A method and system for managing internet resources

Abstract

The invention discloses a management method and system for Internet resources, and relates to the field of data management. The method comprises: receiving resource data indicators and obtaining a resource data indicator matrix; calculating the dynamic entropy weight of each resource indicator based on the matrix; constructing an adaptive entropy weight hybrid optimization algorithm based on the dynamic entropy weight to obtain a resource allocation scheme; performing real-time simulation of the resource allocation scheme through digital twin technology and obtaining simulation results, and optimizing the parameters of the adaptive entropy weight hybrid optimization algorithm based on the simulation results; obtaining the state prediction of Internet resources, and inputting the state prediction into the optimized adaptive entropy weight hybrid optimization algorithm to realize dynamic adjustment of resource allocation strategy. By calculating the dynamic entropy weight of resource data indicators, constructing an adaptive entropy weight hybrid optimization algorithm and generating a resource allocation scheme, and performing real-time simulation and feedback optimization of the allocation scheme through digital twin technology, and combining resource state prediction at the same time, dynamic adjustment of resource allocation is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of data management, and in particular to a method and system for managing Internet resources. Background Art

[0002] With the rapid development of Internet technology, the number and complexity of network resources have shown exponential growth. How to efficiently manage and allocate Internet resources has become an important research direction. Internet resource management involves the collection, analysis, optimization and dynamic adjustment of multiple data indicators. The current technical solutions have obvious deficiencies in the following aspects: The processing method of Internet resource data indicators in the existing technology usually adopts a static method, which is difficult to effectively deal with the diversity and dynamic nature of resource data. This static processing method cannot accurately reflect the changing rules of resources at different times and scenarios, resulting in the lack of real-time and flexibility of resource allocation strategies. Traditional resource indicator weight calculation methods are usually based on fixed weights or empirical weights, which are difficult to adapt to resource management requirements in complex dynamic scenarios, and are prone to excessive or insufficient allocation of certain resources, affecting the efficiency and stability of the overall system. Existing resource allocation algorithms generally rely on a single optimization model and lack multi-objective optimization capabilities. Especially in the case of fierce resource competition and dynamic changes in demand, they cannot comprehensively consider the dynamic characteristics of multiple indicators, resulting in the lack of rationality and scalability of resource allocation schemes. Most current resource allocation methods lack real-time simulation verification links, making it difficult to timely discover potential problems in resource allocation schemes. In addition, the parameter optimization of the allocation model usually relies on manual adjustment or periodic training, and fails to achieve dynamic optimization, resulting in insufficient adaptability of the allocation model. For the prediction of future resource status, existing technologies are often based on static rules or simple linear models, and fail to make full use of complex data relationships and historical trends for high-precision prediction. In addition, the combination of prediction results and resource allocation strategies is weak, making it difficult to achieve the resource management goals of dynamic adjustment and real-time response. Summary of the invention

[0003] In view of this, the present invention proposes a management method and system for Internet resources, which can achieve efficient allocation and dynamic adjustment of Internet resources through the synergy of dynamic entropy weight calculation, adaptive hybrid optimization algorithm, digital twin simulation and feedback optimization, and resource status prediction, and improve the real-time, accuracy and adaptability of the system. The present invention provides the following technical solutions:

[0004] A method for managing Internet resources, the method comprising: receiving resource data indicators of the Internet, and standardizing the resource data indicators to obtain a resource data indicator matrix; calculating the dynamic entropy weight of each resource indicator based on the resource data indicator matrix; constructing an adaptive entropy weight hybrid optimization algorithm based on the dynamic entropy weight to obtain a resource allocation plan; performing real-time simulation of the resource allocation plan through digital twin technology and obtaining simulation results, and optimizing parameters of the adaptive entropy weight hybrid optimization algorithm based on the simulation results; obtaining a state prediction of Internet resources, and inputting the state prediction into the optimized adaptive entropy weight hybrid optimization algorithm to achieve dynamic adjustment of resource allocation strategies.

[0005] Optionally, the method of receiving resource data indicators from the Internet and standardizing the resource data indicators to obtain a resource data indicator matrix includes: receiving multiple resource data indicators in the Internet environment in real time, the resource data indicators including bandwidth, load, memory usage, storage occupancy, and response delay; standardizing the multiple resource data indicators; and converting the standardized resource data indicators into a resource data indicator matrix.

[0006] Optionally, the method for calculating the dynamic entropy weight of each resource indicator based on the resource data indicator matrix includes: calculating the entropy value of each resource indicator, and the calculation formula is:

[0007] ,in, For the The resource indicator The probability distribution of samples, is the sample size, is a constant;

[0008] The initial entropy weight of the resource indicator is calculated according to the entropy value. The calculation formula is:

[0009] ,in, For the The initial entropy weight of each resource indicator, is the total number of resource indicators;

[0010] Monitor the changing trend of the network and dynamically calculate the entropy weight of the resource based on the feedback change data. The calculation formula of the dynamic entropy weight is:

[0011] ,in, For the Resource indicators at time The dynamic entropy weight of For the The entropy weight of a resource indicator at the last moment, For the Resource indicators at time The feedback change data, is the maximum feedback value of all resource indicators, is the feedback adjustment coefficient.

[0012] Optionally, the method of constructing an adaptive entropy weight hybrid optimization algorithm based on the dynamic entropy weight to obtain a resource allocation scheme includes: performing initial resource allocation using a greedy algorithm based on the dynamic entropy weight; initializing multiple resource allocation schemes; and calculating the fitness of each resource allocation scheme, the calculation formula being:

[0013] ,in, For the Resource indicators at time The dynamic entropy weight of For the Resource indicators at time resource requirements; perform iterative optimization of the genetic algorithm for resource allocation based on the calculated fitness, and finally output a resource allocation plan.

[0014] Optionally, the method of simulating the resource allocation scheme in real time through digital twin technology and obtaining simulation results, and optimizing the parameters of the adaptive entropy weight hybrid optimization algorithm based on the simulation results includes: constructing a virtual model of network resources based on digital twin technology to reflect the usage and allocation of resources in real time; simulating the virtual model based on the current resource allocation scheme; evaluating the performance of the resource allocation scheme through simulation results; and adjusting the parameters of the adaptive entropy weight hybrid optimization algorithm according to the simulation results.

[0015] Optionally, the method of obtaining a state prediction of Internet resources and inputting the state prediction into the optimized adaptive entropy weight hybrid optimization algorithm to dynamically adjust the resource allocation strategy includes: calling a time series prediction model to predict the subsequent resource state of Internet resources, and the prediction process is:

[0016] ,in, is the target prediction state, , , …, For the Resource indicators at time , , ..., historical status, For external environment variables, is a time series prediction function; the calculated resource status prediction is input into the optimized adaptive entropy weight hybrid optimization algorithm, and combined with the current dynamic entropy weight and current resource requirements Perform dynamic calculations and output resource allocation plans. The calculation formula is:

[0017] ,in, For the Resource indicators at time The amount of resources allocated, For the Resource indicators at time The dynamic entropy weight of For the The resource status prediction value of each resource indicator, For the Resource indicators at time resource requirements;

[0018] Output the resource allocation plan in a collection form, as follows:

[0019] ,in, For the Resource indicators at time The amount of resources allocated, , is the total number of resource indicators.

[0020] The present invention further discloses a management system for Internet resources, comprising: a data processing module, used to receive resource data indicators of the Internet, and standardize the resource data indicators to obtain a resource data indicator matrix; an entropy weight calculation module, used to calculate the dynamic entropy weight of each resource indicator based on the resource data indicator matrix; a resource allocation module, used to construct an adaptive entropy weight hybrid optimization algorithm based on the dynamic entropy weight to obtain a resource allocation scheme; a simulation optimization module, used to perform real-time simulation of the resource allocation scheme through digital twin technology and obtain simulation results, and optimize the parameters of the adaptive entropy weight hybrid optimization algorithm based on the simulation results; a dynamic allocation module, used to obtain a state prediction of Internet resources, and input the state prediction into the optimized adaptive entropy weight hybrid optimization algorithm to achieve dynamic adjustment of resource allocation strategies.

[0021] The present invention further discloses a computer-readable storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned Internet resource management method is implemented.

[0022] The present invention further discloses an electronic device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned Internet resource management method when executing the program.

[0023] The present invention further discloses a computer program product, including a computer program, wherein the computer program implements the above-mentioned Internet resource management method when executed by a processor.

[0024] According to the technical solution of the present invention, through the standardized processing of resource data indicators, dynamic entropy weight calculation, construction of adaptive entropy weight hybrid optimization algorithm and generation of resource allocation scheme, the allocation scheme is simulated and optimized in real time through digital twin technology, and combined with resource status prediction, dynamic adjustment of resource allocation is realized. This method can scientifically determine the importance weights of resource indicators, take into account the needs of multi-objective dynamic optimization, improve the accuracy and adaptability of the allocation scheme through real-time simulation, and finally realize the efficient allocation and dynamic response of Internet resources, significantly improving the real-time performance, stability and resource utilization of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] For the purpose of illustration and not limitation, the present invention is now described in conjunction with the embodiments of the present invention and the accompanying drawings, in which:

[0026] Figure 1 is a flow chart of a method for managing Internet resources in an embodiment of the present invention;

[0027] Figure 2 It is a structural diagram of a management system for Internet resources in an embodiment of the present invention;

[0028] Figure 3 It is a schematic diagram of the structure of an electronic device in an embodiment of the present invention. DETAILED DESCRIPTION

[0029] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the implementation mode of the present application will be clearly and completely described below in conjunction with the drawings in the implementation mode of the present application. Obviously, the described implementation mode is only a part of the implementation mode of the present application, not all the implementation modes. Based on the implementation mode in the present application, all other implementation modes obtained by ordinary technicians in the field without creative work should fall within the scope of protection of the present application.

[0030] It should be noted that the terms "first", "second", etc. in the specification of the present application 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 data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0031] In the present application, the terms "upper", "lower", "left", "right", "front", "back", "top", "bottom", "inner", "outer", "middle", "vertical", "horizontal", "lateral", "longitudinal" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings. These terms are mainly used to better describe the present application and its implementation methods, and are not used to limit the indicated devices, elements or components to have a specific orientation, or to be constructed and operated in a specific orientation.

[0032] In addition, some of the above terms may be used to express other meanings in addition to indicating orientation or positional relationship. For example, the term "on" may also be used to express a certain dependency or connection relationship in some cases. For those of ordinary skill in the art, the specific meanings of these terms in this application can be understood according to the specific circumstances. In addition, the term "plurality" should mean two or more than two.

[0033] It should be noted that, in the absence of conflict, the embodiments of the present application and the features in the embodiments can be combined with each other. The embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0034] refer to Figure 1 This embodiment discloses a method for managing Internet resources, the method comprising:

[0035] S100: receiving resource data indicators of the Internet, and performing standardization processing on the resource data indicators to obtain a resource data indicator matrix.

[0036] Receive log files sent by servers or network devices, or use monitoring tools to collect resource status data in real time. Log files can be access logs of Web servers, database operation logs, network traffic records, etc., and extract resource data indicator information from log files. Exemplary resource data indicators include: basic system resources: CPU usage (unit: %), memory usage (unit: %), storage occupancy (unit: GB or %), network bandwidth (unit: Mbps), disk IO rate (unit: MB / s), system load (unit: Load Average); network-related indicators: response delay (unit: ms), network traffic (unit: Mbps), number of connections (unit: number), packet loss rate (unit: %), throughput (unit: requests / s); service performance indicators: QPS (Queries Per Second), RTT (Round Trip Time, round-trip delay), request success rate (unit: %), transaction processing time (unit: ms), error rate (unit: %); user behavior related indicators: user request volume (unit: requests), number of active users (unit: individual), access frequency (unit: requests / user), page dwell time (unit: seconds); system log analysis indicators: number of log warnings (unit: item), number of abnormal events (unit: times), resource usage peak time period; custom business indicators: task queue length, data throughput (unit: MB / s), API call frequency (unit: calls / min), cache hit rate (unit: %). The above data indicators are combined into the original data set:

[0037] ,in, For the The sample in The value of a resource indicator, is the total number of samples, is the indicator dimension, , .

[0038] Use maximum and minimum normalization and Z-score standardization to convert the original data set into dimensionless standardized values ​​and eliminate the dimension differences between indicators. Specifically, normalize the original data set to the [0,1] interval:

[0039] ,in, After standardization The sample Resource indicator value, For the The minimum value of a resource indicator. For the The maximum value of resource indicators.

[0040] Further standardize the normalized resource indicator values:

[0041] ,in, For the The mean value of resource indicators, For the The standard deviation of a resource indicator.

[0042] All standardized indicator values ​​are further integrated into the resource data indicator matrix:

[0043] ,in, No. The sample The standardized value of the resource indicator value, , .

[0044] S200: Calculate the dynamic entropy weight of each resource indicator based on the resource data indicator matrix. Specifically including:

[0045] Calculate the entropy value of each resource indicator using the following formula:

[0046] ,in, For the The resource indicator The probability distribution of samples, is the sample size, is a constant.

[0047] The initial entropy weight of the resource indicator is calculated according to the entropy value. The calculation formula is:

[0048] ,in, For the The initial entropy weight of each resource indicator, is the total number of resource indicators;

[0049] Monitor the changing trend of the network and dynamically calculate the entropy weight of the resource based on the feedback change data. The calculation formula of the dynamic entropy weight is:

[0050] ,in, For the Resource indicators at time The dynamic entropy weight of For the The entropy weight of a resource indicator at the last moment, For the Resource indicators at time Feedback change data, is the maximum feedback value of all resource indicators, is the feedback adjustment coefficient.

[0051] S300: constructing an adaptive entropy weight hybrid optimization algorithm based on the dynamic entropy weight to obtain a resource allocation solution. Specifically:

[0052] Based on the dynamic entropy weight, a greedy algorithm is used to perform initial resource allocation. Specifically, the total amount of resources R available in the system and each task are obtained. Resource requirements at the current time t And the dynamic entropy weight of the resource indicator corresponding to the resource demand at time t .

[0053] Computational tasks The weighted score for resource demand is calculated as:

[0054] ,in, For resource requirements The standardized value of .

[0055] After obtaining the weighted scores, calculate each task The comprehensive score is calculated as follows:

[0056] ,in, is the total number of resource samples, The current resource demand priority.

[0057] Based on the comprehensive score , sort all tasks, the higher the comprehensive score, the higher the priority of the task, and the more priority resources will be allocated. Specifically:

[0058] Sort multiple tasks according to the comprehensive scores, traverse the resource indicators of multiple tasks in turn, and read their resource requirements. If the resource requirements of the current task are less than the remaining resources in the total resources, allocate the resource requirements to it, otherwise allocate the remaining resources. If all tasks are traversed or the total resources are allocated, the resource allocation is terminated to obtain the final resource allocation plan.

[0059] Initialize multiple resource allocation schemes;

[0060] Calculate the fitness of each resource allocation scheme using the following formula:

[0061] ,in, For the Resource indicators at time The dynamic entropy weight of For the Resource indicators at time resource requirements;

[0062] The genetic algorithm for resource allocation is iteratively optimized based on the calculated fitness, and the resource allocation plan is finally output.

[0063] S400: Performing real-time simulation of the resource allocation scheme through digital twin technology and obtaining simulation results, and optimizing the parameters of the adaptive entropy weight hybrid optimization algorithm based on the simulation results. Specifically:

[0064] Based on digital twin technology, a virtual model of network resources is constructed to reflect the use and allocation of resources in real time. The resource data indicators obtained in step S100 are extracted and constituted into an input data set. A digital round-robin virtual model of network resources is constructed using virtual modeling tools such as Simulink and AnyLogic. The model is mapped to the resource nodes, task requirements and allocation strategies in the real network. This can reflect the allocation of resources, utilization rate and task execution effect in real time, and achieve high-fidelity mapping between data input and simulation results.

[0065] Based on the current resource allocation scheme, the virtual model is simulated, that is, the resource allocation scheme obtained in step S300 is input into the above virtual model. Then, in the digital twin environment, the resource occupancy, resource scheduling and execution process of each task node are simulated, and problems such as resource bottlenecks, imbalanced allocation or task execution delays are monitored in real time. At the same time, the dynamic performance indicators in the virtual simulation process are recorded, including task completion time, resource utilization, task delay rate, task success rate and other result data.

[0066] The performance of the resource allocation scheme is evaluated through the simulation results. Specifically, the key performance indicators (KPIs) are calculated according to the simulation results. The exemplary implementation includes:

[0067] Resource utilization: evaluates the efficiency of resource use and calculates the ratio of allocated resources to available resources;

[0068] Task completion rate: Count the completion ratio of each task node and evaluate the effectiveness of task allocation;

[0069] Network latency and throughput: Evaluate the network performance of resource allocation schemes while meeting mission requirements.

[0070] Combined with the simulation results, the fitness value of the resource allocation scheme is quantified, and the performance bottleneck or optimization direction is identified through comparative analysis.

[0071] According to the simulation results, the parameters of the adaptive entropy weight hybrid optimization algorithm are adjusted. Specifically, they include:

[0072] According to the resource utilization, task completion rate, delay and other indicators obtained in the simulation, the parameters of the adaptive entropy weight hybrid optimization algorithm are dynamically adjusted, including: entropy weight coefficient adjustment: combining the task priority and resource demand indicator weight distribution, recalculating the dynamic entropy weight coefficient; fitness function parameter optimization: calibrating the weight factor in the fitness function to ensure the accuracy and robustness of the resource allocation plan; iterative control parameter adjustment: such as the crossover probability and mutation probability of the genetic algorithm or the inertia weight of the particle swarm algorithm, to further accelerate the convergence speed.

[0073] The optimized parameters are fed back to the resource allocation algorithm, the resource allocation calculation is re-executed and a new resource allocation plan is generated.

[0074] The optimized resource allocation plan is input into the digital twin model again for simulation to verify the optimization effect. The simulation, evaluation and parameter adjustment process is repeated to form a real-time feedback closed-loop optimization mechanism to ensure that the resource allocation plan is continuously optimized and converges to the optimal solution in a dynamic environment.

[0075] S500: Obtaining the state prediction of Internet resources, and inputting the state prediction into the optimized adaptive entropy weight hybrid optimization algorithm to dynamically adjust the resource allocation strategy. Specifically including:

[0076] The time series prediction model is called to predict the subsequent resource status of the Internet resource. The prediction process is as follows:

[0077] ,in, is the target prediction state, , , …, For the Resource indicators at time , , ..., historical status, For external environment variables, is the time series prediction function;

[0078] The calculated resource status prediction is input into the optimized adaptive entropy weight hybrid optimization algorithm, and combined with the current dynamic entropy weight and current resource requirements Perform dynamic calculations and output resource allocation plans. The calculation formula is:

[0079] ,in, For the Resource indicators at time The amount of resources allocated, For the Resource indicators at time The dynamic entropy weight of For the The resource status prediction value of each resource indicator, For the Resource indicators at time resource requirements;

[0080] Output the resource allocation plan in a collection form, as follows:

[0081] ,in, For the Resource indicators at time The amount of resources allocated, , The total number of resource indicators.

[0082] The resource allocation strategy can be dynamically adjusted through the output resource allocation plan.

[0083] In summary, this implementation method introduces an adaptive entropy weight mechanism, dynamically determines the weight according to the discrete degree of resource indicators and task priority, can scientifically quantify the influence of each indicator on resource allocation, and overcomes the problem that the traditional static weight method cannot adapt to the real-time changing resource demand. Further combine the entropy weight assignment with the greedy algorithm for initial resource allocation, and use the genetic algorithm to perform iterative fitness optimization to achieve efficient resource scheduling and task priority guarantee, and ensure rapid convergence to the optimal allocation plan in a complex and changeable network environment. The combination of dynamic entropy weight and hybrid optimization algorithm breaks through the limitation of local optimality of a single optimization algorithm in resource allocation problems, and has higher resource utilization efficiency and task execution accuracy. Further cooperate with digital twin technology to build a virtual model of network resources, so that the virtual model can be highly mapped with real network resources, so as to reflect the execution effect of the resource allocation plan and the actual performance of the task node in real time, input the current resource allocation plan into the virtual model for simulation, and evaluate the performance indicators such as resource utilization, task completion rate, and network delay in real time, and optimize the parameter settings of the adaptive entropy weight hybrid algorithm based on the simulation result feedback. Among them, by calculating the comprehensive score of each task and allocating resources based on the greedy strategy, resource allocation is made more in line with task priority and actual needs, thereby improving the completion rate and service quality of key tasks. Through iterative optimization of genetic algorithms, the adaptability of resource allocation schemes is further improved, resource waste and task delays are reduced, and accurate matching and efficient scheduling of resources are achieved.

[0084] refer to Figure 2 This embodiment further discloses a management system for Internet resources, including:

[0085] The data processing module 21 is used to receive resource data indicators from the Internet and standardize the resource data indicators to obtain a resource data indicator matrix; it is also used to receive multiple resource data indicators in the Internet environment in real time, the resource data indicators including bandwidth, load, memory usage, storage occupancy, and response delay; standardize the multiple resource data indicators; and convert the standardized resource data indicators into a resource data indicator matrix.

[0086] The entropy weight calculation module 22 is used to calculate the dynamic entropy weight of each resource indicator based on the resource data indicator matrix; it is also used to calculate the entropy value of each resource indicator, and the calculation formula is:

[0087] ,in, For the The resource indicator The probability distribution of samples, is the sample size, is a constant;

[0088] The initial entropy weight of the resource indicator is calculated according to the entropy value. The calculation formula is:

[0089] ,in, For the The initial entropy weight of each resource indicator, is the total number of resource indicators;

[0090] Monitor the changing trend of the network and dynamically calculate the entropy weight of the resource based on the feedback change data. The calculation formula of the dynamic entropy weight is:

[0091] ,in, For the Resource indicators at time The dynamic entropy weight of For the The entropy weight of a resource indicator at the last moment, For the Resource indicators at time The feedback change data, is the maximum feedback value of all resource indicators, is the feedback adjustment coefficient.

[0092] The resource allocation module 23 is used to construct an adaptive entropy weight hybrid optimization algorithm based on the dynamic entropy weight to obtain a resource allocation scheme; and is also used to use a greedy algorithm to perform initial resource allocation based on the dynamic entropy weight;

[0093] Initialize multiple resource allocation schemes;

[0094] Calculate the fitness of each resource allocation scheme using the following formula:

[0095] ,in, For the Resource indicators at time The dynamic entropy weight of For the Resource indicators at time resource requirements;

[0096] The genetic algorithm for resource allocation is iteratively optimized based on the calculated fitness, and the resource allocation plan is finally output.

[0097] The simulation optimization module 24 is used to simulate the resource allocation scheme in real time through digital twin technology and obtain simulation results, and optimize the parameters of the adaptive entropy weight hybrid optimization algorithm based on the simulation results; it is also used to build a virtual model of network resources based on digital twin technology to reflect the use and allocation of resources in real time; based on the current resource allocation scheme, simulate the virtual model; evaluate the performance of the resource allocation scheme through simulation results; and adjust the parameters of the adaptive entropy weight hybrid optimization algorithm according to the simulation results.

[0098] The dynamic allocation module 25 is used to obtain the state prediction of Internet resources and input the state prediction into the optimized adaptive entropy weight hybrid optimization algorithm to dynamically adjust the resource allocation strategy; it is also used to call the time series prediction model to predict the subsequent resource state of Internet resources, and the prediction process is:

[0099] ,in, is the target prediction state, , , …, For the Resource indicators at time , , ..., historical status, For external environment variables, is the time series prediction function;

[0100] The calculated resource status prediction is input into the optimized adaptive entropy weight hybrid optimization algorithm, and combined with the current dynamic entropy weight and current resource requirements Perform dynamic calculations and output resource allocation plans. The calculation formula is:

[0101] ,in, For the Resource indicators at time The amount of resources allocated, For the Resource indicators at time The dynamic entropy weight of For the The resource status prediction value of each resource indicator, For the Resource indicators at time resource requirements;

[0102] Output the resource allocation plan in a collection form, as follows:

[0103] ,in, For the Resource indicators at time The amount of resources allocated, , The total number of resource indicators.

[0104] Figure 3 A schematic diagram of the physical structure of an electronic device provided in an embodiment of the present invention, such as Figure 3 As shown, the electronic device 50 includes: a processor 501 (processor), a memory 502 (memory) and a bus 503;

[0105] The processor 501 and the memory 502 communicate with each other via the bus 503 ; the processor 501 is used to call program instructions in the memory 502 to execute the methods provided by the above-mentioned method implementation methods.

[0106] This embodiment provides a non-transitory computer-readable storage medium, which stores computer instructions. The computer instructions enable a computer to execute the methods provided by the above-mentioned method embodiments.

[0107] A person skilled in the art can understand that all or part of the steps for implementing the above-mentioned method implementation method can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium, which, when executed, executes the steps of the above-mentioned method implementation method; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk, etc., various storage media that can store program codes.

[0108] The device implementation described above is merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, i.e., they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present implementation scheme. Those of ordinary skill in the art may understand and implement it without creative effort.

[0109] Through the description of the above implementation modes, those skilled in the art can clearly understand that each implementation mode can be implemented by means of software plus a necessary general hardware platform, or of course by hardware. Based on such an understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each implementation mode or some parts of the implementation mode.

[0110] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for managing Internet resources, characterized in that: The method comprises: Receiving resource data indicators of the Internet, and performing standardization processing on the resource data indicators to obtain a resource data indicator matrix; Calculating the dynamic entropy weight of each resource indicator based on the resource data indicator matrix includes: calculating the entropy value of each resource indicator, and the calculation formula is: ,in, For the The resource indicator The probability distribution of samples, is the sample size, is a constant; The initial entropy weight of the resource indicator is calculated according to the entropy value. The calculation formula is: ,in, For the The initial entropy weight of each resource indicator, is the total number of resource indicators; Monitor the changing trend of the network and dynamically calculate the entropy weight of the resource based on the feedback change data. The calculation formula of the dynamic entropy weight is: ,in, For the Resource indicators at time The dynamic entropy weight of For the The entropy weight of a resource indicator at the last moment, For the Resource indicators at time The feedback change data, is the maximum feedback value of all resource indicators, is the feedback adjustment coefficient; Constructing an adaptive entropy weight hybrid optimization algorithm based on the dynamic entropy weight to obtain a resource allocation scheme, including: performing initial resource allocation using a greedy algorithm based on the dynamic entropy weight; Initialize multiple resource allocation schemes; Calculate the fitness of each resource allocation scheme using the following formula: ,in, For the Resource indicators at time The dynamic entropy weight of For the Resource indicators at time resource requirements; Iterative optimization of the genetic algorithm for resource allocation based on the calculated fitness, and finally outputting a resource allocation plan; Performing real-time simulation of the resource allocation scheme through digital twin technology and obtaining simulation results, and optimizing parameters of the adaptive entropy weight hybrid optimization algorithm based on the simulation results; The state prediction of Internet resources is obtained, and the state prediction is input into the optimized adaptive entropy weight hybrid optimization algorithm to realize dynamic adjustment of resource allocation strategy.

2. The method for managing Internet resources according to claim 1, characterized in that: The method of receiving resource data indicators of the Internet and performing standardization processing on the resource data indicators to obtain a resource data indicator matrix includes: Receive multiple resource data indicators in the Internet environment in real time, including bandwidth, load, memory usage, storage occupancy, and response delay; Standardize multiple resource data indicators; Convert the standardized resource data indicators into a resource data indicator matrix.

3. The method for managing Internet resources according to claim 1, characterized in that: The method of performing real-time simulation on the resource allocation scheme by digital twin technology and obtaining simulation results, and optimizing the parameters of the adaptive entropy weight hybrid optimization algorithm based on the simulation results includes: Build a virtual model of network resources based on digital twin technology to reflect resource usage and allocation in real time; Based on the current resource allocation scheme, simulating the virtual model; Evaluate the performance of resource allocation schemes through simulation results; The parameters of the adaptive entropy weight hybrid optimization algorithm are adjusted according to the simulation results.

4. The method for managing Internet resources according to claim 1, characterized in that: The method of obtaining a state prediction of Internet resources and inputting the state prediction into the optimized adaptive entropy weight hybrid optimization algorithm to dynamically adjust the resource allocation strategy includes: The time series prediction model is called to predict the subsequent resource status of the Internet resource. The prediction process is as follows: ,in, is the target prediction state, , , …, For the Resource indicators at time , , ..., historical status, For external environment variables, is the time series prediction function; The calculated resource status prediction is input into the optimized adaptive entropy weight hybrid optimization algorithm, and combined with the current dynamic entropy weight and current resource requirements Perform dynamic calculations and output resource allocation plans. The calculation formula is: ,in, For the Resource indicators at time The amount of resources allocated, For the Resource indicators at time The dynamic entropy weight of For the The resource status prediction value of each resource indicator, For the Resource indicators at time resource requirements; Output the resource allocation plan in a collection form, as follows: ,in, For the Resource indicators at time The amount of resources allocated, , The total number of resource indicators.

5. A management system for Internet resources, characterized in that: include: A data processing module, used for receiving resource data indicators of the Internet and performing standardization processing on the resource data indicators to obtain a resource data indicator matrix; The entropy weight calculation module is used to calculate the dynamic entropy weight of each resource indicator based on the resource data indicator matrix, including: calculating the entropy value of each resource indicator, the calculation formula is: ,in, For the The resource indicator The probability distribution of samples, is the sample size, is a constant; The initial entropy weight of the resource indicator is calculated according to the entropy value. The calculation formula is: ,in, For the The initial entropy weight of each resource indicator, is the total number of resource indicators; Monitor the changing trend of the network and dynamically calculate the entropy weight of the resource based on the feedback change data. The calculation formula of the dynamic entropy weight is: ,in, For the Resource indicators at time The dynamic entropy weight of For the The entropy weight of a resource indicator at the last moment, For the Resource indicators at time The feedback change data, is the maximum feedback value of all resource indicators, is the feedback adjustment coefficient; A resource allocation module is used to construct an adaptive entropy weight hybrid optimization algorithm based on the dynamic entropy weight to obtain a resource allocation scheme, including: using a greedy algorithm based on the dynamic entropy weight to perform initial resource allocation; Initialize multiple resource allocation schemes; Calculate the fitness of each resource allocation scheme using the following formula: ,in, For the Resource indicators at time The dynamic entropy weight of For the Resource indicators at time resource requirements; Iterative optimization of the genetic algorithm for resource allocation based on the calculated fitness, and finally outputting a resource allocation plan; A simulation optimization module, used to perform real-time simulation of the resource allocation scheme through digital twin technology and obtain simulation results, and optimize the parameters of the adaptive entropy weight hybrid optimization algorithm based on the simulation results; The dynamic allocation module is used to obtain the state prediction of Internet resources and input the state prediction into the optimized adaptive entropy weight hybrid optimization algorithm to realize dynamic adjustment of resource allocation strategy.

6. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 4 is implemented.

8. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

Images