Network optimization method and system based on cloud network fusion technology

Abstract

The invention relates to a network optimization method and system based on a cloud network fusion technology, and the method specifically comprises the following steps: 1, resource monitoring: monitoring the use conditions of cloud resources and network resources in a network, and collecting monitoring data; 2, data analysis: preprocessing the collected and monitored data, such as data cleaning and normalization, analyzing the data by using a machine learning algorithm, and identifying bottlenecks and optimization points in the network; step 3, resource scheduling: dynamically adjusting distribution of cloud resources and network resources according to an analysis result, and determining an optimal resource distribution scheme by using an optimization algorithm; step 4, performance evaluation: evaluating the optimized network performance, including bandwidth, delay and packet loss rate indexes, and using a performance evaluation model to evaluate the optimization effect; and step 5, mechanism feedback: feeding back an optimization result to the system to realize continuous network optimization, and adjusting a resource scheduling strategy according to a feedback result to further improve the network performance.

Description

Technical Field

[0001] The present invention relates to the field of cloud-network fusion technology, and in particular to a network optimization method and system based on cloud-network fusion technology. Background Art

[0002] With the rapid development of Internet technology, the integration of cloud computing and network services (cloud-network integration) has become an important direction for improving network performance and user experience, and cloud-network integration has become an important trend in the development of current network architecture.

[0003] Existing network optimization methods often rely on single cloud computing resources or network resources, making it difficult to achieve optimal resource configuration and dynamic adjustment. The lack of effective resource monitoring and dynamic adjustment mechanisms leads to low resource utilization, unstable network performance, and affects the quality and efficiency of network services. In addition, in a cloud-network converged environment, the dynamic allocation and management of network resources still face many challenges. Traditional static network resource allocation methods cannot meet the needs of network resource flexibility and efficiency in a cloud computing environment. Summary of the invention

[0004] In view of the shortcomings of the prior art, the purpose of the present invention is to provide a network optimization method and system based on cloud-network fusion technology, which realizes dynamic allocation and optimization of network resources by real-time monitoring of network resource usage and combining advanced machine learning algorithms, thereby improving the utilization rate of network resources and the overall performance of the system.

[0005] The above-mentioned object of the present invention is achieved through the following technical solutions: A network optimization method based on cloud-network fusion technology comprises the following steps: Step 1: Resource monitoring: monitoring the usage of cloud resources and network resources in the network and collecting monitoring data; Step 2: Data analysis: pre-process the collected and monitored data, such as data cleaning and normalization, and then use machine learning algorithms to analyze the data to identify bottlenecks and optimization points in the network; Step 3: Resource scheduling: dynamically adjust the allocation of cloud resources and network resources based on the analysis results, and use optimization algorithms to determine the optimal resource allocation plan; Step 4: Performance evaluation: evaluate the performance of the optimized network, including bandwidth, delay, and packet loss rate indicators, and use the performance evaluation model to evaluate the optimization effect; Step 5: Mechanism feedback: Feedback the optimization results to the system to achieve continuous network optimization and adjust the resource scheduling strategy according to the feedback results to further improve network performance.

[0006] As a further technical solution of the present invention: in step 1, a Nagios or Zabbix network monitoring tool is used to monitor the usage of cloud resources and network resources, and data is regularly collected and stored in a database.

[0007] As a further technical solution of the present invention: in step 2, use Python data analysis tools to perform data preprocessing, and use Scikit-learn or TensorFlow machine learning library to perform data analysis.

[0008] As a further technical solution of the present invention: in step 3, a genetic algorithm or a particle swarm optimization algorithm is used to determine the optimal resource allocation scheme, the resource allocation scheme is applied to the actual network, and the optimization effect is monitored.

[0009] As a further technical solution of the present invention: in step 4, the optimized network performance is evaluated using NS3 or OMNeT++ network simulation tools, and the optimization effect is verified through actual tests using iperf and ping.

[0010] A network optimization system based on cloud-network integration technology, comprising: Resource monitoring module, used to monitor cloud resources and network resources in the network; Data analysis module, used to analyze the monitored data; Resource scheduling module, used to dynamically adjust resource allocation based on analysis results; Performance evaluation module, used to evaluate the performance of the optimized network; Feedback module, used to feed back the optimization results to the system.

