CN113535360B - Request scheduling method and device based on tenant granularity in software defined cloud - Google Patents
Request scheduling method and device based on tenant granularity in software defined cloud Download PDFInfo
- Publication number
- CN113535360B CN113535360B CN202110835633.4A CN202110835633A CN113535360B CN 113535360 B CN113535360 B CN 113535360B CN 202110835633 A CN202110835633 A CN 202110835633A CN 113535360 B CN113535360 B CN 113535360B
- Authority
- CN
- China
- Prior art keywords
- tenant
- request
- granularity
- requests
- fine
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/48—Program initiating; Program switching, e.g. by interrupt
- G06F9/4806—Task transfer initiation or dispatching
- G06F9/4843—Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
- G06F9/4881—Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5061—Partitioning or combining of resources
- G06F9/5072—Grid computing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0645—Rental transactions; Leasing transactions
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Finance (AREA)
- Mathematical Physics (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Computer And Data Communications (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The invention discloses a request scheduling method and device based on tenant granularity in a software defined cloud. Wherein the method comprises the following steps: collecting fine-grained requests in a current software-defined cloud system; according to request information in the fine-grained requests, aggregating the fine-grained requests into tenant granularity requests; and carrying out request scheduling and resource allocation on the tenant granularity request according to the tenant granularity request. Because the number of the aggregated tenant granularity requests is far lower than the number of the fine granularity requests, the tenant granularity request scheduling can greatly reduce the scheduling overhead, reduce the load of a scheduler and further improve the expandability of the system. In addition, when the tenant granularity request scheduling is carried out, in order to ensure tenant isolation, the scheme allocates the resources of each server to one tenant, so that the possibility that a plurality of tenants share one server resource is avoided, and the system safety and the tenant service quality are greatly improved.
Description
Technical Field
The embodiment of the invention relates to the technical field of fine-grained flow management in a software-defined network, in particular to a request scheduling method and device based on tenant granularity in a software-defined cloud.
Background
Cloud computing has driven the development of the internet industry by providing infrastructure as a service (IaaS) and software as a service (SaaS) services to tenants, which has received increasing attention from academia and industry. It is predicted that by 2022, the global cloud service market will be expected to grow to approximately 528.4 billion dollars. Wherein revenue from business users accounts for over 90% of the total revenue. Enterprise users purchase services from cloud service providers, then employees of the enterprises can submit their requests to the cloud, and finally the dispatcher is responsible for dispatching the requests to the appropriate servers. Each individual request represents a particular task, such as a model training task, and scheduling with individual requests at granularity is referred to as fine-grained request scheduling.
With the help of software-defined technology, the scheduler realizes fine-grained request scheduling, and has high flexibility and efficiency. In recent years, fine-grained request scheduling problems have been widely studied for different purposes, such as minimizing the number of servers used, saving power consumption, and minimizing the completion time of requests. While the fine-grained request scheduling approach helps to maximize system profits and achieve better resource utilization, it still faces the following two challenges.
The first challenge is system scalability. As cloud services have become available to reduce enterprise operating costs, increasing flexibility in resource deployment, more and more enterprises shift their workload to the cloud. For example, the number of enterprise tenants active on the alicloud has exceeded 50 tens of thousands. Even if a tenant submits only 100 fine-grained requests per second, the scheduler needs to schedule 5000 tens of thousands of fine-grained requests within one second. Thus, if scheduling is done with fine-grained requests, scheduling overhead, including scheduling decision delay and control bandwidth consumption, can be increased, reducing user quality of service.
The second challenge is tenant isolation. In the cloud, enterprise users may generate a large number of fine-grained requests. To increase resource utilization, cloud service providers may schedule requests of different tenants onto one server. This sharing of resources breaks tenant isolation, potentially leading to security vulnerabilities. Currently, there have been related studies showing that virtual machines sharing one server can detect the type and characteristics of applications of other virtual machines. With this information, malicious tenants can launch a wide range of network attacks, including denial of service attacks (DoS) and coreside attacks with high probability of success. Therefore, without considering tenant isolation, once a tenant generates a malicious request, security of other tenants sharing resources on the same server may be affected.
Disclosure of Invention
The invention provides a request scheduling method and device based on tenant granularity in a software defined cloud, which are used for improving the expandability of a system and improving the safety of the system and the service quality of tenants.
