Network resource allocation method and device based on load balancing, equipment and medium

Abstract

The embodiment of the invention discloses a network resource allocation method and device based on load balancing, equipment and a medium. The method comprises the following steps: segmenting a physical wireless local area network into at least two virtual network slices by adopting a network function virtualization algorithm and a software defined network algorithm, and carrying out customized configuration on the at least two virtual network slices; determining a load state and an average load of the at least two virtual network slices, and determining a network resource allocation quantity of the at least two virtual network slices according to the load state and the average load; configuring corresponding service quality parameters for the at least two virtual network slices, and allocating processing tasks of different levels according to the service quality parameters; and dynamically adjusting the network resource allocation quantities of the at least two virtual network slices according to the network resource allocation quantities and the processing tasks of the corresponding levels. By adopting the scheme, the network resources are reasonably allocated, the communication requirements of different applications can be met, and the utilization rate of the network resources is improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of wireless communication technology, and in particular to a network resource allocation method, device, equipment and medium based on load balancing. Background Art

[0002] With the development of smart grids, intelligent operation and maintenance (O&M) of power transmission and transformation equipment has become an indispensable part of the power system. Intelligent O&M uses advanced sensors, monitoring equipment and data analysis technology to achieve real-time monitoring, status assessment and fault warning of power transmission and transformation equipment, thereby improving the reliability and operating efficiency of the power system. However, these smart devices have put forward higher requirements on communication networks, especially in terms of data transmission speed, reliability and real-time performance.

[0003] Traditional communication network architectures are unable to simultaneously meet the diverse needs of power transmission and transformation equipment. Faced with different types of equipment and application scenarios, such as real-time monitoring requires low-latency, high-reliability communication links, while data transmission and analysis require high-bandwidth support, existing networks often have problems such as unreasonable resource allocation and network overload, which affect the performance and stability of the overall system.

[0004] Therefore, how to reasonably allocate network resources is an urgent problem that people in this technical field need to solve. Summary of the invention

[0005] The purpose of the present invention is to overcome the defects in the prior art and provide a network resource allocation method, device, equipment and medium based on load balancing to achieve reasonable allocation of network resources, meet the communication needs of different applications, and improve the utilization rate of network resources.

[0006] In a first aspect, an embodiment of the present invention provides a network resource allocation method based on load balancing, comprising:

[0007] Using a network function virtualization algorithm and a software defined network algorithm, the physical wireless local area network is divided into at least two virtual network slices, and customized configuration is performed on the at least two virtual network slices;

[0008] Determine the load status and average load of at least two virtual network slices, and determine the network resource allocation amount of at least two virtual network slices according to the load status and the average load; the load status includes network traffic and device connection status;

[0009] Configuring corresponding quality of service parameters for the at least two virtual network slices, and allocating processing tasks of different levels according to the quality of service parameters; wherein the higher the quality of service parameter, the higher the task level;

[0010] Based on the network resource allocation amount and the corresponding level of processing tasks, the network resource allocation amount of the at least two virtual network slices is dynamically adjusted.

[0011] In a second aspect, an embodiment of the present invention further provides a network resource allocation device based on load balancing, comprising:

[0012] A network virtualization module, configured to use a network function virtualization algorithm and a software defined network algorithm to divide the physical wireless local area network into at least two virtual network slices, and perform customized configuration on the at least two virtual network slices;

[0013] A load balancing module, used to determine the load status and average load of at least two virtual network slices, and determine the network resource allocation amount of at least two virtual network slices according to the load status and the average load; the load status includes network traffic and device connection status;

[0014] a service quality assurance module, configured to configure corresponding service quality parameters for the at least two virtual network slices, and to allocate processing tasks of different levels according to the service quality parameters; wherein the higher the service quality parameter, the higher the task level;

[0015] An intelligent management module is used to dynamically adjust the network resource allocation amount of the at least two virtual network slices according to the network resource allocation amount and the corresponding level of processing tasks.

[0016] In a third aspect, an embodiment of the present invention further provides an electronic device, the electronic device comprising:

[0017] one or more processors;

[0018] A storage device for storing one or more programs;

[0019] When the one or more programs are executed by the one or more processors, the one or more processors implement the load balancing-based network resource allocation method described in any embodiment of the present invention.

[0020] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the network resource allocation method based on load balancing described in any embodiment of the present invention is implemented.

[0021] In order to achieve the above objectives, the beneficial effects of the present invention are: providing an efficient and reliable communication solution for the intelligent operation and maintenance integrated system of power transmission and transformation equipment, which can not only meet the communication needs of different applications and improve the utilization rate of network resources; but also improve the overall operation level and safety of the power system through intelligent management and optimization, which is of great significance to promoting the development of smart grids. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Other features, objects and advantages of the present invention will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings. The drawings are only for the purpose of illustrating preferred embodiments and are not to be considered as limiting the present invention. Also, the same reference symbols are used throughout the drawings to represent the same parts. In the drawings:

[0023] Figure 1 is a flow chart of a network resource allocation method based on load balancing provided in Embodiment 1 of the present invention;

[0024] Figure 2 is a flow chart of a network resource allocation method based on load balancing provided in Embodiment 2 of the present invention;

[0025] Figure 3 This is a schematic diagram of a network virtualization structure provided by Embodiment 2 of the present invention;

[0026] Figure 4 This is a schematic diagram of a virtual network slice load balancing structure provided by Embodiment 2 of the present invention;

[0027] Figure 5 This is a schematic diagram of a service quality assurance structure provided by Embodiment 2 of the present invention;

[0028] Figure 6 This is a schematic diagram of an intelligent system management structure provided by Embodiment 2 of the present invention;

[0029] Figure 7 It is a structural diagram of a network resource allocation device based on load balancing provided in Embodiment 3 of the present invention;

[0030] Figure 8 It is a structural schematic diagram of an electronic device provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0031] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0032] Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow charts describe the operations (or steps) as sequential processes, many of the operations (or steps) therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of the operations can be rearranged. The process can be terminated when its operation is completed, but can also have additional steps not included in the accompanying drawings. The process can correspond to a method, function, procedure, subroutine, subprogram, etc.