[0011] As a further technical solution of the present invention: the resource monitoring module includes a cloud resource monitoring submodule and a network resource monitoring submodule; The cloud resource monitoring submodule uses the API provided by the cloud platform to obtain usage data of computing resources, storage resources, and bandwidth resources; The network resource monitoring submodule uses a network monitoring tool to collect network bandwidth, delay and packet loss rate performance data.

[0012] As a further technical solution of the present invention: the data analysis module includes a data preprocessing submodule and a machine learning analysis submodule; The data preprocessing submodule: uses the Pandas library to perform cleaning, denoising, and normalization preprocessing operations on the collected data; The machine learning analysis submodule uses the decision tree and support vector machine algorithms of the Scikit-learn library to analyze data and identify performance bottlenecks.

[0013] As a further technical solution of the present invention: the resource scheduling module includes a resource allocation submodule and an optimization algorithm submodule; The resource allocation submodule: dynamically adjusts resource allocation using the cloud platform API based on data analysis results; The optimization algorithm submodule uses the DEAP library to implement genetic algorithms and particle swarm optimization algorithms to determine the optimal resource allocation solution.

[0014] As a further technical solution of the present invention: the performance evaluation module includes a performance evaluation submodule and a performance evaluation model submodule, and the feedback module includes a feedback submodule and a strategy adjustment submodule; The performance evaluation submodule: uses Iperf and Ping tools to perform real-time performance testing; The performance evaluation model submodule: uses NS3 or OMNeT++ to perform network simulation and evaluate the optimization effect; The feedback submodule feeds back the optimization results to the system to achieve continuous network optimization; The policy adjustment submodule: dynamically adjusts the resource scheduling policy using a rule engine or a machine learning model according to the feedback results.

[0015] In summary, the present invention includes at least one of the following beneficial technical effects: The present invention discloses a network optimization method and system based on cloud-network fusion technology, which can accurately grasp the actual use of network resources through real-time monitoring and data analysis, and dynamically allocate according to demand, thereby improving the utilization rate of network resources. By optimizing the allocation and scheduling strategy of network resources, it is possible to reduce network delays, improve key performance indicators such as data transmission rate, and thus improve the overall performance of the system. The technical solution of the present invention has adaptive adjustment capabilities, and can be adjusted and optimized according to real-time changes in network environment and user needs to ensure that the system always remains in the best performance state. Through reasonable network resource allocation and management strategies, unnecessary resource waste and operating cost expenditures can be reduced. In summary, through resource monitoring, data analysis, resource scheduling, performance evaluation and feedback mechanisms, it realizes dynamic optimization of network resources and improves the quality and efficiency of network services. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 The figure is a simplified flow chart of the method of the present invention.

[0017] Figure 2 It is a structural diagram of the system of the present invention. DETAILED DESCRIPTION

[0018] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application; obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments, and all other embodiments obtained by ordinary technicians in this field based on the embodiments in the present application without making creative work are within the scope of protection of the present application.

[0019] In the description of the present application, it should be noted that the terms "upper", "lower", "inner", "outer", "top / bottom" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific position, be constructed and operated in a specific position, and therefore cannot be understood as limiting the present application. In addition, the terms "first" and "second" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0020] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "provided with", "set / connected", "connected", etc. should be understood in a broad sense. For example, "connected" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0021] Embodiment 1: Reference Figure 1 , is a network optimization method based on cloud-network fusion technology disclosed in the present invention, comprising the following steps: Step 1: Resource monitoring: monitoring the usage of cloud resources and network resources in the network and collecting monitoring data; Step 2: Data analysis: pre-process the collected and monitored data, such as data cleaning and normalization, and then use machine learning algorithms to analyze the data to identify bottlenecks and optimization points in the network; Step 3: Resource scheduling: dynamically adjust the allocation of cloud resources and network resources based on the analysis results, and use optimization algorithms to determine the optimal resource allocation plan; Step 4: Performance evaluation: evaluate the performance of the optimized network, including bandwidth, delay, and packet loss rate indicators, and use the performance evaluation model to evaluate the optimization effect; Step 5: Mechanism feedback: Feedback the optimization results to the system to achieve continuous network optimization and adjust the resource scheduling strategy according to the feedback results to further improve network performance.