In a first aspect, an embodiment of the present invention provides a request scheduling method based on tenant granularity in a software defined cloud, including:
collecting fine-grained requests in a current software-defined cloud system;
according to request information in the fine-grained requests, aggregating the fine-grained requests into tenant granularity requests;
and carrying out request scheduling and resource allocation on the tenant granularity request according to the tenant granularity request.
Optionally, aggregating the fine-grained request into a tenant granularity request according to the request information in the fine-grained request includes:
dividing the fine-grained requests according to the tenant information and the service type information requested in the fine-grained requests to obtain tenant granularity requests;
each tenant granularity request comprises at least one fine granularity request with the same tenant information and service type information.
Optionally, before performing request scheduling and resource allocation on the tenant granularity request according to the tenant granularity request, the method further includes:
judging whether the bandwidth and the electric quantity of a rack in the software defined cloud system are overloaded or not;
if not, carrying out request scheduling and resource allocation on the tenant granularity request according to the tenant granularity request.
Optionally, when performing request scheduling and resource allocation on the tenant granularity request, allocating resources of a server to a tenant correspondingly.
In a second aspect, an embodiment of the present invention further provides a request scheduling device based on tenant granularity in a software defined cloud, including:
the collection module is used for collecting fine granularity requests in the current software defined cloud system;
the aggregation module is used for aggregating the fine-grained requests into tenant granularity requests according to the request information in the fine-grained requests;
and the scheduling module is used for carrying out request scheduling and resource allocation on the tenant granularity request according to the tenant granularity request.
Optionally, the aggregation module is specifically configured to: dividing the fine-grained requests according to the tenant information and the service type information requested in the fine-grained requests to obtain tenant granularity requests;
each tenant granularity request comprises at least one fine granularity request with the same tenant information and service type information.
According to the method, the system and the device, the fine-grained requests are aggregated into the tenant granularity requests, and then the tenant granularity requests are scheduled, and as the quantity of the tenant granularity requests is far smaller than the data quantity of the fine-grained requests, the scheduling cost is greatly reduced, the load of a scheduler is reduced, and the expandability of the system is improved. And when the tenant granularity request scheduling is carried out, the resources of each server are allocated to one tenant, so that the possibility that a plurality of tenants share one server resource is avoided, tenant isolation is realized, and the system safety and tenant service quality are greatly improved.
Drawings
FIG. 1 is a flowchart of a request scheduling method based on tenant granularity in a software defined cloud;
FIG. 2 is a diagram of network architecture and table entries in a tenant granularity request scheduling process;
fig. 3 is a schematic structural diagram of a request scheduling device based on tenant granularity in a software defined cloud according to the embodiment of the present invention.
Detailed Description
The invention is described in further detail below with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting thereof. It should be further noted that, for convenience of description, only some, but not all of the structures related to the present invention are shown in the drawings.
Examples
Fig. 1 is a flowchart of a request scheduling method based on tenant granularity in a software defined cloud, where the embodiment of the present invention is applicable to a case where a system schedules tenant requests in the software defined cloud, and the method may be executed by a request scheduling device based on tenant granularity in the software defined cloud, and specifically includes the following steps:
s110, collecting fine-grained requests in the current software defined cloud system.
Wherein scheduling with single request granularity is called fine-grained request scheduling. In this embodiment, all fine-grained requests present in the current software-defined cloud system are first collected by the scheduler.
S120, aggregating the fine-grained requests into tenant granularity requests according to request information in the fine-grained requests.
The request information in the fine-grained requests comprises tenant information and required service type information of each fine-grained request.
Correspondingly, in this embodiment, according to the request information in the fine-grained request, aggregating the fine-grained request into the tenant granularity request includes: dividing the fine-grained requests according to the tenant information and the service type information requested in the fine-grained requests to obtain a plurality of sets, wherein all the fine-grained requests in each set have the same tenant information and require the same service type. Then calculating the total amount of resources required by the fine-grained requests in each set, and constructing a tenant granularity request; each tenant granularity request comprises at least one fine granularity request with the same tenant information and service type information. Furthermore, the amount of resources required for each tenant-granularity request is the sum of the resources of all fine-granularity requests within the set.
S130, carrying out request scheduling and resource allocation on the tenant granularity request according to the tenant granularity request.
Specifically, resources are allocated according to the tenant granularity request, and further, the fine granularity request contained in the tenant granularity request is scheduled to the allocated resources (such as a server). Because the number of the request with the tenant granularity is far lower than that of the request with the fine granularity, the dispatching cost can be greatly reduced by using the request with the tenant granularity for dispatching, the load of a dispatcher is reduced, and the expandability of a system is improved.
