A method for virtual network resource allocation in a multi-server scenario

Abstract

A virtual network resource allocation method in a multi-server scenario, a network communication system based on a virtual network and a physical network, the resources required by a virtual node include computing power, memory and storage, and the demand of a virtual link is bandwidth; the physical network is composed of physical nodes and physical links, and the core of virtual network resource mapping is to reasonably allocate virtual nodes and links to physical nodes and links; in a multi-server environment, communication between virtual nodes can cross multiple physical servers, so the number and efficiency of cross-host links become the key to affecting system performance; an adaptive mapping algorithm is adopted; by calculating the adaptability between virtual nodes and physical nodes, it is judged whether the physical node can meet the demand of the virtual node; the adaptability is calculated according to the resource demand of the virtual node and the available resources of the physical node, and only the physical node with the adaptability reaching the set threshold is considered as the effective mapping target.

Description

TECHNICAL FIELD

[0001] The present application relates to a network communication technology, in particular a multi-server network virtualization resource allocation method. BACKGROUND

[0002] With the rapid development of network function virtualization and cloud computing technology, broadband operators are facing increasingly complex challenges in network resource management and optimization. The emergence of network function virtualization enables traditional network functions to run on general-purpose hardware platforms through software, thereby improving the flexibility and scalability of the network. However, this also brings new problems, namely how to efficiently allocate virtual network resources in a multi-server environment to achieve optimal resource utilization and network performance improvement.

[0003] In a multi-server scenario, the allocation of virtual network resources becomes a core problem. The communication needs between virtual nodes are frequent, and how to reduce the number of cross-host links and optimize the data transmission path between physical hosts is the key to improving the overall network performance. Especially in large-scale network deployment, unoptimized cross-host links can cause network bottlenecks, increase data transmission delay, and significantly affect user experience.

[0004] Existing virtual network resource allocation methods mainly focus on how to map virtual nodes to physical servers to achieve resource optimization and network performance improvement. However, these methods have the following shortcomings:

[0005] 1. Insufficient optimization of cross-host links: In a multi-server environment, frequent communication between virtual nodes requires passing through different physical hosts. Current methods fail to fully optimize the number of cross-host links, resulting in large data transmission delays and affecting the overall performance of the network.

[0006] 2. Unbalanced resource utilization: Existing resource allocation methods lack effectiveness in load balancing, with some physical servers having excessively high resource loads and others having idle resources, resulting in insufficient utilization of resources. Optimizing resource allocation not only improves the economic efficiency of the system but also reduces unnecessary energy consumption.

[0007] 3. Lack of real-time dynamic adjustment mechanism: Many existing allocation strategies only target initial allocation and fail to dynamically adjust virtual node allocation based on real-time load of physical servers, resulting in decreased system performance and severe resource waste in high-load scenarios.

[0008] In summary, the current virtual network resource allocation method has obvious deficiencies in cross-host link optimization, resource utilization balance and dynamic allocation strategy, and cannot fully meet the needs of broadband operators in a multi-server environment. In order to solve these problems, an urgent need exists for a virtual network resource allocation method that can optimize cross-host links between physical hosts, improve resource utilization, and support real-time dynamic adjustment to adapt to the actual application scenarios of broadband operators in network function virtualization and cloud computing environments. SUMMARY

[0009] The purpose of the present application is to provide a virtual network resource allocation method in a multi-server scenario, covering both initial allocation and real-time dynamic adjustment, aiming to optimize the number of cross-host links between multiple physical hosts, improve the efficiency, real-time performance of resource allocation, and the performance of the overall system. The present application not only effectively optimizes the resource utilization of virtual nodes and cross-host communication through the initial allocation method, but also intelligently adjusts according to the real-time load of physical nodes during system operation through the dynamic allocation module, ensuring that the system remains stable in performance under high load environment.

[0010] The technical solution of the present application: a virtual network resource allocation method in a multi-server scenario, based on a network communication system of virtual network and physical network, the virtual nodes and links in the virtual network are represented by certain resource requirements, the resources required by virtual nodes include computing power, memory and storage, etc., while the demand of virtual links is bandwidth; the physical network is composed of physical nodes and physical links, each physical node has a certain resource capacity including processor, memory and storage, etc., and the physical link provides corresponding bandwidth resources.

[0011] G V represents a virtual network, containing a set of virtual nodes and virtual links, each virtual node n V has a specific resource requirement R V , and the virtual link l V has a bandwidth requirement B V ; the physical network G P contains physical nodes and physical links, the physical node n P has available resources R P , and the physical link l P provides available bandwidth B P ;

[0012] The core of virtual network resource mapping is to reasonably allocate virtual nodes and links to physical nodes and links; during the allocation process, the following conditions must be met:

[0013] · Each virtual node must be mapped to a physical node that can provide sufficient resources, i.e. R P ≥ R VTo meet the computing and storage needs of virtual nodes;

[0014] • Each virtual link must be mapped to a physical link that can provide sufficient bandwidth, i.e., B P ≥B V To ensure the needs of network communication;

[0015] In multi-server environments, communication between virtual nodes may span multiple physical servers, making the number and efficiency of cross-host links critical to system performance. To optimize link configuration, this invention proposes a link optimization strategy to reduce the number of cross-host links, thereby lowering data transmission latency and improving resource utilization efficiency. This strategy analyzes the communication needs between virtual nodes and maps frequently communicating virtual nodes to the same physical nodes whenever possible, avoiding unnecessary cross-host communication. When cross-host links are unavoidable, physical links with higher capacity and lower load are selected for mapping to ensure data transmission stability and efficiency.