[0022] In step 1, use Nagios or Zabbix network monitoring tools to monitor the usage of cloud resources and network resources, and regularly collect data and store it in the database. In step 2, use Python data analysis tools to preprocess the data, and use Scikit-learn or TensorFlow machine learning libraries for data analysis.

[0023] In step 3, use genetic algorithm or particle swarm optimization algorithm to determine the optimal resource allocation scheme, apply the resource allocation scheme to the actual network, and monitor the optimization effect. In step 4, use NS3 or OMNeT++ network simulation tools to evaluate the performance of the optimized network, and verify the optimization effect through actual iperf and ping tests.

[0024] Embodiment 2: Reference Figure 2 , a network optimization system based on cloud-network fusion technology, comprising: Resource monitoring module, used to monitor cloud resources and network resources in the network; Data analysis module, used to analyze the monitored data; Resource scheduling module, used to dynamically adjust resource allocation based on analysis results; Performance evaluation module, used to evaluate the performance of the optimized network; Feedback module, used to feed back the optimization results to the system.

[0025] The resource monitoring module includes a cloud resource monitoring submodule and a network resource monitoring submodule; the cloud resource monitoring submodule: uses the API provided by the cloud platform to obtain the usage data of computing resources, storage resources and bandwidth resources; the network resource monitoring submodule: uses network monitoring tools to collect network bandwidth, delay and packet loss performance data. The resource monitoring module is responsible for real-time monitoring of the resource usage of each network node in the cloud-network fusion environment, including key indicators such as bandwidth utilization, data transmission rate, and network delay. At the same time, it collects other data related to network performance, such as user behavior data, application layer data, etc., to provide data support for subsequent network resource optimization.

[0026] The resource monitoring module is equipped with an intelligent collaborative caching mechanism, which uses the characteristics of cloud-network integration to deploy an intelligent caching system at the edge nodes of the network. By analyzing user access patterns and content popularity, popular content is dynamically cached to edge nodes to reduce user access delays. Intelligent updates and synchronization of cached content are achieved to ensure that users can always obtain the latest and most relevant content. The resource monitoring module combines the flexibility of cloud computing and the diversity of the network to design a multi-path transmission strategy. According to the real-time status of the network, it dynamically selects the optimal transmission path to avoid network congestion and single point failures, and uses data segmentation and parallel transmission technology to improve the efficiency and reliability of data transmission.

[0027] The intelligent collaborative caching mechanism is an advanced strategy based on cloud-network integration technology. Its working principle can be summarized into the following key steps: Intelligent perception and prediction: The system first collects information such as user access patterns, content popularity, and network status through intelligent perception technology. Using this data, combined with advanced prediction algorithms, the system can predict possible high-visit content in the future.

[0028] Collaborative caching decisions: Based on the prediction results, the intelligent collaborative caching mechanism makes caching decisions at the edge nodes of the network (such as base stations, servers close to users, etc.). These decisions ensure that popular and upcoming popular content is pre-cached closer to the user.

[0029] Dynamic content updates: Cache content is not static, but is dynamically updated based on changes in user demand and content popularity. Outdated or no longer popular content is replaced by new content to maintain cache efficiency.

[0030] User request processing: When a user initiates a content request, the system first checks whether the requested content has been cached in the edge node. If so, the content is directly provided from the edge node, which greatly reduces the user access delay.

[0031] Cache collaboration and consistency: Cache collaboration is achieved between multiple edge nodes to ensure the consistency and efficient use of content. If the content of a node is updated or replaced, other related nodes will also be notified and updated accordingly.

[0032] In this way, the intelligent collaborative caching mechanism can significantly reduce user access latency. Because the content is pre-cached at the edge node closer to the user, the user does not need to wait to get the content from the remote server. This not only improves the user experience, but also reduces the transmission pressure of the core network, optimizing the overall network performance.

[0033] The resource monitoring module is based on the cloud-network converged architecture to realize the virtualization and slice management of network resources. It dynamically creates and adjusts network slices according to the needs and service quality requirements of different businesses, ensuring that each slice has independent resources and management strategies to meet the performance requirements of specific businesses.

[0034] In the adaptive network optimization system of cloud-network fusion technology, the resource monitoring module is the "sensing organ" of the entire system. It penetrates into every corner of the network architecture and continuously captures changes in network status through highly sensitive detectors. These detectors are like "tentacles" distributed on network nodes, which can capture key performance indicators such as bandwidth utilization, data transmission rate, and network latency in real time. This module is not only limited to collecting data at the network layer, but also actively extends its "sensing range" to include multiple data such as the application layer and user behavior. This enables the system to have a more comprehensive understanding of the network operation status and provide rich materials for subsequent data analysis and demand forecasting.

[0035] The collected data is quickly gathered to the central processing unit through efficient data transmission channels. Here, the data is cleaned, integrated and preliminarily analyzed, and converted into valuable information, laying a solid foundation for the subsequent network optimization work. The whole process is highly automated, ensuring the real-time and accuracy of the data, providing strong data support for adaptive network optimization.

[0036] The data analysis module includes a data preprocessing submodule and a machine learning analysis submodule; Data preprocessing submodule: Use the Pandas library to clean, denoise, and normalize the collected data; Machine learning analysis submodule: Use the decision tree and support vector machine algorithms of the Scikit-learn library to analyze data and identify performance bottlenecks. The data analysis module uses the collected data to perform data analysis and demand forecasting through advanced machine learning algorithms. First, train and learn historical data to establish a model between network resource usage and influencing factors; then, based on the model, predict network resource demand in the future to provide a decision basis for subsequent resource allocation.

[0037] The data analysis module uses advanced artificial intelligence technology to conduct in-depth analysis of the collected network data to discover hidden patterns and trends. Through machine learning algorithms, the module can predict future network traffic and performance requirements, so as to make optimization decisions in advance. Combined with business logic and rule engines, it intelligently generates network optimization suggestions and automatically or semi-automatically adjusts network resource configuration. The data analysis module uses artificial intelligence technology to continuously monitor the network status and diagnose faults. Once a network anomaly or fault is found, the self-healing mechanism is automatically triggered for rapid fault location and recovery. Through continuous learning and optimization, the accuracy and efficiency of network self-healing are improved.

[0038] When accurately predicting future network resource demand through data analysis and demand forecasting modules, the following innovative strategies and methods are combined: Time series analysis and trend prediction: Use historical data to build a time series model to analyze the seasonal and cyclical changes in network traffic. Use algorithms such as ARIMA and LSTM to capture and predict long-term trends and short-term fluctuations. User behavior pattern mining: Analyze users' network usage habits, such as access time, access frequency, data consumption, etc. Apply clustering algorithms to group users and identify network demand characteristics of different user groups.

[0039] Fusion of machine learning and prediction models: Combine multiple machine learning algorithms (such as linear regression, random forest, neural network, etc.) to build prediction models. Use model fusion technologies (such as stacking and blending) to improve the accuracy and stability of predictions. Real-time data stream processing and dynamic adjustment: Use stream processing technology to process and analyze network data streams in real time. Dynamically adjust prediction model parameters based on real-time data feedback to adapt to changes in the network environment.

[0040] Introduce external influencing factors: Consider the impact of holidays and special events (such as large-scale events and promotions) on network demand. Use crawler technology to obtain external data sources such as social media and news websites, and analyze the impact of public sentiment and points of interest on network demand. Interactive prediction and decision support: Build an interactive prediction platform to allow network administrators to adjust prediction parameters according to actual conditions. Combine expert systems and decision trees to provide decision recommendations based on prediction results for network optimization. Continuous learning and model optimization: Use online learning technology to enable prediction models to continuously learn new data. Regularly evaluate model performance and use automated tools to tune and iterate models.

[0041] Through these innovative methods, the data analysis and demand forecasting module can more accurately predict future network resource requirements and provide strong support for adaptive network optimization in a cloud-network converged environment.