In addition, when request scheduling and resource allocation are carried out on the tenant granularity request, resources of one server are allocated to one tenant as much as possible, so that the possibility that a plurality of tenants share one server resource is avoided, interference of malicious tenants to normal tenants is prevented, and service quality of the tenants is improved.
Further, before performing request scheduling and resource allocation on the tenant granularity request according to the tenant granularity request, the method further includes: judging whether the bandwidth and the electric quantity of a rack in the software defined cloud system are overloaded or not; if not, carrying out request scheduling and resource allocation on the tenant granularity request according to the tenant granularity request.
In particular, since the ToR switches on the racks implement communication between servers, the bandwidth capacity of the ToR switches may limit the bandwidth capacity of one rack. Thus, when scheduling requests at tenant granularity, the scheduler schedules the requests to the server below it only if the ToR switch has free bandwidth resources.
Since the power supply to each rack is limited and the power consumption of the servers placed on the rack is related to its load. Thus, when scheduling requests at tenant granularity, the scheduler schedules the requests to the servers below it only if the chassis is not overloaded with power consumption as well.
According to the technical scheme, when request scheduling and resource allocation are carried out on the tenant granularity request, bandwidth capacity constraint of the ToR switch on the rack and power consumption constraint of the rack are considered, the tenant request is scheduled under the condition that the bandwidth and the electric quantity of the rack are not overloaded, and the situation that the in-out flow and the power consumption of a server in the rack exceed the capacity can be avoided.
On the basis of the embodiment, the request scheduling method with the tenant granularity provided by the invention can coexist with the request scheduling method with the fine granularity. Specifically, the tenant granularity request scheduling can be performed first, and then for some underutilized servers, some fine granularity requests are independently scheduled to the servers in a fine granularity mode, so that the utilization rate of resources is improved.
Furthermore, the request scheduling method based on tenant granularity in the software defined cloud provided by the invention can be applied to various scenes. For example: 1) For enterprise users, they purchase SaaS products (such as online video and group call conferences) from cloud service providers. The method provided by the invention can realize the dispatching request based on the granularity of the tenant, so as to improve the expandability of the dispatcher. 2) In an enterprise's data center, such as Facebook, some servers handle requests from instragram users and some servers handle requests from WhatsApp users. By means of the request scheduling method, requests from Instagram and WhatsApp can be respectively aggregated into requests with tenant granularity, and scheduling of the requests can be achieved on the basis of the requests, so that scheduling cost can be reduced.
By way of example, with continued reference to fig. 2, fig. 2 is a network architecture and table entry diagram in a tenant granularity request scheduling process.
In this embodiment, it is assumed that four servers in the system provide the same service, including two tenants t1 and t2. When the fine-grained requests of the two tenants reach the scheduler of the control layer in the software-defined cloud, the scheduler aggregates the fine-grained requests into tenant-grained requests according to the tenant attributes of the requests and the service types of the requests. Since there are only two tenants t1 and t2 in the current system and only one service type, the fine-grained requests are divided according to the tenant attribute and the required service type to obtain two sets J1 and J2. Wherein J1 contains only the fine-grained request of tenant t1 and J2 contains only the fine-grained request of tenant t2. And then respectively calculating the total amount of resources required by the sets J1 and J2, and constructing logical tenant granularity requests Q1 and Q2. Under the condition that server resources, rack bandwidth and power are not overloaded, a scheduler performs resource scheduling on tenant granularity requests, and assuming that servers s1 and s2 are allocated to tenant granularity request Q1 and servers s3 and s4 are allocated to tenant granularity request Q2, fine granularity requests contained in tenant granularity request Q1 are scheduled to servers s1 and s2, and fine granularity requests contained in tenant granularity request Q2 are scheduled to servers s3 and s4. Corresponding matching rules are installed on the ingress switches 1 and 2 to realize request scheduling, and 4 rules are required to be installed in total to realize request scheduling, and the content of the rules is shown in fig. 2. Let Z be the number of fine-grained requests each tenant generates, T be the number of tenants in the network, and S be the number of service types provided by the system. Assuming that the computation overhead of the scheduler is related to the number of installed rules, if the tenant granularity request scheduling method is used, the scheduler only needs to install O (t·s) rule in the data layer, and if the fine granularity request scheduling method is used, O (t·s·z) rule is needed to implement request scheduling.