[0016] To achieve efficient resource allocation, this invention employs a fit-based mapping algorithm. This algorithm calculates the fit between virtual nodes and physical nodes to determine whether a physical node can meet the needs of the virtual node. The fit is calculated based on the resource requirements of the virtual node and the available resources of the physical node; only physical nodes with a fit reaching a set threshold are considered valid mapping targets. During the mapping process, this method prioritizes physical nodes with high fit and low load to ensure balanced resource utilization. Furthermore, link optimization is considered concurrently during initial allocation. By evaluating the communication needs of virtual nodes, nodes with frequent communication are preferentially mapped to the same physical node, reducing the need for cross-host links.

[0017] The allocation mechanism for virtual network resources consists of the following parts: network resource assessment, network resource quantification, link strategy optimization, initial resource allocation, and dynamic resource allocation.

[0018] (1) The process of determining network resources is achieved through a comprehensive analysis of the resource requirements of virtual nodes and the available resources of physical nodes. First, the system collects resource requirement information of virtual nodes, such as computing power, memory, storage, and bandwidth, forming a virtual node requirement matrix. Simultaneously, the system monitors the resource status of each physical node, including available computing power, memory, storage space, and bandwidth, forming a physical resource matrix. Next, by calculating the resource compatibility between virtual nodes and physical nodes, it determines whether the physical nodes can meet the requirements of the virtual nodes, providing a reliable foundation for subsequent allocation and link optimization.

[0019] (2) The process of network resource quantification involves representing the resource requirements and status of virtual and physical nodes with specific numerical values ​​to achieve precise matching during allocation. First, the resource requirements of virtual nodes (such as CPU, memory, storage, and bandwidth) are quantified into demand vectors, representing the specific resource requirements of each virtual node. Second, the available resources of physical nodes are also quantified into corresponding resource vectors, recording the amount of resources they can currently provide. By establishing a virtual node demand matrix and a physical node available resource matrix, the demand and supply of network resources are clearly quantified. This process provides a numerical basis for subsequent virtual node mapping, helps to accurately calculate fit, and optimizes the allocation of virtual nodes.

[0020] (3) The link strategy optimization process improves data transmission efficiency and reduces latency by reducing the number of links between virtual nodes communicating across physical hosts. First, the system analyzes the communication needs between virtual nodes and identifies frequently communicating virtual node pairs. Then, during resource allocation, it tries to map these frequently communicating virtual nodes to the same physical host, thereby avoiding unnecessary cross-host links. When cross-host communication is unavoidable, the system prioritizes mapping physical links with sufficient bandwidth and low load to ensure data transmission stability and efficiency. Through this link optimization strategy, network performance is improved, and resource utilization is more reasonable.

[0021] (4) Dynamic resource allocation is performed, and the final process of dynamic resource allocation is based on the results of these preliminary steps. Based on the allocation results calculated in the preliminary steps, the system generates a set of configuration files corresponding to a set of physical nodes. Each file corresponds to one physical node and contains the virtual node mapping relationship for that node. These files typically use a standardized format (such as YAML) and include parameters such as the resource requirements of the virtual nodes, allocated computing power, memory, storage space, and bandwidth. Automated operation and maintenance tools (such as Kubernetes) are used to push these configuration files to the corresponding physical nodes. The automated tools read the configuration files and start and configure the corresponding virtual machine instances on each physical node according to the file content, ensuring that the resource requirements of the virtual nodes match the resources of the physical nodes. The entire initial allocation process ensures reasonable resource allocation between virtual and physical nodes, optimized data transmission paths, and maximizes the utilization of physical resources.

[0022] Beneficial Effects: This invention proposes a method for allocating virtual network resources, aiming to solve the problems of low physical resource utilization and excessive cross-host links when virtual nodes are mapped to physical nodes in a multi-server environment. This method effectively judges and allocates virtual and physical network resources, ensuring that cross-host link configuration is optimized while meeting resource requirements.

[0023] The virtual network resource allocation scheme of this invention provides broadband operators with an efficient, flexible, and low-cost solution that can meet the actual needs of today's complex network environment and significantly improve the overall performance and economic benefits of the system.

[0024] The method of this invention is particularly suitable for broadband operators facing the needs of large-scale virtual network deployment and management in network function virtualization and cloud computing environments. It can effectively solve the problems of insufficient cross-host link optimization, uneven resource utilization, and untimely dynamic response in existing resource allocation methods, and provide operators with an efficient and flexible resource allocation solution in dynamic and ever-changing network environments.

[0025] The specific advantages are:

[0026] 1. Improve resource utilization: By quantifying and matching the resources of virtual nodes and physical nodes, the adaptation algorithm designed in this invention ensures that the resource requirements of virtual nodes are highly matched with the resource supply of physical nodes, thereby maximizing the resource utilization of physical servers and reducing resource waste.

[0027] 2. Reduce cross-host link communication: This technical solution focuses on optimizing the link configuration across physical hosts. By prioritizing the mapping of frequently communicating virtual nodes to the same physical node, the number of cross-host links is effectively reduced, thereby reducing data transmission latency and improving network performance.

[0028] 3. Dynamic Adjustment Capability: This invention not only covers initial resource allocation but also introduces a real-time dynamic adjustment mechanism, enabling adaptive adjustments to resource allocation based on the load of physical nodes. This ensures that the system maintains high stability and efficiency even when the load changes, making it suitable for dynamic and ever-changing network environments.

[0029] 4. Support for large-scale network deployment: This method is particularly suitable for the deployment of large-scale virtual networks. By introducing and optimizing link degree information, it can reduce system complexity while maintaining network performance and ensure high scalability and adaptability in large-scale environments.

[0030] 5. Reduced Operating Costs: By improving resource utilization and reducing inefficient cross-host communication links, this invention helps operators significantly reduce operating and maintenance costs in large-scale network deployments. Simultaneously, optimized resource allocation also reduces energy consumption, further improving the system's economic efficiency. Attached Figure Description

[0031] Figure 1 This is a schematic diagram of a virtual network resource allocation scenario provided by the present invention;

[0032] Figure 2This is a schematic diagram of the virtual network resource allocation process provided by the present invention;

[0033] Figure 3 This is a schematic diagram of the node allocation method based on adaptability according to the present invention;

[0034] Figure 4 This is a schematic diagram of the algorithm flow for the initial allocation module of this invention;

[0035] Figure 5 This is a schematic diagram of the algorithm flow of the dynamic allocation module of the present invention. Detailed Implementation

[0036] This invention mainly consists of a resource analysis module, an initial allocation module, a mapping operation module, and a dynamic allocation module. The resource analysis module is responsible for comprehensively evaluating and judging the resource requirements of virtual nodes and the available resources of physical nodes, ensuring accurate matching of each virtual node with its corresponding physical node during resource allocation. By quantifying the resource status of virtual and physical nodes, a clear resource requirement matrix and resource availability matrix are constructed, providing a reliable foundation for subsequent mapping.

[0037] The initial allocation module employs a genetic algorithm, combining the link degree information of virtual nodes, to optimize the mapping process from virtual nodes to physical nodes through operations such as selection, crossover, and mutation. In this module, adaptability not only considers the rational allocation of resources but also introduces link degree as an important evaluation metric, thereby effectively reducing the number of cross-host links and improving overall network performance. Through the collaborative work of these two modules, this invention enables efficient and flexible initial allocation of virtual network resources, meeting the practical needs of multi-server environments.

[0038] The mapping module is responsible for applying the virtual node link allocation results output by the algorithm mapping module to the physical hosts. Its main tasks are generating configuration files and using automated tools to allocate virtual nodes to physical nodes.

[0039] The dynamic allocation module aims to dynamically adjust the allocation of virtual nodes based on the real-time load of physical nodes and the resource requirements of virtual nodes. By monitoring the resource usage of physical nodes in real time, the module triggers resource reallocation when the load exceeds a set threshold. Incorporating a particle swarm optimization algorithm, this module can adaptively adjust the allocation scheme of virtual nodes to achieve system load balancing and resource optimization.

[0040] I. Resource Analysis Module: This module uses modeling to determine and quantify the resource requirements of virtual network nodes and the resource status of physical nodes, and performs a preliminary analysis of their compatibility.

[0041] Step 1: Virtual Node Resource Requirements Modeling

[0042] Each virtual node V in the virtual network i Resource demand can be characterized by the following key indicators:

[0043] • Computing power requirements Expressed in terms of the number of CPU cores.

[0044] Memory requirements Expressed in GB.

[0045] Storage requirements Expressed in GB.

[0046] Bandwidth requirements Expressed in Mbps.

[0047] The resource requirements of each virtual node can be aggregated into a single resource requirement vector:

[0048]

[0049] Step 2: Modeling the resource status of physical nodes

[0050] Each server node P in the physical network j The resource status can also be characterized by similar key indicators:

[0051] Available computing power Expressed in terms of the number of CPU cores.

[0052] Available memory Expressed in GB.

[0053] Available storage Expressed in GB.

[0054] Available bandwidth Expressed in Mbps.

[0055] The available resources of a server can be consolidated into a resource status vector:

[0056]

[0057] Step 3: Establishing the Resource Demand and Resource Status Matrix

[0058] By organizing the resource requirements of all virtual nodes and the resource status of all physical nodes into a matrix, the resource matching process can be effectively managed.

[0059] Virtual Node Demand Matrix:

[0060]

[0061] • Physical node resource status matrix R P :

[0062]

[0063] Step 4: Resource Adaptability Calculation

[0064] After quantifying the resources of virtual and physical nodes, the next step is to calculate the Compatibility Fit Rating (CFR). ij The fit is used to evaluate whether physical nodes can meet the resource requirements of virtual nodes. The calculation formula is as follows:

[0065]

[0066] Step 5: Setting the fit threshold

[0067] To ensure the reasonableness of the mapping, a fit threshold CFR is set. Th Only when CFR ij ≥CFR Th At that time, physical node P j Only then can it be considered to satisfy the virtual node V i The effective mapping target.

[0068] In summary, the modeling process described above effectively quantifies and analyzes the resource requirements of virtual nodes and the resource status of physical nodes, laying a solid foundation for subsequent virtual node mapping. This process ensures accurate matching during resource allocation, maximizes resource utilization efficiency, and provides a scientific basis for the management and allocation of network resources.

[0069] II. Initial Allocation Module: This module optimizes the mapping process from virtual nodes to physical nodes by combining a genetic algorithm with virtual node link degree. The detailed algorithm design for this integration of link degree and genetic algorithm is as follows.

[0070] Step 1: Algorithm Input

[0071] Virtual node demand matrix R V Resource requirements for each virtual node.

[0072] • Physical node resource status matrix R P Available resources for each physical node.

[0073] • Fit threshold T: The fit threshold used to filter valid mappings.

[0074] • Link degree matrix D: Link degree of each virtual node.

[0075] • Population size P: The population size in the genetic algorithm.

[0076] Crossover probability C p : The probability of crossover operation.

[0077] Mutation probability M p : The probability of mutation operation.

[0078] • Number of iterations G: The number of iterations of the algorithm.

[0079] Step 2: Initialize the population

[0080] Generate initial solution:

[0081] • Randomly generate P mapping solutions, each solution containing the mapping relationship between virtual nodes and physical nodes.

[0082] • Ensure that each virtual node is mapped to a physical node with a fit greater than the threshold T.

[0083] Step 3: Fit Assessment

[0084] For each solution S in the population k (representing a set of virtual nodes mapped to physical nodes), calculate the fitness degree F(S). k Adaptability considers not only fit but also link quality, as shown in the formula:

[0085]

[0086] Among them, CFR ij It's about compatibility. λ is the link degree of the virtual node, and λ is the weighting coefficient of the link degree's contribution to the adaptability.

[0087] Step 4: Select Operation - Tournament Selection

[0088] During the selection phase, a tournament selection method is used to determine which individuals will enter the next generation of the population.

[0089] 4.1: Setting Tournament Parameters

[0090] Determine the size T of the tournament, which is the number of individuals randomly selected from the population each time (e.g., T = 3).

[0091] 4.2: Conducting the tournament

[0092] Repeat the following process until the required number of adapted individuals N are selected:

[0093] • Randomly select an individual: Randomly select T individuals from the current population.

[0094] • Calculate fitness: Calculate the fitness F(S) of these T individuals. ti ).

[0095] • Select the best fit individual: Choose the individual with the highest fit as the winner.

[0096] 4.3: Formation of new populations

[0097] The selected adapted individuals are added to the new population S' until the size of the new population reaches the predetermined value.

[0098] Step 5: Cross-operation

[0099] The selected solutions are subjected to a crossover operation to generate new solutions. The crossover operation can be performed at a single point or multiple points.

[0100] Selecting crossover individuals: Randomly select two solutions S i and S j .

[0101] Intersection selection: Intersection points are randomly determined.

[0102] Generate a new solution: Keep the part before the intersection point and swap the part after the intersection point to generate a new solution.

[0103] Step 6: Mutation Operation

[0104] The new solution is mutated to increase the diversity of the population. The mutation operation can be achieved by randomly selecting a virtual node and reassigning it to another physical node.

[0105] • Selecting mutant individuals: based on the mutation probability M p Individuals are randomly selected for mutation.

[0106] • Perform mutation: Randomly change the mapping of a virtual node within the individual.

[0107] Step 7: Generate a new generation of population

[0108] The solutions obtained from crossover and mutation are combined with the original population to form a new population S”, and the optimal solution is selected based on fitness.

[0109] Step 8: Iterative Process

[0110] Repeat steps 3 to 7 until the set number of iterations G is reached or the fitness level reaches the desired level.

[0111] Step 9: Output the mapping result

[0112] After the algorithm finishes, the solution with the highest fitness is selected as the final virtual node to physical node mapping scheme, and the mapping relationship is output.

[0113] In summary, by combining virtual node link degree with a genetic algorithm, this invention achieves efficient virtual node mapping. It not only considers resource adaptability but also effectively utilizes the link degree information of virtual nodes to optimize resource allocation, reduce the number of cross-host links, and ultimately improve the performance and resource utilization of the entire network.

[0114] III. Mapping Operation Module: Generates configuration files and uses automated tools to assign virtual nodes to physical nodes.

[0115] Step 1: Generate configuration file:

[0116] Based on the output of the algorithm allocation module, a set of configuration files is generated, each corresponding to a physical node. The configuration files detail the mapping relationships of each virtual node, including its resource requirements, required computing power, memory, storage space, and bandwidth. These configuration files typically use a standardized format (such as YAML) for easy subsequent processing and automated deployment.

[0117] Step 2: Push configuration file:

[0118] Using automated operations and maintenance tools (such as Kubernetes), the generated configuration files are pushed to the corresponding physical nodes. The automated tools then start and configure the appropriate virtual machine instances on each physical node based on the information in the configuration files. This process can significantly reduce manual intervention and improve deployment efficiency.

[0119] Step 3: Resource Verification:

[0120] After a virtual node instance starts, the system performs resource verification to ensure that the actual resources of each virtual node match the available resources of the physical node. Simultaneously, the system checks whether the network link configuration meets expectations, ensuring the validity of the data transmission path. If resource mismatches or link problems are detected, the system logs the anomaly information and automatically adjusts the mapping to resolve the issue.

[0121] Step 4: Monitoring and Dynamic Adjustment

[0122] After mapping is complete, the mapping module will continuously monitor the running status and resource usage of the virtual nodes. Through a real-time monitoring system, it analyzes the performance data of each virtual node to ensure the stability of network services. If, during operation, the module detects that the resource utilization of certain physical nodes is too high or too low, it will make necessary adjustments based on real-time feedback to optimize resource allocation and network performance. For example, it can reallocate some virtual nodes to less loaded physical nodes, or, if necessary, launch additional virtual instances to meet the demand.

[0123] Step 5: Feedback and Optimization

[0124] This module also includes a feedback mechanism that periodically evaluates the effectiveness of the mapping strategy based on operational results. By analyzing historical data and resource usage, the mapping operation module provides optimization suggestions for future resource allocation and mapping strategies, thereby continuously improving the overall efficiency of the system.

[0125] Summarize:

[0126] By implementing this mapping operation module, the present invention can ensure efficient matching between virtual nodes and physical nodes, optimize data transmission paths, maximize the utilization of physical resources, and achieve dynamic adjustment and optimization, thereby enabling the network system to have greater flexibility and stability.

[0127] IV. Dynamic Allocation Module: Through the particle swarm optimization algorithm, the module can effectively find the globally optimal allocation scheme during the migration of virtual nodes, reduce the risk of physical node overload, reduce the communication overhead of cross-host links, and improve system performance.

[0128] 1. Definition:

[0129] • Particle xi: Represents an allocation scheme from virtual node V to physical node P.

[0130] Particle velocity v i : Represents particle x i The update direction and movement speed.

[0131] Fitness function f(x) i ): Used to evaluate the quality of particle assignment schemes. Minimizes the system using the fitness function.

[0132] The overall load difference.

[0133] ·Global optimal solution g * The best virtual node allocation scheme globally to date.

[0134] • Individual optimal solution p i : The optimal solution found by particle i itself.

[0135] 2. Fitness function:

[0136] f(x i We need to measure the load balancing status of each physical node, which is represented here by the load index of the physical node:

[0137]

[0138] in:

[0139] · It is physical node P j The current load index;

[0140] · It is the average load across all physical nodes.

[0141] The goal is to minimize the deviation between the load on each physical node and the average load, ensuring overall load balance in the system.

[0142] 3. Dynamically adjust algorithm steps

[0143] Step 1: Initialization

[0144] (1) Initialize the particle swarm: Randomly generate a particle swarm {x1, x2, ..., x} n}, where each particle represents a mapping from a virtual node to a physical node.

[0145] (2) Initialize velocity: Assign an initial velocity v to each particle. i The initial value can be a random decimal.

[0146] (3) Calculate the initial fitness: using the fitness function f(x) i Calculate the fitness of each particle.

[0147] (4) Set the initial individual optimal solution and the global optimal solution: Take the current state of each particle as its individual optimal solution p. i The particle with the best fitness is selected as the global optimal solution g. * .

[0148] Step 2: Particle Swarm Update

[0149] In each iteration, the particle is updated based on its velocity and position, as follows:

[0150] (1) Update speed:

[0151] The particle velocity update formula is:

[0152] v i(t+1) =w·v i (t)+c1·r1·(p i -x i (t))+c2·r2·(g * -x i (t))

[0153] in:

[0154] w is the inertia weight, used to control the smoothness of velocity updates;

[0155] c1 and c2 are learning factors that control the influence of individual components on the global optimal solution.

[0156] r1 and r2 are random numbers used to increase the diversity of exploration;

[0157] p i It is the individual optimal solution of the particle itself;

[0158] g * It is the globally optimal solution.

[0159] (2) Update location:

[0160] The particle positions (i.e., the allocation scheme) are updated as follows:

[0161] x i (t+1)=x i (t)+v i (t+1)

[0162] The new position of the particle represents a new mapping scheme for the virtual node.

[0163] (3) Boundary constraints:

[0164] Ensure that the mapping of each virtual node is within the resource limits of the physical node. If a new location exceeds the resource limits of the physical node, correct the particle's position to avoid invalid allocation schemes.

[0165] Step 3: Fitness Assessment and Update

[0166] Calculate the new fitness: based on the new particle position x i (t+1), recalculate fitness f(x) i ).

[0167] Update the individual optimal solution: If the particle's current fitness is better than its individual optimal solution, then update its individual optimal solution p. i .

[0168] Update the global optimum: if the current particle's fitness is better than the global optimum g. * Then update the global optimal solution.

[0169] Step 4: Iteration and Stopping Conditions

[0170] Iteration: Repeat steps 2 and 3 to continuously update the particle's velocity, position, and fitness.

[0171] Stopping condition: The algorithm stops when it reaches the set maximum number of iterations G or when the fitness of the global optimal solution no longer improves.

[0172] 4. Dynamic adjustment strategy

[0173] • Migration Strategy: Based on the globally optimal solution found by the particle swarm optimization, virtual nodes that need to be migrated are moved from the overloaded physical node P. j Reassigned to the lower-load physical node P k.

[0174] • Real-time adjustment: The real-time dynamic allocation module periodically runs the particle swarm optimization algorithm to analyze and adjust the mapping scheme of virtual nodes, ensuring that the system maintains stable performance under high load.

[0175] Summarize:

[0176] The dynamic allocation module monitors the load status of physical nodes in real time and uses a particle swarm optimization algorithm to make rapid and effective adjustments during resource allocation, ensuring balanced utilization of physical node resources and optimized system load. This module demonstrates its efficiency and flexibility in high-load and dynamic network environments, particularly in large-scale network scenarios for broadband operators.

[0177] In summary, the four modules of this invention—resource analysis module, initial allocation module, mapping operation module, and dynamic allocation module—are closely integrated to form a complete dynamic allocation scheme for virtual network resources. This scheme not only provides a scientific basis for broadband operators to map virtual nodes to physical nodes in multi-server environments through accurate resource demand analysis and effective adaptability assessment, but also optimizes resource allocation using genetic algorithms and link degree information, significantly reducing the number of cross-host links and thus improving network performance.

[0178] In real-world applications, broadband operators face ever-increasing user demand and complex network environments. This invention, through an efficient resource allocation mechanism and dynamic adjustment strategies, ensures that operators maintain network stability and service quality when dealing with peak traffic. Simultaneously, optimized resource utilization efficiency and reduced operating costs will bring higher economic benefits and competitiveness to broadband operators.

[0179] Therefore, this invention not only has high technical feasibility, but also demonstrates significant commercial value in practical applications, providing broadband operators with practical solutions to meet their urgent needs in network management and resource optimization.

[0180] Example:

[0181] A set of 10 virtual network nodes is assigned to 2 physical hosts. The link topology connectivity of the virtual network nodes is 0.5, and the topology is randomly generated. The resulting resource matrix is ​​as follows:

[0182]

[0183] The link degree of a node is calculated by counting the number of links between each virtual node and its neighbors.

[0184] D i =[3,6,1,2,5,3,2,3,4,1]

[0185] Calculate the fit using virtual node V1 and physical node P1 as an example:

[0186]

[0187] The reasonable fit threshold (CFR) here Th =5, corresponding to the case where virtual network nodes are evenly distributed among physical nodes. The initial fitness matrix is ​​calculated similarly:

[0188]

[0189] CFR is visible ij All greater than CFR Th The initial allocation is completed by multiplying the fit by the link degree and weighting the result using a genetic algorithm for heuristic optimization.

[0190]

[0191] The initial allocation results are as follows: physical node P1 is allocated virtual network nodes V2, V4, V5, V9, and V10; physical node P2 is allocated virtual network nodes V1, V3, V6, V7, and V8.

[0192] When the resource status of a virtual network node changes but the link topology remains the same, the dynamic allocation process begins.

[0193] After the update

[0194]

[0195] The initial allocation result is used as the initial position of the particles, and the fitness matrix is ​​passed in as the velocity. The dynamic allocation result is obtained through the particle swarm optimization algorithm: [2,2,2,1,1,2,1,2,2,1]. That is, physical node P1 is allocated virtual network nodes V4, V5, V7, and V10.

[0196] Physical node P2 is assigned virtual network nodes V1, V2, V3, V6, V8, and V9.

[0197] Simulation performance evaluation

[0198] 1. Test scenario: Set the number of virtual network nodes to 25, 50, 75, 100, 125, 150, 175, and 200, the link connection rate to 0.5, and the topology to be randomly generated; set two physical hosts, with a total resource of 150% of the total resource of the virtual network nodes.

[0199] 2. Test Indicators:

[0200] • Number of cross-physical host resource links: Records the number of links across physical servers generated after the virtual network topology is allocated. Since the total amount of resources is fixed at 150% of the virtual network resources and the occupancy rate is fixed, the number of cross-host resource links can reflect the degree of node aggregation and link optimization after the algorithm allocation. The fewer the number, the better.

[0201] • Algorithm execution time: Record the execution time of each algorithm on nodes of different sizes to evaluate its real-time performance and efficiency; the faster the better.

[0202] 3. Test algorithms: Genetic algorithm, Particle swarm optimization algorithm, Sequential algorithm, Greedy algorithm.

[0203] 4. Test Results:

[0204]

[0205]

[0206]

[0207] Based on the simulation data above, in terms of resource allocation, the genetic algorithm exhibits the fewest cross-host resource links and the highest resource utilization across all node counts, followed by the particle swarm optimization algorithm. Both are significantly better than the greedy algorithm and the sequential algorithm. Regarding runtime, the genetic algorithm's time increases dramatically with the number of nodes, while the particle swarm optimization algorithm, although slower than the greedy and sequential algorithms, shows only a slight difference. In summary, in initial allocation scenarios, the genetic algorithm can fully utilize its global search capability to find the optimal resource and link allocation scheme, improving system efficiency. In dynamic allocation scenarios, the particle swarm optimization algorithm balances real-time performance and resource optimization effectiveness, ensuring rapid adjustment under changing loads and maintaining system stability and performance. This combined optimization not only improves resource utilization but also effectively reduces the number of cross-host links, ensuring the system maintains optimal performance under different load conditions.

[0208] Specific embodiments have been used to illustrate the principles and implementation methods of this invention. The descriptions of the embodiments above are only for the purpose of helping to understand the method and core ideas of this invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this invention. Therefore, the content of this specification should not be construed as a limitation of this invention.

Claims

1. A method for allocating virtual network resources in a multi-server scenario, characterized in that, A network communication system based on virtual and physical networks is characterized by virtual nodes and links in the virtual network through certain resource requirements. The resources required by virtual nodes include computing power, memory, and storage, while the requirements of virtual links are bandwidth. The physical network consists of physical nodes and physical links. Each physical node has a certain resource capacity, including processor, memory, and storage, while the physical links provide corresponding bandwidth resources. Use G V This represents a virtual network, consisting of a set of virtual nodes and virtual links, where each virtual node is n. V With specific resource requirements R V Virtual Link V Bandwidth requirement B V Physical network G P Includes physical nodes and physical links, physical node n P Available resources R P Physical link P Provide available bandwidth B P ; The core of virtual network resource mapping lies in the rational allocation of virtual nodes and links to physical nodes and links; during the allocation process, the following conditions must be guaranteed: Each virtual node must be mapped to a physical node that can provide sufficient resources, i.e., R. P ≥R V To meet the computing and storage needs of virtual nodes; Each virtual link must be mapped to a physical link that can provide sufficient bandwidth, i.e., B. P ≥B V To ensure the needs of network communication; In a multi-server environment, communication between virtual nodes can span multiple physical servers, so the number and efficiency of cross-host links become key factors affecting system performance. To achieve efficient resource allocation, a mapping algorithm based on adaptability is adopted. The algorithm calculates the adaptability between virtual nodes and physical nodes to determine whether physical nodes can meet the needs of virtual nodes. The adaptability is calculated based on the resource requirements of virtual nodes and the available resources of physical nodes. Only physical nodes with an adaptability that reaches a set threshold are considered valid mapping targets. During the mapping process, physical nodes with high adaptability and low load are selected to ensure balanced resource utilization. In addition, link optimization is considered simultaneously during the initial allocation. By evaluating the communication needs of virtual nodes, nodes that communicate frequently are preferentially mapped to the same physical node to reduce the need for cross-host links. The allocation mechanism for virtual network resources consists of the following parts: network resource assessment, network resource quantification, link policy optimization, initial resource allocation, and dynamic resource allocation. (1) The process of network resource judgment is achieved through a comprehensive analysis of the resource requirements of virtual nodes and the available resources of physical nodes. First, the system collects the resource requirement information of virtual nodes, including computing power, memory, storage and bandwidth, to form a virtual node requirement matrix. At the same time, the system monitors the resource status of each physical node, including available computing power, memory, storage space and bandwidth, to form a physical resource matrix. Next, by calculating the resource compatibility between virtual nodes and physical nodes, it is determined whether the physical nodes can meet the requirements of virtual nodes, which provides a reliable basis for subsequent allocation and link optimization. (2) The process of quantifying network resources is to represent the resource requirements and resource status of virtual nodes and physical nodes with specific numerical values ​​so as to achieve accurate matching in the allocation process. First, the resource requirements of virtual nodes are quantified into a demand vector, representing the specific resource requirements of each virtual node. Second, the available resources of physical nodes are also quantified into a corresponding resource vector, recording the amount of resources that they can currently provide. By establishing a virtual node demand matrix and a physical node available resource matrix, the demand and supply of network resources are clearly quantified. This process provides a numerical basis for subsequent virtual node mapping, which helps to accurately calculate the fit and optimize the allocation of virtual nodes.

2. The virtual network resource allocation method in a multi-server scenario according to claim 1, characterized in that, Perform link strategy optimization. Link strategy optimization improves data transmission efficiency and reduces latency by reducing the number of cross-physical host communication links between virtual nodes. First, the system analyzes the communication needs between virtual nodes and identifies frequently communicating virtual node pairs. Then, during resource allocation, it tries to map these frequently communicating virtual nodes to the same physical host, thus avoiding unnecessary cross-host links. When cross-host communication is unavoidable, the system prioritizes mapping physical links with sufficient bandwidth and low load to ensure data transmission stability and efficiency. Through this link optimization strategy, network performance is improved, and resource utilization is more rational.

3. The virtual network resource allocation method in a multi-server scenario according to claim 1 or 2, characterized in that, Dynamic resource allocation is performed; the final process of dynamic resource allocation will be based on the results of these preliminary steps; based on the allocation results calculated in the preliminary steps, the system will generate a set of configuration files corresponding to a set of physical nodes, with each file corresponding to a physical node and containing the virtual node mapping relationship of that node; These files typically use a standardized format and include the resource requirements of virtual nodes, allocated computing power, memory, storage space, and bandwidth parameters. Automated operation and maintenance tools push these configuration files to the corresponding physical nodes. The automated tools read the configuration files and start and configure the corresponding virtual machine instances on each physical node according to the file content, ensuring that the resource requirements of the virtual nodes match the resources of the physical nodes. The entire initial allocation process ensures reasonable allocation of resources between virtual and physical nodes, optimized data transmission paths, and maximizes the utilization of physical resources.

4. The virtual network resource allocation method in a multi-server scenario according to claim 2, characterized in that, To optimize link configuration, the strategy analyzes the communication needs between virtual nodes and maps frequently communicating virtual nodes to the same physical node to avoid unnecessary cross-host communication. When cross-host communication is unavoidable, physical links with higher capacity and lower load are selected for mapping to ensure the stability and efficiency of data transmission.

5. The virtual network resource allocation method in a multi-server scenario according to claim 2, characterized in that, When optimizing the link strategy, a combination of genetic algorithm and virtual node link degree is used to optimize the mapping process from virtual nodes to physical nodes; the algorithm design integrates link degree and genetic algorithm. Step 1: Algorithm Input ●Virtual Node Demand Matrix R V Resource requirements for each virtual node; ●Physical Node Resource Status Matrix R R Available resources for each physical node; ●Fitness threshold T: The fit threshold used to filter valid mappings; ●Link degree matrix D: Link degree of each virtual node; ●Population size P: Population size in genetic algorithms; ● Crossover probability C p The probability of a crossover operation; ●Probability of mutation M p The probability of a mutation operation; ● Number of iterations G: The number of iterations of the algorithm; Step 2: Initialize the population Generate initial solution: ● Randomly generate P mapping solutions, each solution containing the mapping relationship between virtual nodes and physical nodes; ● Ensure that each virtual node is mapped to a physical node with a fit greater than the threshold T; Step 3: Fit Assessment For each solution S in the population k Each represents a set of virtual nodes mapped to physical nodes, and the fitness degree F(S) is calculated. k Adaptability considers not only adaptability but also link degree, and the formula is: Among them, CFR ij It's about compatibility. λ is the link degree of the virtual node, and λ is the weight coefficient of the link degree's contribution to the adaptability. Step 4: Select Operation - Tournament Selection During the selection phase, a tournament selection method is used to determine which individuals will enter the next generation of the population; 4.1: Setting Tournament Parameters Determine the size T of the tournament, which is the number of individuals randomly selected from the population each time; 4.2: Conducting the tournament Repeat the following process until the required number of adapted individuals N are selected: ● Randomly select an individual: Randomly select individual T from the current population; ● Calculate fitness: Calculate the fitness F(S) of these T individuals. ti ); ●Select the best fit individual: Choose the individual with the highest fit as the winner; 4.3: Formation of new populations The selected adapted individuals are added to the new population S′ until the size of the new population reaches the predetermined value; Step 5: Cross-operation Perform a crossover operation on the selected solutions to generate new solutions; the crossover operation can be performed at a single point or multiple points. Selecting crossover individuals: Randomly select two solutions S i and S j ; Intersection selection: Randomly determine the intersection point; Generate a new solution: Keep the part before the intersection point, and swap the part after the intersection point to generate a new solution; Step 6: Mutation Operation The new solution is mutated to increase the diversity of the population; the mutation operation is achieved by randomly selecting a virtual node and reassigning it to another physical node. ●Selecting mutant individuals: Based on the mutation probability M p Randomly select individuals for mutation; • Perform mutation: Randomly change the mapping of a virtual node within this individual; Step 7: Generate a new generation of population The solutions obtained from crossover and mutation are combined with the original population to form a new population S″, and the optimal solution is selected based on fitness. Step 8: Iterative Process Repeat steps 3 to 7 until the set number of iterations G is reached or the fitness level reaches the desired level; Step 9: Output the mapping result After the algorithm finishes, the solution with the highest fitness is selected as the final virtual node to physical node mapping scheme, and the mapping relationship is output.

6. The virtual network resource allocation method in a multi-server scenario according to claim 5, characterized in that, Mapping module: Generates configuration files and uses automated tools to assign virtual nodes to physical nodes; Step 1: Generate configuration file: Based on the output of the algorithm allocation module, a set of configuration files are generated, each file corresponding to a physical node. The configuration files record in detail the mapping relationship of each virtual node, including its resource requirements, required computing power, memory, storage space and bandwidth parameters. These configuration files are usually in a standardized format to facilitate subsequent processing and automated deployment. Step 2: Push configuration file: Use automated operation and maintenance tools to push the generated configuration files to the corresponding physical nodes; The automation tool starts and configures the corresponding virtual machine instance on each physical node based on the information in the configuration file; this process greatly reduces manual intervention and improves deployment efficiency. Step 3: Resource Verification: After a virtual node instance is started, the system performs resource verification to ensure that the actual resources of each virtual node match the available resources of the physical node. At the same time, the system also checks whether the network link configuration meets expectations to ensure the validity of the data transmission path. If resource mismatch or link problems are found, the system will record the abnormal information and automatically adjust the mapping to resolve the problem. Step 4: Monitoring and Dynamic Adjustment After mapping is completed, the mapping operation module will continuously monitor the running status and resource usage of the virtual nodes; through the real-time monitoring system, it will analyze the performance data of each virtual node to ensure the stability of network services. If, during operation, the module detects that the resource utilization of certain physical nodes is too high or too low, it will make necessary adjustments based on real-time feedback information to optimize resource allocation and network performance.

7. The virtual network resource allocation method in a multi-server scenario according to claim 5, characterized in that, Dynamic allocation module: Through particle swarm optimization algorithm, the module can effectively find the globally optimal allocation scheme during the migration of virtual nodes, reduce the risk of physical node overload, reduce the communication overhead of cross-host links, and improve system performance. 1) Definition: Particle x i : Represents an allocation scheme from virtual node V to physical node P; Particle velocity v i : Represents particle x i The update direction and movement speed; Fitness function f(x) i ): Used to evaluate the quality of particle assignment schemes; minimizes the overall load variation of the system through the fitness function; ·Global optimal solution g * The best virtual node allocation scheme globally to date; • Individual optimal solution p i The optimal solution found by particle i itself; 2) Fitness function: f(x i We need to measure the load balancing status of each physical node, which is represented here by the load index of the physical node: in: · It is physical node P j The current load index; ● It is the average load across all physical nodes; The goal is to minimize the deviation between the load on each physical node and the average load, ensuring overall load balance in the system. 3) Dynamically adjust algorithm steps Step 1: Initialization (1) Initialize the particle swarm: Randomly generate a particle swarm {x1, x2, ..., x} n }, where each particle represents a mapping from a virtual node to a physical node; (2) Initialize velocity: Assign an initial velocity v to each particle. i The initial value is a random decimal; (3) Calculate the initial fitness: using the fitness function f(x) i Calculate the fitness of each particle; (4) Set the initial individual optimal solution and the global optimal solution: Take the current state of each particle as its individual optimal solution p. i The particle with the best fitness is selected as the global optimal solution g. * ; Step 2: Particle Swarm Update In each iteration, the particle is updated based on its velocity and position, as follows: (1) Update speed: The particle velocity update formula is: v i(t+1) =w·v i (t)+c1·r1·(p i -x i (t))+c2·r2·(g * -x i (t)) in: w is the inertia weight, used to control the smoothness of velocity updates; c1 and c2 are learning factors that control the influence of individual components on the global optimal solution. r1 and r2 are random numbers used to increase the diversity of exploration; p i It is the individual optimal solution of the particle itself; g * It is the globally optimal solution; (2) Update location: The particle positions (i.e., the allocation scheme) are updated as follows: x i (t+1)=x i (t)+v i (t+1) The new position of the particle represents a new mapping scheme for the virtual node; (3) Boundary constraints: Ensure that the mapping of each virtual node is within the resource limits of the physical node; if the new position exceeds the resource limits of the physical node, correct the position of the particle to avoid invalid allocation schemes. Step 3: Fitness Assessment and Update Calculate the new fitness: based on the new particle position x i (t+1), recalculate fitness f(x) i ); Update the individual optimal solution: If the particle's current fitness is better than its individual optimal solution, then update its individual optimal solution p. i Update the global optimum: if the current particle's fitness is better than the global optimum g. * Then update the global optimal solution; Step 4: Iteration and Stopping Conditions Iteration: Repeat steps 2 and 3 to continuously update the particle's velocity, position, and fitness; Stopping condition: The algorithm stops when it reaches the set maximum number of iterations G or when the fitness of the global optimum no longer improves; 4) Dynamic adjustment strategy ● Migration Strategy: Based on the globally optimal solution found by the particle swarm optimization, virtual nodes that need to be migrated are moved from the overloaded physical node P. j Reassigned to the lower-load physical node P k ; ● Real-time adjustment: The real-time dynamic allocation module periodically runs the particle swarm optimization algorithm to analyze and adjust the mapping scheme of virtual nodes, ensuring that the system maintains stable performance under high load; The dynamic allocation module monitors the load status of physical nodes in real time and uses the particle swarm optimization algorithm to make rapid and effective adjustments during the resource allocation process, ensuring that the resources of physical nodes are used in a balanced manner and the system load is optimized.

Images