[0042] The resource scheduling module includes a resource allocation submodule and an optimization algorithm submodule; the resource allocation submodule: uses the cloud platform API to dynamically adjust resource allocation based on data analysis results; the optimization algorithm submodule: uses the DEAP library to implement genetic algorithms and particle swarm optimization algorithms to determine the optimal resource allocation plan. The resource scheduling module is responsible for formulating and executing dynamic resource allocation strategies based on the results of data analysis and demand forecasting. By adjusting the resource quotas of network nodes and optimizing network traffic scheduling, on-demand allocation and efficient utilization of network resources can be achieved. At the same time, the module also has adaptive adjustment capabilities, and can dynamically adjust resource allocation strategies based on real-time changes in network load and user needs to ensure that the system always maintains optimal performance.

[0043] Resource Scheduling Module Based on the output of the Intelligent Analysis and Decision-making Module, the Dynamic Resource Allocation Module can adjust the allocation of network resources in real time. For example, it can automatically adjust bandwidth allocation, server load balancing, cache strategy, etc. to ensure that network performance is always in the best state. Through close integration with the cloud computing platform, resources can be quickly expanded and contracted to cope with sudden traffic peaks or valleys.

[0044] When making real-time adjustments, the resource scheduling module can closely integrate the network environment and user needs and adopt the following innovative strategies: Network environment perception and adaptive adjustment: Real-time monitoring technology is used to continuously collect network status data, such as bandwidth utilization, transmission delay, and packet loss rate. Through data analysis, abnormal situations such as network congestion and performance degradation are identified, and adaptive adjustment mechanisms are triggered. For example, when the network is congested, the module can automatically adjust the resource allocation strategy to prioritize the transmission quality of key services.

[0045] User demand prediction and personalized services: Analyze user historical data and behavior patterns to predict network resource demand in the future. Combine user preferences and service quality requirements to provide users with personalized resource allocation solutions. For example, for users with high bandwidth requirements, the module can dynamically increase the amount of resources allocated to them to ensure a smooth network experience.

[0046] Resource pooling and elastic scaling: Build a resource pool to centrally manage and schedule computing, storage, and network resources. Rapid scaling and flexible allocation of resources can be achieved based on changes in the network environment and user needs. For example, during peak demand periods, the module can automatically allocate more resources from the resource pool to meet users' immediate needs.

[0047] Intelligent algorithms and decision support: Use intelligent algorithms such as machine learning and deep learning to accurately predict network environments and user needs. Combine business rules and optimization goals to generate intelligent resource allocation and adjustment decisions. Through simulation and actual verification, continuously optimize algorithm models and decision-making effects to improve resource utilization efficiency and user satisfaction.

[0048] In summary, the resource scheduling module can realize dynamic adjustment and optimal configuration of network resources by real-time perception of network environment and user needs, combined with intelligent algorithms and personalized service strategies, thereby improving network performance and user experience.

[0049] The performance evaluation module includes a performance evaluation submodule and a performance evaluation model submodule, and the feedback module includes a feedback submodule and a policy adjustment submodule; the performance evaluation submodule: uses Iperf and Ping tools for real-time performance testing; the performance evaluation model submodule: uses NS3 or OMNeT++ for network simulation to evaluate the optimization effect; the feedback submodule: feeds back the optimization results to the system to achieve continuous network optimization; the policy adjustment submodule: uses a rule engine or a machine learning model to dynamically adjust the resource scheduling strategy based on the feedback results. The performance evaluation module and the feedback module continuously collect performance data and user feedback during system operation by establishing a real-time feedback mechanism. Based on this information, the network resource optimization method is continuously improved and optimized to adapt to the ever-changing network environment and user needs.

[0050] The implementation principle of the present invention is as follows: The present invention discloses a network optimization method and system based on cloud-network fusion technology, which can accurately grasp the actual use of network resources through real-time monitoring and data analysis, and dynamically allocate according to demand, thereby improving the utilization rate of network resources. By optimizing the allocation and scheduling strategy of network resources, it is possible to reduce network delays, improve key performance indicators such as data transmission rate, and thus improve the overall performance of the system. The technical solution of the present invention has adaptive adjustment capabilities, and can be adjusted and optimized according to real-time changes in network environment and user needs to ensure that the system always remains in the best performance state. Through reasonable network resource allocation and management strategies, unnecessary resource waste and operating cost expenditures can be reduced. In summary, through resource monitoring, data analysis, resource scheduling, performance evaluation and feedback mechanisms, it realizes the dynamic optimization of network resources and improves the quality and efficiency of network services.

[0051] The embodiments of this specific implementation method are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A network optimization method based on cloud-network fusion technology, characterized in that: The following steps are involved: Step 1: Resource monitoring: monitoring the usage of cloud resources and network resources in the network and collecting monitoring data; Step 2: Data analysis: pre-process the collected and monitored data, such as data cleaning and normalization, and then use machine learning algorithms to analyze the data to identify bottlenecks and optimization points in the network; Step 3: Resource scheduling: dynamically adjust the allocation of cloud resources and network resources based on the analysis results, and use optimization algorithms to determine the optimal resource allocation plan; Step 4: Performance evaluation: evaluate the performance of the optimized network, including bandwidth, delay, and packet loss rate indicators, and use the performance evaluation model to evaluate the optimization effect; Step 5: Feedback mechanism: Feedback the optimization results to the system to achieve continuous network optimization. Adjust the resource scheduling strategy according to the feedback results to further improve network performance. In step 1, use Nagios or Zabbix network monitoring tools to monitor the usage of cloud resources and network resources, and regularly collect data and store it in a database; In step 2, data preprocessing is performed using Python data analysis tools, and data analysis is performed using Scikit-learn or TensorFlow machine learning libraries; In step 3, a genetic algorithm or a particle swarm optimization algorithm is used to determine an optimal resource allocation scheme, the resource allocation scheme is applied to the actual network, and the optimization effect is monitored; In step 4, the optimized network performance is evaluated using NS3 or OMNeT++ network simulation tools, and the optimization effect is verified through actual tests using iperf and ping.

2. A network optimization system based on cloud-network fusion technology, characterized in that: include: Resource monitoring module, used to monitor cloud resources and network resources in the network; Data analysis module, used to analyze the monitored data; Resource scheduling module, used to dynamically adjust resource allocation based on analysis results; Performance evaluation module, used to evaluate the performance of the optimized network; Feedback module, used to feed back the optimization results to the system.

3. A network optimization system based on cloud-network integration technology according to claim 2, characterized in that: The resource monitoring module includes a cloud resource monitoring submodule and a network resource monitoring submodule; The cloud resource monitoring submodule uses the API provided by the cloud platform to obtain usage data of computing resources, storage resources, and bandwidth resources; The network resource monitoring submodule uses a network monitoring tool to collect network bandwidth, delay and packet loss rate performance data.

4. A network optimization system based on cloud-network integration technology according to claim 2, characterized in that: The data analysis module includes a data preprocessing submodule and a machine learning analysis submodule; The data preprocessing submodule: uses the Pandas library to perform cleaning, denoising, and normalization preprocessing operations on the collected data; The machine learning analysis submodule uses the decision tree and support vector machine algorithms of the Scikit-learn library to analyze data and identify performance bottlenecks.

5. The network optimization system based on cloud-network integration technology according to claim 2 is characterized in that: The resource scheduling module includes a resource allocation submodule and an optimization algorithm submodule; The resource allocation submodule: dynamically adjusts resource allocation using the cloud platform API based on data analysis results; The optimization algorithm submodule uses the DEAP library to implement genetic algorithms and particle swarm optimization algorithms to determine the optimal resource allocation solution.

6. A network optimization system based on cloud-network integration technology according to claim 2, characterized in that: The performance evaluation module includes a performance evaluation submodule and a performance evaluation model submodule, and the feedback module includes a feedback submodule and a strategy adjustment submodule; The performance evaluation submodule: uses Iperf and Ping tools to perform real-time performance testing; The performance evaluation model submodule: uses NS3 or OMNeT++ to perform network simulation and evaluate the optimization effect; The feedback submodule feeds back the optimization results to the system to achieve continuous network optimization; The policy adjustment submodule: dynamically adjusts the resource scheduling policy using a rule engine or a machine learning model according to the feedback results.

Images