Fig. 3 is a schematic structural diagram of a request scheduling device based on tenant granularity in a software defined cloud according to the embodiment of the present invention. The device specifically comprises:
a collection module 210 for collecting fine-grained requests in the current software-defined cloud system;
an aggregation module 220, configured to aggregate the fine-grained request into a tenant granularity request according to request information in the fine-grained request;
and the scheduling module 230 is configured to perform request scheduling and resource allocation on the tenant granularity request according to the tenant granularity request.
Wherein, the aggregation module 220 is specifically configured to:
dividing the fine-grained requests according to the tenant information and the service type information requested in the fine-grained requests to obtain tenant granularity requests;
each tenant granularity request comprises at least one fine granularity request with the same tenant information and service type information.
Further, the device also comprises a judging module for judging whether the bandwidth and the electric quantity of the rack in the software defined cloud system are overloaded;
if not, carrying out request scheduling and resource allocation on the tenant granularity request according to the tenant granularity request.
Optionally, when performing request scheduling and resource allocation on the tenant granularity request, allocating resources of a server to a tenant correspondingly. The request scheduling device based on tenant granularity in the software defined cloud provided by the embodiment of the invention can execute the request scheduling method based on tenant granularity in the software defined cloud provided by any embodiment of the invention, has corresponding functional modules and beneficial effects of the execution method, and is not repeated.
Note that the above is only a preferred embodiment of the present invention and the technical principle applied. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, while the invention has been described in connection with the above embodiments, the invention is not limited to the embodiments, but may be embodied in many other equivalent forms without departing from the spirit or scope of the invention, which is set forth in the following claims.
Claims (3)
1. A request scheduling method based on tenant granularity in a software defined cloud is characterized by comprising the following steps:
collecting fine-grained requests in a current software-defined cloud system;
according to the request information in the fine-grained request, aggregating the fine-grained request into a tenant granularity request, including: dividing the fine-grained requests according to the tenant information and the service type information requested in the fine-grained requests to obtain tenant granularity requests; each tenant granularity request comprises at least one fine granularity request with the same tenant information and service type information;
according to the tenant granularity request, carrying out request scheduling and resource allocation on the tenant granularity request;
when request scheduling and resource allocation are carried out on the tenant granularity request, the resources of one server are correspondingly allocated to one tenant.
2. The method of claim 1, further comprising, prior to request scheduling and resource allocation for the tenant granularity request according to the tenant granularity request:
judging whether the bandwidth and the electric quantity of a rack in the software defined cloud system are overloaded or not;
if not, carrying out request scheduling and resource allocation on the tenant granularity request according to the tenant granularity request.
3. A request scheduling device based on tenant granularity in a software defined cloud, comprising:
the collection module is used for collecting fine granularity requests in the current software defined cloud system;
the aggregation module is used for aggregating the fine-grained requests into tenant granularity requests according to the request information in the fine-grained requests;
the dispatching module is used for carrying out request dispatching and resource allocation on the tenant granularity request according to the tenant granularity request;
the aggregation module is specifically used for: dividing the fine-grained requests according to the tenant information and the service type information requested in the fine-grained requests to obtain tenant granularity requests;
each tenant granularity request comprises at least one fine granularity request with the same tenant information and service type information;
when request scheduling and resource allocation are carried out on the tenant granularity request, the resources of one server are correspondingly allocated to one tenant.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110835633.4A CN113535360B (en) | 2021-07-23 | 2021-07-23 | Request scheduling method and device based on tenant granularity in software defined cloud |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110835633.4A CN113535360B (en) | 2021-07-23 | 2021-07-23 | Request scheduling method and device based on tenant granularity in software defined cloud |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113535360A CN113535360A (en) | 2021-10-22 |