[0033] Among them, the acquisition, storage, use and processing of data in the technical solution of this application are in compliance with the relevant provisions of national laws and regulations. It should be noted that in the embodiments of this application, some existing solutions in the industry such as certain software, components or models may be mentioned, which should be considered as exemplary, and their purpose is only to illustrate the feasibility of the implementation of the technical solution of this application, but it does not mean that the applicant has or will necessarily use the solution.

[0034] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein.

[0035] Embodiment 1

[0036] Figure 1 This is a flow chart of a method for allocating network resources based on load balancing provided by Embodiment 1 of the present invention. This embodiment is applicable to the case of allocating network resources based on load balancing. The method of this embodiment can be executed by a network resource allocation device based on load balancing, and the device can be implemented in hardware and / or software. The device can be configured in a server for allocating network resources based on load balancing. The method specifically includes the following steps:

[0037] S110. Use a network function virtualization algorithm and a software-defined network algorithm to divide the physical wireless local area network into at least two virtual network slices, and customize the at least two virtual network slices.

[0038] Network Function Virtualization (NFV) refers to a concept of network architecture that uses virtualization technology to divide the functions of the network node layer into several functional blocks, which are implemented in software.

[0039] Software Defined Network (SDN) technology may refer to a network management method that supports dynamic, programmatic and efficient network configuration, aiming to improve network performance and monitoring capabilities, making it more like cloud computing rather than traditional network management.

[0040] In an embodiment of the present invention, network function virtualization is used to divide the network function of a physical wireless local area network into at least two virtual network functions, and at least two virtual network slices are constructed; software-defined network technology is used to customize the at least two virtual network slices to provide differentiated services.

[0041] S120. Determine the load status and average load of at least two virtual network slices, and determine the network resource allocation amount of the at least two virtual network slices based on the load status and the average load.

[0042] The load status includes network traffic and device connection status; the network traffic may refer to data traffic transmitted on the network; the device connection status may refer to data and operation status of the device connection. In the embodiment of the present invention, the current load of the at least two virtual network slices is determined based on the load status.

[0043] The average load may refer to the average of the current loads of the at least two virtual network slices. In an embodiment of the present invention, the network resource allocation amount of the at least two virtual network slices is adjusted according to the difference between the current load of the at least two virtual network slices and the average load. For example, if the current load of the first virtual network slice is greater than the average load, the difference between the current load and the average load is determined, and the network resource allocation amount of the first virtual network slice is dynamically adjusted according to the difference; such as increasing the corresponding network resource allocation amount. Optionally, if the current load of the first virtual network slice is less than the average load, the corresponding network resource allocation amount is reduced.

[0044] S130. Configure corresponding quality of service parameters for the at least two virtual network slices, and allocate processing tasks of different levels according to the quality of service parameters.

[0045] Among them, by setting different service quality parameters for the at least two virtual network slices, the priority communication rights of key tasks are ensured to meet the needs of various application scenarios. The service quality parameters include but are not limited to bandwidth management, delay control, reliability assurance and priority scheduling. The bandwidth management is used to ensure the bandwidth requirements of each application; the delay control is used to set the corresponding low-latency path for the processing task to ensure the real-time communication; the reliability assurance provides redundant paths and fast recovery mechanisms for the processing tasks to ensure the stability and continuity of communication; the priority scheduling assigns different priorities to different virtual network slices to ensure the priority communication rights of key tasks.

[0046] The higher the quality of service parameter of the virtual network slice, the higher the level of processing tasks assigned to the virtual network slice. For example, if the second virtual network slice can provide a lower latency path, a fast recovery mechanism, and a higher priority, then the processing tasks with a higher task level can be assigned to the second virtual network slice to determine the real-time and reliability of the processing tasks.

[0047] S140. Dynamically adjust the network resource allocation amounts of the at least two virtual network slices according to the network resource allocation amounts and the processing tasks of the corresponding levels.

[0048] The determination of the network resource allocation amount is based on the network traffic and device connection status of the virtual network slice. Based on the network traffic and device connection status, the level task allocated to the virtual network slice is determined to adjust the network resource allocation amount of the virtual network slice. For example, the first network resource allocation amount determined based on the network traffic and device connection status of the virtual network slice is A. If the level task allocated to the virtual network slice is higher, A can be appropriately adjusted to increase to the second network resource allocation amount B.

[0049] The embodiment of the present invention provides a network resource allocation method based on load balancing. By adopting a network function virtualization algorithm and a software defined network algorithm, a physical wireless local area network is divided into at least two virtual network slices and the at least two virtual network slices are customized; the load status and average load of the at least two virtual network slices are determined, and the network resource allocation amount of the at least two virtual network slices is determined according to the load status and the average load; the load status includes network traffic and device connection status; corresponding service quality parameters are configured for the at least two virtual network slices, and different levels of processing tasks are allocated according to the service quality parameters; wherein, the higher the service quality parameter, the higher the task level; according to the network resource allocation amount and the corresponding level of processing tasks, the network resource allocation amount of the at least two virtual network slices is dynamically adjusted. The technical solution of the embodiment of the present invention is adopted to provide an efficient and reliable communication solution for the intelligent operation and maintenance integrated system of power transmission and transformation equipment, which can not only meet the communication needs of different applications and improve the utilization rate of network resources; but also improve the overall operation level and safety of the power system through intelligent management and optimization, which is of great significance to promoting the development of smart grids.

[0050] Embodiment 2

[0051] Figure 2 The flowchart of a network resource allocation method based on load balancing provided in the second embodiment of the present invention. The embodiment of the present invention further optimizes the above embodiment on the basis of the above embodiment, and the embodiment of the present invention can be combined with various optional solutions in one or more of the above embodiments. Figure 2 As shown, the network resource allocation method based on load balancing provided in an embodiment of the present invention may include the following steps:

[0052] S210. Use a network function virtualization algorithm and a software-defined network algorithm to divide the physical wireless local area network into at least two virtual network slices, and customize the at least two virtual network slices.

[0053] Among them, the embodiment of the present invention divides the physical wireless local area network into multiple independent virtual network slices by utilizing network function virtualization (NFV) and software defined network (SDN) technologies. Each virtual network slice is customized according to specific application requirements to provide differentiated services.

[0054] As an optional but non-limiting implementation, the network function virtualization algorithm and the software defined network algorithm are used to divide the physical wireless local area network into at least two virtual network slices, and the at least two virtual network slices are customized and configured, including but not limited to steps A1-A3:

[0055] Step A1: Use network function virtualization to divide the network function module of the physical wireless local area network into at least two virtual network functions, and use a network function virtualization orchestrator to uniformly manage and schedule the at least two virtual network functions.

[0056] Step A2: Based on the at least two virtual network functions, the physical wireless local area network is divided into at least two virtual network slices.

[0057] Step A3: Use software-defined network technology to obtain network traffic status, user needs and application characteristics, and dynamically adjust the network resources and traffic configured by the at least two virtual network slices.

[0058] Among them, see Figure 3 , through NFV technology, the network functions of the physical wireless local area network are modularized into at least two virtual network functions, which run on standard servers, realizing flexible deployment and management of network services. The network function virtualization orchestrator is responsible for the unified management and scheduling of virtual network functions, including life cycle management, resource allocation and performance monitoring, and dynamically adjusts the deployment and configuration of virtual network functions according to real-time network conditions and application requirements to ensure the efficient operation of network services.

[0059] In terms of SDN technology, the network control plane is separated from the data plane. The SDN controller, as the "brain" of the network, has a global network view and intelligent decision-making capabilities. The SDN controller communicates with the data plane device through the southbound interface to issue traffic scheduling strategies and configuration instructions; it interacts with applications and services through the northbound interface, receives application requirements and policy instructions, and feeds back network status and performance data. The SDN controller dynamically adjusts network resource allocation and traffic scheduling strategies based on network traffic conditions, user needs, and application characteristics to ensure efficient operation of the network.

[0060] During the creation and configuration of virtual network slices, physical network resources (such as computing, storage, and bandwidth) are first virtualized into multiple logical resource pools. The corresponding resources are allocated from the logical resource pools according to the requirements of the virtual network slices, and the corresponding virtual network function instances are created. The network topology and traffic scheduling strategy within the slice are configured through the SDN controller to ensure the communication path and service quality within the slice. Each virtual network slice is configured with different parameters according to specific needs, including but not limited to bandwidth, latency, reliability, and security. The SDN controller and network function virtualization orchestrator are used to achieve unified management and dynamic adjustment of virtual network slice configuration parameters to ensure that the service quality and performance within the virtual network slice meet the requirements.

[0061] Optionally, an embodiment of the present invention constructs a virtualization management platform, which provides unified virtualization management and scheduling functions, has real-time monitoring, fault detection and resource scheduling functions, and can dynamically adjust virtual network slice configuration and resource allocation according to network conditions and application requirements. By real-time monitoring of the performance data of each virtual network slice, potential performance bottlenecks and faults can be discovered and resolved in a timely manner, and network operation data can be deeply analyzed and optimized using data analysis and machine learning techniques to improve network resource utilization efficiency and service quality. In addition, the isolation between different virtual network slices is ensured to prevent data leakage and unauthorized access, and sensitive data and communication security within the virtual network slices are protected through strict access control and security policies.

[0062] The embodiments of the present invention can effectively improve the communication efficiency and reliability of the intelligent operation and maintenance integrated system of power transmission and transformation equipment through network function virtualization and software-defined network technology, and meet the needs of intelligent development of the power system.

[0063] S220. Determine the load status and average load of at least two virtual network slices, and determine the network resource allocation amount of at least two virtual network slices based on the load status and the average load.

[0064] The embodiment of the present invention realizes dynamic adjustment and optimal allocation of resources of each virtual network slice by designing an efficient load balancing algorithm. Figure 4 The core of load balancing is to dynamically adjust the network resource allocation of each virtual network slice according to real-time network traffic, user needs and application characteristics to ensure efficient use and stable operation of network resources. Load balancing evenly distributes the task pressure to each network (or operation unit) in the cluster to avoid excessive pressure on some networks in the cluster and too much idleness on some networks. After load balancing, each virtual network slice obtains the processing capacity load that suits it.

[0065] As an optional but non-limiting implementation manner, the determining the load status and average load of at least two virtual network slices, and determining the network resource allocation amount of at least two virtual network slices according to the load status and the average load, includes but is not limited to steps B1-B4:

[0066] Step B1: Monitor the network traffic and device connection status of the at least two virtual network slices in real time, and determine the current load of the at least two virtual network slices based on the network traffic and device connection status.

[0067] Step B2: Determine the average load based on the current loads of the at least two virtual network slices.

[0068] Step B3: Determine the resource adjustment amount of at least two virtual network slices based on the current load and average load of the at least two virtual network slices.

[0069] Step B4: Dynamically adjust the network resources of the virtual network slice according to the resource adjustment amount, and determine the network resource allocation amount of the at least two virtual network slices.

[0070] The load balancing algorithm calculates the current load status of each virtual network slice by monitoring the network traffic and device connection status of each virtual network slice in real time. Assume that there are N slices, represented as S1, S2, …, S N , the current load of each virtual network slice is represented as L i (t), where i is the virtual network slice number and t is time. The total network resources are represented by R total , the resource allocation of each virtual network slice is expressed as R i (t).

[0071] The goal of load balancing is to balance the load of each virtual network slice, that is, to make the load of each virtual network slice close to the average load. avg (t) is expressed as:

[0072]

[0073] The resource allocation strategy dynamically adjusts the network resource allocation according to the load of each virtual network slice. Assume that at time t, slice S i The current load L i (t) exceeds the average load L avg (t), the network resource allocation of the virtual network slice needs to be increased, otherwise it needs to be reduced. The virtual network resource adjustment amount is expressed as ΔR i (t), which is calculated as follows:

[0074] ΔR i (t) = k·(L i (t)-L avg (t))

[0075] Where k is the adjustment coefficient, which is set according to actual needs. The adjusted network resource allocation is expressed as:

[0076] R i (t+1)=R i (t)+ΔR i (t)

[0077] Among them, R i (t) represents the network resource allocation before adjustment, R i(t+1) represents the adjusted network resource allocation amount.

[0078] In order to ensure that the total amount of network resource allocation of the at least two virtual network slices does not exceed the total amount of network resources, normalization processing is required. The normalized network resource allocation amount is expressed as:

[0079]

[0080] Among them, R total Indicates the total amount of network resources.

[0081] S230. Construct constraints and an objective function to optimize the network resource allocation amount of the at least two virtual network slices.

[0082] In order to achieve the optimal load balancing effect, a mathematical model can be used for optimization. The mathematical model includes but is not limited to linear programming and convex optimization. The optimization goal is to minimize the load difference between the at least two virtual network slices; the objective function is expressed as:

[0083]

[0084] The constraints are expressed as:

[0085]

[0086] Among them, L i (t) represents the current load of the i-th virtual network slice, L avg (t) represents the average load, R i (t) represents the network resource allocation of the ith virtual network slice, R total Indicates the total amount of network resources.

[0087] Optionally, in actual applications, the load balancing system can dynamically monitor and schedule each virtual network slice through an intelligent management platform. Using artificial intelligence and machine learning technology, the historical network traffic and device connection status of each virtual network slice can be analyzed and predicted to further optimize the resource allocation strategy of the virtual network slice and improve the efficiency and accuracy of load balancing.

[0088] The embodiment of the present invention can effectively improve the resource utilization of each virtual network slice through the load balancing technology, ensure the efficient and stable operation of the network, and meet the communication requirements of the integrated intelligent operation and maintenance system of power transmission and transformation equipment.

[0089] S240. Configure corresponding quality of service parameters for the at least two virtual network slices, and allocate processing tasks of different levels according to the quality of service parameters.

[0090] Among them, Quality of Service (QoS) is one of the key technologies in the present invention. By setting different QoS parameters for different virtual network slices, the priority communication rights of processing tasks are ensured to meet the needs of various application scenarios. Figure 5 ,QoS technology mainly involves bandwidth management, delay control, reliability guarantee and priority ,scheduling.

[0091] The quality of service parameters of the at least two virtual network slice configurations include bandwidth resources, target delay paths, redundant paths, fault recovery strategies, and priority scheduling.

[0092] In an optional solution of the embodiment of the present invention, bandwidth management ensures the bandwidth requirements of each application by allocating specific bandwidth resources to each virtual network slice. Assume that the total bandwidth is B total , slice S i The bandwidth allocation is B i , the following conditions are met:

[0093]

[0094] The bandwidth allocation optimization problem can be expressed as a linear programming problem:

[0095]

[0096] Among them, w i For slice S i The weight of reflects its relative importance. The constraints can be characterized as:

[0097]

[0098]

[0099] in, Indicates the minimum bandwidth, The bandwidth of the virtual network slice is constrained by the minimum bandwidth and the maximum bandwidth. The embodiment of the present invention optimizes the bandwidth allocation problem to determine the optimal bandwidth allocation for each virtual network slice.

[0100] In an optional solution of the embodiment of the present invention, delay control may refer to setting a target delay path for a processing task to ensure the real-time communication. i The delay target is D i , the delay control strategy includes path selection and queue management. The delay can be expressed as the sum of the transmission delay and the queuing delay on the path:

[0101]

[0102] Among them, the transmission delay Depending on the path length and link bandwidth, the queuing delay Depends on the queue length and processing rate. Assume there are M links on the path and the bandwidth of each link is B j , the transmission delay is d j , the total transmission delay is:

[0103]

[0104] Among them, L i The size of the data packet.

[0105] Optionally, in order to achieve delay control, mechanisms such as priority queuing and weighted fair queuing (WFQ) can be used. Priority queuing puts high-priority packets at the front of the queue to ensure that they are processed first; WFQ allocates bandwidth according to weights to ensure fairness and priority of each virtual network slice.

[0106] In an optional solution of the embodiment of the present invention, reliability assurance ensures the stability and continuity of communication by providing redundant paths and fault recovery strategies for processing tasks. i The reliability target is R i , which can be achieved through multi-path transmission and fault recovery strategies.

[0107] The multipath transmission strategy improves the reliability of communication by using multiple paths for data transmission at the same time. Assume that there are paths, and the reliability of each path is r k , then the total reliability R i It can be expressed as:

[0108]

[0109] The fault recovery strategy achieves fast fault recovery by monitoring link status and quickly switching paths. Fault recovery time T recovery It can be expressed as the detection time T detect and switching time T switch sum:

[0110] T recovery =T detect +T switch

[0111] In order to minimize the fault recovery time, fast detection algorithms and fast switching mechanisms can be used to improve network reliability.

[0112] In an optional solution of the embodiment of the present invention, priority scheduling ensures the priority communication right of processing tasks by assigning different priorities to different virtual network slices. i The priority is P i ,The priority scheduling strategy includes priority-based bandwidth allocation and queue management.

[0113] The goal of priority scheduling is to minimize the delay and packet loss rate of high priority tasks. The priority bandwidth allocation can be calculated by the following formula:

[0114]

[0115] Priority queue management ensures that high-priority processing tasks are processed first by allocating dedicated queues to them. Priority scheduling can be achieved using mechanisms such as priority queues and weighted fair queues.

[0116] S250. Dynamically adjust the network resource allocation amount of the at least two virtual network slices based on the network resource allocation amount and the corresponding level of processing tasks.

[0117] Among them, intelligent management is an important part of the present invention for optimizing and improving the efficiency of network resource utilization. By introducing artificial intelligence (AI) and machine learning (ML) technology, automatic management and intelligent scheduling of network resources are realized. Intelligent management mainly includes real-time monitoring, data analysis and prediction, and resource scheduling optimization.

[0118] As an optional but non-limiting implementation, the network resource allocation amount of the virtual network slice is dynamically adjusted according to the network resource allocation amount and the corresponding level of processing tasks, including but not limited to steps C1-C3:

[0119] Step C1: Obtain the current network status and historical network status of the virtual network slice; the network status includes the network traffic, number of device connections, and service quality parameters of the virtual network slice.

[0120] Step C2: predicting the network status of the virtual network slice at the next moment based on the current network status and the historical network status.

[0121] Step C3: Dynamically adjust the network resource allocation of the virtual network slice based on the predicted network status.

[0122] The intelligent management system obtains comprehensive data on network operation by monitoring the network traffic, device connection status, and service quality parameters of each virtual network slice in real time. i The network traffic is F i (t), the number of connected devices is Ui (t), the service quality parameter is Q i (t), then the main data monitored by the system is X i (t) include:

[0123] X i (t)=[F i (t),U i (t),Q i (t)]

[0124] The real-time monitoring data is stored in the database for subsequent data analysis and optimization.

[0125] Optionally, data analysis processes historical monitoring data to extract useful features and patterns. Assume that the historical data set is D = {X i (t1),X i (t2),…,X i (t T )}, use machine learning algorithms to train data and predict future network status. Common machine learning algorithms include but are not limited to linear regression, support vector machine (SVM), random forest and neural network. Assume that linear regression is used to predict future traffic The linear regression model is expressed as:

[0126]

[0127] Wherein, w is the regression coefficient and b is the bias term. The linear regression model is trained by minimizing the mean square error (MSE), which can be expressed as:

[0128]

[0129] The optimization goal is The optimization problem is solved by the gradient descent method to obtain the optimal regression coefficient w and bias term b.

[0130] Optionally, resource scheduling optimization dynamically adjusts resource allocation strategies by analyzing the predicted network status. Assume that the total resource volume is R total , the network resource allocation of each virtual network slice is R i (t), the optimization goal is to maximize network performance and minimize delay and packet loss rate. The optimization problem can be expressed as:

[0131]

[0132] Among them, αi and β i is the weight coefficient, QoS i (t) is the service quality indicator, D i (t) is the delay. The constraints are:

[0133]

[0134] Use the Lagrange multiplier method to solve the optimization problem, introduce the Lagrange multiplier λ, and construct the Lagrange function Through Find the partial derivative and set it equal to zero to get the optimal resource allocation strategy. Finally, combined with the constraints, the optimal R i (t).

[0135]

[0136] Optionally, the intelligent scheduling algorithm ensures the service quality and network performance of each virtual network slice by dynamically adjusting network resources. Assuming that a reinforcement learning (RL) algorithm such as deep Q learning (DQN) is adopted, its main steps include state representation, action space and reward function.

[0137] The state representation may refer to the current network state s(t), including network traffic, number of connected devices, and service quality parameters. The action space may refer to the resource allocation strategy a(t), i.e., the amount of network resource allocation for each virtual network slice. The reward function may refer to the reward function r(t) designed based on service quality and network performance.

[0138] The state transfer equation can be expressed as:

[0139] s(t+1)=f(s(t),a(t))

[0140] The goal is to maximize the cumulative reward, which can be expressed as:

[0141]

[0142] Among them, γ represents the discount factor, which is an empirical value.

[0143] Approximate the Q-value function through a deep neural network (DNN):

[0144] Q(s(t),a(t);θ)

[0145] Update the Q value using the Bellman equation:

[0146]

[0147] Where a' represents all possible values ​​under the new state s(t+1). The optimal scheduling strategy is obtained through experience replay and stable training of the target network.

[0148] As an optional but non-limiting implementation, the dynamically adjusting the network resource allocation amount of the virtual network slice also includes but is not limited to steps D1-D3:

[0149] Step D1: Determine the network traffic change, the change in the number of connected devices, and the service quality parameters of the target virtual network slice within a preset time interval.

[0150] Step D2: Determine the load change of the target virtual network slice based on the network traffic change, the change in the number of connected devices and the service quality parameters.

[0151] Step D3: Dynamically adjust the network resource allocation of the target virtual network slice according to the load change.

[0152] Among them, the current load L is calculated by real-time monitoring of the network traffic and device connection status of each virtual network slice i (t), and determine the adjusted resource allocation of the virtual network slice. The monitoring data includes the traffic F of each slice i (t), the number of connected devices U i (t) and service quality parameter Q i (t).

[0153] Assume that within the preset time interval Δt, according to the virtual network slice S i The flow rate increase is ΔF i (t), the growth of the number of connected devices is ΔU i (t) and the service quality parameter, determine the load change of the virtual network slice, and the load change is expressed as:

[0154] ΔL i (t) = α·ΔF i (t)+β·ΔU i (t)+γ·Q i (t)

[0155] Wherein α, β and γ are weight coefficients, which are set according to specific application requirements. The network resource allocation amount of the virtual network slice is dynamically adjusted according to the load change amount.

[0156] See also Figure 6,The schematic diagram of the intelligent management system shows a closed-loop control system, which includes monitoring module, data acquisition, data analysis and prediction, resource scheduling optimization, intelligent scheduling algorithm and real-time network adjustment. The monitoring module is responsible for real-time monitoring of network traffic, device connection status and service quality parameters of each slice; the data acquisition module obtains data from the monitoring module and stores it for subsequent analysis; the data analysis and prediction module uses machine learning algorithms to process and train historical data to predict future network status; the resource scheduling optimization module dynamically adjusts resource allocation strategies according to the prediction results to maximize network performance and minimize latency and packet loss rate; the intelligent scheduling algorithm realizes dynamic adjustment of network resources through reinforcement learning to ensure the service quality and network performance of each slice; the real-time network adjustment module adjusts network resource allocation in real time according to the output of the intelligent scheduling algorithm to optimize network operation. The entire system provides feedback through the network status monitoring module to ensure the system's adaptive and efficient operation.

[0157] The embodiment of the present invention provides a network resource allocation method based on load balancing. The physical network is virtualized into multiple independent virtual network slices through network slicing technology. Each virtual network slice can be customized according to the needs of specific applications, thereby providing differentiated services. Combining software-defined networking (SDN) and network function virtualization (NFV) technology, virtual network slices can flexibly and dynamically allocate network resources, significantly improving network utilization and service quality. In the intelligent operation and maintenance integrated system of power transmission and transformation equipment, wireless local area network slicing technology based on load balancing is particularly important. The load balancing strategy dynamically adjusts the resource allocation of each virtual network slice by real-time monitoring of network traffic and device connection status, ensuring that each virtual network slice can operate efficiently and stably. At the same time, different operation and maintenance tasks can obtain corresponding network resource support according to priority and demand, avoiding waste and bottlenecks of network resources. The technical solution of the embodiment of the present invention can realize automatic operation and maintenance and efficient management of the network through intelligent management and optimization, meeting the growing equipment access needs and diversified business scenarios.

[0158] Embodiment 3

[0159] Figure 7 This is a schematic diagram of the structure of a network resource allocation device based on load balancing provided by the third embodiment of the present invention. The technical solution of this embodiment can be applied to the situation of network resource allocation based on load balancing. The device can be implemented by software and / or hardware and is generally integrated on any electronic device with network communication function, including but not limited to: servers, computers, personal digital assistants and other devices. Figure 7As shown, the network resource allocation device based on load balancing provided in this embodiment may include: a network virtualization module 710, a load balancing module 720, a service quality assurance module 730 and an intelligent management module 740; wherein,

[0160] The network virtualization module 710 is used to adopt a network function virtualization algorithm and a software defined network algorithm to divide the physical wireless local area network into at least two virtual network slices, and customize the at least two virtual network slices;

[0161] A load balancing module 720 is used to determine the load status and average load of at least two virtual network slices, and determine the network resource allocation amount of at least two virtual network slices according to the load status and the average load; the load status includes network traffic and device connection status;

[0162] A service quality assurance module 730 is used to configure corresponding service quality parameters for the at least two virtual network slices, and allocate processing tasks of different levels according to the service quality parameters; wherein the higher the service quality parameter, the higher the task level;

[0163] The intelligent management module 740 is used to dynamically adjust the network resource allocation amount of the at least two virtual network slices according to the network resource allocation amount and the corresponding level of processing tasks.

[0164] Based on the above embodiment, optionally, the network virtualization module is specifically used to:

[0165] Using network function virtualization to divide the network function module of the physical wireless local area network into at least two virtual network functions, and using a network function virtualization orchestrator to uniformly manage and schedule the at least two virtual network functions;

[0166] Dividing the physical wireless local area network into at least two virtual network slices according to the at least two virtual network functions;

[0167] Software-defined network technology is used to obtain network traffic status, user needs and application characteristics, and dynamically adjust the network resources and traffic configured by the at least two virtual network slices.

[0168] Based on the above embodiment, optionally, the load balancing module is specifically used to:

[0169] monitoring network traffic and device connection status of the at least two virtual network slices in real time, and determining current loads of the at least two virtual network slices according to the network traffic and device connection status;

[0170] Determining an average load according to current loads of the at least two virtual network slices;

[0171] Determining resource adjustment amounts of at least two virtual network slices according to the current loads and the average loads of the at least two virtual network slices;

[0172] The network resources of the virtual network slice are dynamically adjusted according to the resource adjustment amount, and the network resource allocation amount of the at least two virtual network slices is determined.

[0173] Based on the above embodiment, optionally, the load balancing module is further specifically used for:

[0174] Constructing constraint conditions and objective functions to optimize the network resource allocation amounts of the at least two virtual network slices; wherein the optimization goal is to minimize the load difference between the at least two virtual network slices;

[0175] The objective function is expressed as:

[0176]

[0177] The constraints are expressed as:

[0178]

[0179] Among them, L i (t) represents the current load of the i-th virtual network slice, L avg (t) represents the average load, R i (t) represents the network resource allocation of the ith virtual network slice, R total Indicates the total amount of network resources.

[0180] Based on the above embodiment, optionally, the quality of service parameters configured for the at least two virtual network slices include bandwidth resources, target delay paths, redundant paths, fault recovery strategies, and priority scheduling.

[0181] Based on the above embodiment, optionally, the intelligent management module is specifically used to:

[0182] Obtain the current network status and historical network status of the virtual network slice; the network status includes the network traffic, number of device connections, and quality of service parameters of the virtual network slice;

[0183] Predicting the network state of the virtual network slice at the next moment based on the current network state and the historical network state;

[0184] Dynamically adjust the network resource allocation of the virtual network slice based on the predicted network status.

[0185] Based on the above embodiment, optionally, the intelligent management module is further specifically used for:

[0186] Determine the network traffic change amount, the change amount of the number of connected devices and the service quality parameters of the target virtual network slice within a preset time interval;

[0187] Determining a load change of a target virtual network slice according to the network traffic change, the change in the number of connected devices, and the quality of service parameter;

[0188] The network resource allocation amount of the target virtual network slice is dynamically adjusted according to the load change.

[0189] The load balancing-based network resource allocation device provided in the embodiment of the present invention can execute the load balancing-based network resource allocation method provided in any of the above-mentioned embodiments of the present invention, and has the corresponding functions and beneficial effects of executing the load balancing-based network resource allocation method. For detailed processes, please refer to the relevant operations of the load balancing-based network resource allocation method in the above-mentioned embodiments.

[0190] Embodiment 4

[0191] Figure 8 1 is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0192] like Figure 8 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0193] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0194] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The processor 11 executes the various methods and processes described above, such as a network resource allocation method based on load balancing.

[0195] In some embodiments, the network resource allocation method based on load balancing can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the network resource allocation method based on load balancing described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to execute the network resource allocation method based on load balancing in any other appropriate manner (for example, by means of firmware).

[0196] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0197] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0198] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0199] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0200] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0201] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0202] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0203] The above embodiments are merely examples for the purpose of clear explanation, and are not intended to limit the implementation methods. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the implementation methods here. The obvious changes or modifications derived therefrom are still within the scope of protection of the invention.

Claims

1. A network resource allocation method based on load balancing, characterized in that: The method comprises: Using a network function virtualization algorithm and a software defined network algorithm, the physical wireless local area network is divided into at least two virtual network slices, and customized configuration is performed on the at least two virtual network slices; Determine the load status and average load of at least two virtual network slices, and determine the network resource allocation amount of at least two virtual network slices according to the load status and the average load; the load status includes network traffic and device connection status; Configuring corresponding quality of service parameters for the at least two virtual network slices, and allocating processing tasks of different levels according to the quality of service parameters; wherein the higher the quality of service parameter, the higher the task level; Based on the network resource allocation amount and the corresponding level of processing tasks, the network resource allocation amount of the at least two virtual network slices is dynamically adjusted.

2. The method according to claim 1, characterized in that: The adopting of a network function virtualization algorithm and a software defined network algorithm to divide a physical wireless local area network into at least two virtual network slices, and performing customized configuration on the at least two virtual network slices includes: Using network function virtualization to divide the network function module of the physical wireless local area network into at least two virtual network functions, and using a network function virtualization orchestrator to uniformly manage and schedule the at least two virtual network functions; Dividing the physical wireless local area network into at least two virtual network slices according to the at least two virtual network functions; Software-defined network technology is used to obtain network traffic status, user needs and application characteristics, and dynamically adjust the network resources and traffic configured by the at least two virtual network slices.

3. The method according to claim 1, characterized in that The determining of the load status and the average load of at least two virtual network slices, and determining the network resource allocation amount of at least two virtual network slices according to the load status and the average load, includes: Monitoring network traffic and device connection status of the at least two virtual network slices in real time, and determining current loads of the at least two virtual network slices according to the network traffic and device connection status; Determining an average load according to current loads of the at least two virtual network slices; Determining resource adjustment amounts of at least two virtual network slices according to the current loads and the average loads of the at least two virtual network slices; The network resources of the virtual network slice are dynamically adjusted according to the resource adjustment amount, and the network resource allocation amount of the at least two virtual network slices is determined.

4. The method according to claim 1, characterized in that: After determining the network resource allocation amounts of at least two virtual network slices, the method further includes: Constructing constraint conditions and objective functions to optimize the network resource allocation amounts of the at least two virtual network slices; wherein the optimization goal is to minimize the load difference between the at least two virtual network slices; The objective function is expressed as: The constraints are expressed as: Among them, L i t represents the current load of the ith virtual network slice, L avg t represents the average load, R i t represents the network resource allocation of the ith virtual network slice, R total Indicates the total amount of network resources.

5. The method according to claim 1, characterized in that The quality of service parameters of the at least two virtual network slice configurations include bandwidth resources, target delay paths, redundant paths, fault recovery strategies, and priority scheduling.

6. The method according to claim 1, characterized in that The dynamically adjusting the network resource allocation amount of the virtual network slice according to the network resource allocation amount and the processing task of the corresponding level includes: Obtain the current network status and historical network status of the virtual network slice; the network status includes the network traffic, number of device connections, and quality of service parameters of the virtual network slice; Predicting the network state of the virtual network slice at the next moment based on the current network state and the historical network state; Dynamically adjust the network resource allocation of the virtual network slice based on the predicted network status.

7. The method according to claim 1, characterized in that The dynamically adjusting the network resource allocation amount of the virtual network slice also includes: Determine the network traffic change amount, the change amount of the number of connected devices and the service quality parameters of the target virtual network slice within a preset time interval; Determining a load change of a target virtual network slice according to the network traffic change, the change in the number of connected devices, and the quality of service parameter; The network resource allocation amount of the target virtual network slice is dynamically adjusted according to the load change.

8. A network resource allocation device based on load balancing, characterized in that: The device comprises: A network virtualization module, configured to use a network function virtualization algorithm and a software defined network algorithm to divide the physical wireless local area network into at least two virtual network slices, and perform customized configuration on the at least two virtual network slices; A load balancing module, used to determine the load status and average load of at least two virtual network slices, and determine the network resource allocation amount of at least two virtual network slices according to the load status and the average load; the load status includes network traffic and device connection status; a service quality assurance module, configured to configure corresponding service quality parameters for the at least two virtual network slices, and to allocate processing tasks of different levels according to the service quality parameters; wherein the higher the service quality parameter, the higher the task level; An intelligent management module is used to dynamically adjust the network resource allocation amount of the at least two virtual network slices according to the network resource allocation amount and the corresponding level of processing tasks.

9. The device according to claim 8, characterized in that The network virtualization module is specifically used for: Using network function virtualization to divide the network function module of the physical wireless local area network into at least two virtual network functions, and using a network function virtualization orchestrator to uniformly manage and schedule the at least two virtual network functions; Dividing the physical wireless local area network into at least two virtual network slices according to the at least two virtual network functions; Software-defined network technology is used to obtain network traffic status, user needs and application characteristics, and dynamically adjust the network resources and traffic configured by the at least two virtual network slices.

10. The device according to claim 8, characterized in that The load balancing module is specifically used for: Monitoring network traffic and device connection status of the at least two virtual network slices in real time, and determining current loads of the at least two virtual network slices according to the network traffic and device connection status; Determining an average load according to current loads of the at least two virtual network slices; Determining resource adjustment amounts of at least two virtual network slices according to the current loads and the average loads of the at least two virtual network slices; The network resources of the virtual network slice are dynamically adjusted according to the resource adjustment amount, and the network resource allocation amount of the at least two virtual network slices is determined.

11. The device according to claim 8, characterized in that The load balancing module is further specifically used for: Constructing constraint conditions and objective functions to optimize the network resource allocation amounts of the at least two virtual network slices; wherein the optimization goal is to minimize the load difference between the at least two virtual network slices; The objective function is expressed as: The constraints are expressed as: Among them, L i t represents the current load of the ith virtual network slice, L avg t represents the average load, R i t represents the network resource allocation of the ith virtual network slice, R total Indicates the total amount of network resources.

12. The device according to claim 8, characterized in that The quality of service parameters of the at least two virtual network slice configurations include bandwidth resources, target delay paths, redundant paths, fault recovery strategies, and priority scheduling.

13. The device according to claim 8, characterized in that The intelligent management module is specifically used for: Obtain the current network status and historical network status of the virtual network slice; the network status includes the network traffic, number of device connections, and quality of service parameters of the virtual network slice; Predicting the network state of the virtual network slice at the next moment based on the current network state and the historical network state; Dynamically adjust the network resource allocation of the virtual network slice based on the predicted network status.

14. The device according to claim 8, characterized in that The intelligent management module is also specifically used for: Determine the network traffic change amount, the change amount of the number of connected devices and the service quality parameters of the target virtual network slice within a preset time interval; Determining a load change of a target virtual network slice according to the network traffic change, the change in the number of connected devices, and the quality of service parameter; The network resource allocation amount of the target virtual network slice is dynamically adjusted according to the load change.

15. An electronic device, characterized in that: include: at least one processor; a storage device for storing at least one computer executable instruction; When the at least one program is executed by the at least one processor, the at least one processor implements the network resource allocation method based on load balancing as described in any one of claims 1-7.

16. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions are used to execute the network resource allocation method based on load balancing as described in any one of claims 1 to 7 when executed by a processor.

Images