems are resolved. This paper proposed an effective multimedia load balancing (MLB) scheme for CMS using support vector machine (SVM) and dynamic multiservice load balancing with adaptive genetic algorithm (AGA) (MLB-SVM-AGA). In this work, SVM is introduced for the purpose of quantifying the unevenness in the utilisation of multiple resources on a resource manager on the client side and confirmed at the server side in the each cluster. Unevenness scenario can be modelled as a mathematical hyperplane problem, but in most cases it is computationally intractable. Here, AGA is used for the purpose of solving the problem of dynamic load balancing. The experimental evaluation is conducted in the CloudSim toolkit for both proposed and existing research methodologies. The performance evaluation is done and the results demonstrate that AGA approach is able to dynamically spread the multimedia task load equally.

MultiPathP2P: a simple multipath ant routing system for P2P networks

This paper presents MultiPathP2P that is a new routing protocol dedicated to P2P system. MultiPathP2P relies on the social networks concepts where nodes are identified through their virtual addresses. The proposed protocol will decrease the routing overhead within the network. The main idea consists of using mobile agents in order to find optimal routes towards the destination nodes. These agents are generated by each network node. Whenever a network node plans to request a resource in the network, it set a local resource request rather than broadcasting it. Then, this request will be shared among the others nodes using the agents which are moving within the network. We also present a data routing protocol based on ant's general behaviour in order to increase the performance of MultiPathP2P. The simulation results show that our new algorithm provide a significant improvement in terms of various performance metrics compared to other protocols.

Designing a No-Wait Cyclic Schedule for a Class of Concurrent Repetitive Production Processes

The concurrent repetitive manufacturing processes sharing resources according to a mutual exclusion protocol are considered. A system of the processes is a composition of subsystems that consist of n cyclic processes sharing one resource. In case of resource conflicts between the processes regarding access to the resources a certain priority is used (e.g. FIFO rule) which guarantees starvation-free access of the processes to the shared resources. A class of systems which are structurally deadlock-free is considered, i.e. resource requests of repetitive processes can’t create closed loop. For this class of systems is searched conflict-free, cyclic schedule for which the processes never wait for the resources, i.e. resource conflicts are avoided and a priority rule is not in the operation. A structure of production processes sharing resources and the operation times are defined. The problem of computing the starting times of the processes for which a no-wait cyclic schedule exists is formulated in a declarative way using constraint programming (CP) method. The necessary and sufficient conditions for existence of a no-wait schedule in the n-process system are given and used to compute the possible schedules of the processes. An illustrative example is presented.

Non-Payment Incentive Mechanism Design for Resource Allocation in a Private Cloud System

Truthful resource request from users is the premise to achieve the maximum social welfare in an enterprise private cloud. To stimulate the truthfulness of users, most previous works mainly rely on introducing the payment, which however, might not be applicable in enterprise private clouds, where there is a lack of money transfer. To address this issue, this paper proposes non-payment but efficient mechanisms in private clouds to stimulate the truthfulness of the users and meanwhile maximize the social welfare. Moreover, different from previous works that allow only one job request from one user, this paper studies a more general model, where multiple jobs can be submitted by each user. Specifically, we consider two task models: the migration-admissible model and non-migration model. In the former model, jobs can be executed at different servers, and may undergo migration if necessary. Alternatively, in the latter model, jobs can only be executed at one server without migration. For both models, we design incentive resource allocation mechanisms to maximize the social welfare. Theoretically analysis shows that the proposed mechanisms are truthful for general monotonic profit functions and the worst-case performance on the social welfare are well-bounded within a constant factor of the optimal solution for linear profit functions. Simulation results also demonstrate that the performances of the proposed mechanisms are very close to the optimal solution, in terms of maximizing the social welfare.

Process of Development of a County-wide Crisis Care Plan - Riverside County, California, 2016-7.

Introduction: Disasters with substantial impacts to the health care and public health systems can have multiple reverberating effects, including the need to alter the medical standard of care as well as centrally control scarce medical resources. A current crisis care plan can help to establish an ethical and operational framework for stakeholders before such a disaster takes place. However, there are few examples of such a plan that cover large areas and health jurisdictions. This article describes the process of developing such a “Crisis Care Plan.”Methods: Plan developers from the Riverside County Department of Public Health and Riverside County Emergency Management Department first developed an ethical framework for decision making, followed by the development of a full operational crisis care plan with conditions for activation, life cycle and deactivation. The plan was then reviewed by major county stakeholders, including local emergency medical services, the county medical association and the hospital association, and additional comments incorporated. Before the final plan is implemented it will be submitted for public review and provider training materials will be developed.Results: The development of a prerequisite ethical framework helped to reduce the risk that the operational plan would cause or exacerbate care disparities by informing a blinded, objective process for evaluating resource requests centrally prior to distribution. The ethical framework served to establish the grounding principle of all lives having an equal claim on value. Stakeholders recognized the need for such a Crisis Care Plan and agreed with the underlying ethical principles. Stakeholders also contributed useful recommendations to enable the plan to operate in as successful a manner as possible under the difficult conditions within which it would exist.Discussion: The development of a clear ethical framework and the early identification and involvement of stakeholders can enable even very large health jurisdictions to construct crisis care plans that enable the best care under difficult circumstances, while protecting individual rights and incorporating the concerns of the public and the health care community.

Cell Selection and Resource Allocation in LTE-Advanced Heterogeneous Networks

A LTE-advanced heterogeneous network consists of many macrocells, and within each macrocell, there can have many picocells and user equipments (UEs). A UE within a macrocell can request resource blocks (RBs) from either the macrocell or a picocell within the macrocell. In this paper, two optimal problems are defined for the association of UEs, RBs, and heterogeneous cells. We show that both problems are equivalent to a 0/1 knapsack problem and, therefore, can be solved in pseudo-polynomial time by dynamic programming. Based on above two optimal problems, we, then, propose a cell selection and resource allocation (CSRA) scheme to solve the problem of allocating a UE to its macrocell or to a picocell within the macrocell. The design goal of picocells is to unload the traffic for the macrocell. When there are available RBs and UEs within the picocell, the CSRA scheme offloads UEs to the picocell to release the most number of RBs for the macrocell. Only when there are not enough RBs within a picocell and there are available RBs within the macrocell, for load balancing, the CSRA scheme moves some UEs to the macrocell. The CSRA scheme stops whenever the picocell is not overloaded or the macrocell does not have available RBs. Simulation results show that our proposed scheme performs better than the cell range expansion scheme in terms of goodput, loss rate, and delay.

An analysis of interlibrary loan services: a case study of a university in South Africa

PurposeThe landscape of teaching, learning and research has changed requiring the need for diverse information resources. Given the current budgetary constraints and financial conditions prevailing in many universities, sharing of information resources has become a necessity. The Interlibrary Loan (ILL) services have thus become an important service to meet the immediate needs of library users. The aim of this paper is to analyse the ILL services of the North-West University in South Africa from 2006 to 2016. Using statistical data, the paper shows the emerging pattern in borrowing and lending between institutions as well as determines the existence of correlations between borrowing and lending libraries. The results of this study show that ILL amongst libraries has decreased in the past 11 years. A need exists for increased awareness of ILL and there is need for technological innovations that will ensure that library users are able to request for information resources seamlessly.Design/methodology/approachThis is a quantitative study that uses ILL data from the North-West University. Data were downloaded from the SABINET ILL system using the three NWU JC codes. They were then collated and uploaded on excel spreadsheets. In the main, the excel spreadsheets were used to interpret the data. Further, the Statistical Package for Social Sciences (SPSS) software, in particular Spearman’s Correlation Analysis, was used to test correlations between data from libraries that requested information resources from NWU and data from libraries that supplied information resources to NWU during this period using Rumsey’s guidelines to interpret the correlations.FindingsThe findings of the study reveal that ILL among libraries in South Africa had generally declined owing mostly to the proliferation of online resources resulting to changes in user information-seeking behaviour. The decline is despite the challenges of low budgets received by most libraries for the acquisition of information resources. It can also be concluded that public university libraries still value ILL as demonstrated by the high number of items requested from other libraries. The findings also reveal that most ILL activities were conducted by public universities.Research limitations/implicationsIt was not possible to obtain the list of titles that have been requested and also to obtain the user’s details. This would have enabled the authors to determine the type of titles that are being requested, and the users that request them.Practical implicationsILL should continue to be enhanced in view of the challenge of dwindling library budgets against the escalating prices of information resources. There is also a need for user education so that they become aware of the ILL service. From experience, library users normally give up once they realize that what they wanted is not available through the local catalogue and this calls for librarians to create an awareness to users that ILL could help solve their frustrations.Social implicationsThese results show that ILL can play a significant role to level the playing field between the well-resourced libraries in urbanized regions or provinces and the poorly resourced ones in rural regions or provinces. This social justice aspect of ILL is probably the reason why better resourced libraries in South Africa have decided to remain in the scheme unlike other countries where better resourced libraries opted out of reciprocal arrangements with small and medium-sized institutions.Originality/valueThe study adds to a very limited number of studies emanating from Africa. A study of this nature has never been conducted in Africa, as previous studies were nationwide studies. As far as the authors know, this is the first study that uses ILL data to research the impact of the global financial crisis on libraries in Africa.

Joint cache resource allocation and request routing for in-network caching services

In-network caching is recognized as an effective solution to offload content servers and the network. A cache service provider (SP) always has incentives to better utilize its cache resources by taking into account diverse roles that content providers (CPs) play, e.g., their business models, traffic characteristics, preferences. In this paper, we study the cache resource allocation problem in a Multi-Cache Multi-CP environment. We propose a cache partitioning approach, where each cache can be partitioned into slices with each slice dedicated to a content provider. We propose a content-oblivious request routing algorithm, to be used by individual caches, that optimizes the routing strategy for each CP. We associate with each content provider a utility that is a function of its content delivery performance, and formulate an optimization problem with the objective to maximize the sum of utilities over all content providers. We establish the biconvexity of the problem, and develop decentralized (online) algorithms based on convexity of the subproblem. The proposed model is further extended to bandwidth-constrained and minimum-delay scenarios, for which we prove fundamental properties, and develop efficient algorithms. Finally, we present numerical results to show the efficacy of our mechanism and the convergence of our algorithms.

SDN-Based Resource Pooling to Provide Transparent Multi-Path Communications

Fueled by the ever growing consumption of digital content and services, providers of packet- switched networks suffer more and more a conflict between network engineering constraints and end-user usage patterns. This conflict is due to the fact that deployed networks exhibit low efficiency in their average resource utilization rate, which stands opposed to, at times, unsatisfiable resource request peaks generated by users. Multipath transmissions are theoretically able to temper this offset, but have been an uphill road due to the complexity they require to dominate. This article proposes a network paradigm able to transparently provide end users with such capabilities, by virtually pooling network resources through Software-Defined Networking. It is shown how this discipline may be deployed in current network infrastructures, while complying with the main 5G architectures envisaged so far. It is advocated how such an effort may allow service providers to meet users' expectations and strengthen profits without the need for unbearable financial investments, at the same time seamlessly improving their networks' performance, reliability, resource utilization efficiency and energy consumption. To demonstrate the technical feasibility and the potential benefits of the proposed approach, we present a set of emulation results showing that the sweet spot between n-fold performance increases and robust resilience properties can be practically met.

Stochastic scheduling for variation-aware virtual machine placement in a cloud computing CPS

As the most promising computing paradigm, cloud computing opens up new horizons for the area of high-performance distributed computing. Cyber-physical Systems (CPSs) present novel digital systems, which integrate computation, communication and the control of physical resource. Applied CPSs architecture in cloud computing can provide real-time and scalable resource monitoring and offer time-critical applications. With unrivaled scalability and flexibility, the CPSs based cloud services brings significant convenience to customers in need of elastic computing power. The quality of CPSs based cloud services is, to an large extent, determined by the performance of Virtual Machine (VM) placement algorithm for the data center. VM placement also effect the communication between applications and physical resource distribution in cloud computing CPSs.The traditional VM placement algorithm is built upon the two-tier architecture. With the presence of multi-media applications, the application level controller cannot accurately quantify the varying amount computing resources required by VMs at runtime. Consequently, lacking accurate resource demand for each VM, controller at the data center level cannot generate the VM placement with satisfactory feasibility. This architecture no longer fits the modern data centers. In this paper, the two tier VM placement framework is proposed to resolve this technical challenge. Our LP-based variation-unaware VM placement algorithm generates the VM placement with minimized energy consumption. On the other hand, our feasibility driven stochastic VM placement (FDSP) algorithm works seamlessly with the LP-based algorithm to achieve desirable feasibility of the placement. Our experimental results show that the LP-based variation unaware VM placement algorithm improves the energy consumption by 15.3% on average from the baseline algorithm. For test cases with resource request variations, the FDSP algorithm saves 15.7% energy cost compared to the “worst case scenario” of the traditional VM placement paradigm. On the other hand, it improves the feasibility by 50.0% compared to the “best case scenario”.