| CN113535360B true CN113535360B (en) | 2023-07-28 |
Family
ID=78120662
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110835633.4A Active CN113535360B (en) | 2021-07-23 | 2021-07-23 | Request scheduling method and device based on tenant granularity in software defined cloud |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113535360B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104866244A (en) * | 2015-05-31 | 2015-08-26 | 上海交通大学 | RAID-6 I/O scheduling method for balancing strip writing |
| CN107135241A (en) * | 2016-02-26 | 2017-09-05 | 新华三技术有限公司 | A kind of method and device for business processing |
| CN108132775A (en) * | 2016-11-30 | 2018-06-08 | 新华三技术有限公司 | A kind of tenant manages system and method |
| CN108701059A (en) * | 2016-02-19 | 2018-10-23 | 华为技术有限公司 | Multi-tenant resource allocation methods and system |
| CN110377415A (en) * | 2018-04-12 | 2019-10-25 | 华为技术有限公司 | A kind of request processing method and server |
| CN112422450A (en) * | 2020-05-09 | 2021-02-26 | 上海哔哩哔哩科技有限公司 | Computer equipment, and flow control method and device for service request |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9912582B2 (en) * | 2013-11-18 | 2018-03-06 | Telefonaktiebolaget Lm Ericsson (Publ) | Multi-tenant isolation in a cloud environment using software defined networking |
-
2021
- 2021-07-23 CN CN202110835633.4A patent/CN113535360B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104866244A (en) * | 2015-05-31 | 2015-08-26 | 上海交通大学 | RAID-6 I/O scheduling method for balancing strip writing |
| CN108701059A (en) * | 2016-02-19 | 2018-10-23 | 华为技术有限公司 | Multi-tenant resource allocation methods and system |
| CN107135241A (en) * | 2016-02-26 | 2017-09-05 | 新华三技术有限公司 | A kind of method and device for business processing |
| CN108132775A (en) * | 2016-11-30 | 2018-06-08 | 新华三技术有限公司 | A kind of tenant manages system and method |
| CN110377415A (en) * | 2018-04-12 | 2019-10-25 | 华为技术有限公司 | A kind of request processing method and server |
| CN112422450A (en) * | 2020-05-09 | 2021-02-26 | 上海哔哩哔哩科技有限公司 | Computer equipment, and flow control method and device for service request |
Non-Patent Citations (3)
| Title |
|---|
| Jonathan Mace 等.2DFQ: Two-Dimensional Fair Queuing for Multi-Tenant Cloud Services.《SIGCOMM '16: Proceedings of the 2016 ACM SIGCOMM Conference》.2016,144-159. * |
| Workflow Scheduling in Multi-Tenant Cloud Computing Environments;Bhaskar Prasad Rimal 等;《IEEE Transactions on Parallel and Distributed Systems》;第28卷(第1期);290-304 * |
| 云计算弹性资源分配与作业调度策略优化研究;凌晓;《中国博士学位论文全文数据库 信息科技辑》(第2期);I139-15 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113535360A (en) | 2021-10-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107241281B (en) | Data processing method and device | |
| Andrzejak et al. | Bounding the resource savings of utility computing models | |
| CN100440891C (en) | Method for balancing gridding load | |
| US20080256238A1 (en) | Method and system for utilizing a resource conductor to optimize resource management in a distributed computing environment | |
| CN110071965B (en) | Data center management system based on cloud platform | |
| Khalifa¹ et al. | Collaborative autonomic resource management system for mobile cloud computing | |
| Mosa et al. | Dynamic virtual machine placement considering CPU and memory resource requirements | |
| Liu et al. | A survey on virtual machine scheduling in cloud computing | |
| CN106095581B (en) | Network storage virtualization scheduling method under private cloud condition | |
| Atiewi et al. | A review energy-efficient task scheduling algorithms in cloud computing | |
| CN115202836A (en) | Computational power pooling system for improving GPU utilization efficiency | |
| Karthik et al. | Resource scheduling approach in cloud Testing as a Service using deep reinforcement learning algorithms | |
| WO2022062981A1 (en) | Resource scheduling method and system, electronic device, and computer-readable storage medium | |
| Zhang et al. | A Multi-Agent based load balancing framework in Cloud Environment | |
| CN113535360B (en) | Request scheduling method and device based on tenant granularity in software defined cloud | |
| Huang et al. | Multi-resource packing for job scheduling in virtual machine based cloud environment | |
| CN110069319B (en) | Multi-target virtual machine scheduling method and system for cloud resource management | |
| Addya et al. | A hybrid queuing model for virtual machine placement in cloud data center | |
| Chunlin et al. | Elastic resource provisioning in hybrid mobile cloud for computationally intensive mobile applications | |
| CN114489978A (en) | Resource scheduling method, device, equipment and storage medium | |
| Zhou et al. | Fine-grained scheduling in multi-resource clusters | |
| Rahman et al. | Group based resource management and pricing model in cloud computing | |
| Liao et al. | Efficient and fair scheduler of multiple resources for MapReduce system | |
| CN110995863A (en) | Data center load distribution method and system based on load demand characteristics | |
| Chen et al. | Online scheduling strategy to minimize penalty of tardiness for real-time tasks in mobile edge computing systems |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |