Network service dynamic optimization method, system and device and storage medium

Abstract

The invention discloses a network service dynamic optimization method, system and device and a storage medium. The method comprises the following steps: acquiring current network state information; determining a service operation level according to the current network state information; the operation level is the use priority of the current service to the network resources; inputting the network state information into an energy consumption prediction model, and determining energy consumption information; if the energy consumption information is larger than a preset energy consumption threshold value, the energy consumption level is adjusted to be the operation level of the high-energy-consumption service. According to the embodiment of the invention, energy consumption prediction is carried out on the service through the network state information, the operation level of the service is adjusted according to the prediction result, dynamic adjustment of network resources is realized, and the operation stability of the system is improved. The method can be widely applied to the technical field of network energy.

Description

Technical Field

[0001] The present invention relates to the field of network energy technology, and in particular to a network service dynamic optimization method, system, device and storage medium. Background Art

[0002] As network usage increases, energy supply becomes unstable. In response, operators will limit network energy usage to ensure continued operation within a limited energy budget. In related technologies, the network system cannot make timely adjustments to the energy usage of each service, resulting in service interruptions and affecting the stable operation of the system. Summary of the invention

[0003] The purpose of the present invention is to solve one of the technical problems existing in the prior art to at least a certain extent.

[0004] To this end, an object of the present invention is to provide an efficient network service dynamic optimization method, system, device and storage medium.

[0005] In order to achieve the above technical objectives, one aspect of an embodiment of the present invention provides a method for dynamic optimization of network services, comprising the following steps: obtaining current network status information; determining the operation level of the service based on the current network status information; the operation level is the priority of the current service for using network resources; inputting the network status information into an energy consumption prediction model to determine energy consumption information; if the energy consumption information is greater than a preset energy consumption threshold, adjusting the operation level of the service with a high energy consumption level. The embodiment of the present application predicts the energy consumption of the service through network status information, adjusts the operation level of the service according to the prediction result, realizes dynamic adjustment of network resources, and is conducive to improving the operational stability of the system.

[0006] In some embodiments, the method for dynamic optimization of network services in an embodiment of the present invention, if the energy consumption information is greater than a preset energy consumption threshold, adjusting the operation level of the service with a high energy consumption level includes:

[0007] If the energy consumption information is greater than a preset energy consumption threshold and the first service is a non-critical service, the operation level of the first service is reduced; the energy consumption level of the first service is high energy consumption;

[0008] The network status information is updated, and the step of inputting the network status information into an energy consumption prediction model to determine energy consumption information is returned.

[0009] In some embodiments, in one embodiment of the present invention, determining the current operating level of each service according to the current network status information includes:

[0010] Determine the response time of each service according to the current network status information, and then determine the operation level;

[0011] Alternatively, according to the current network status information, the availability of each service is determined, and then the operation level is determined;

[0012] Alternatively, the throughput of each current service is determined according to the current network status information, and then the operation level is determined.

[0013] In some embodiments, in one embodiment of the present invention, the energy consumption prediction model is established by the following steps:

[0014] Determine the autoregressive term based on the current network state and the historical network state;

[0015] Determine the difference term based on the stationarity of the time series corresponding to the network state;

[0016] Determine the sliding average item based on the current forecast error and the historical forecast error;

[0017] The energy consumption prediction model is established based on the autoregressive term, the differential term and the sliding average term.

[0018] In some embodiments, in one embodiment of the present invention, the method further comprises:

[0019] Obtain network energy supply and load information;

[0020] Determining the preset energy consumption threshold according to the energy supply and the load information;

[0021] issuing a service warning according to the energy consumption information and the preset energy consumption threshold;

[0022] According to the service warning, the energy consumption prediction model is adjusted.

[0023] In some embodiments, in one embodiment of the present invention, the method further comprises:

[0024] The adjusted operation level of the service is sent to the user equipment, so that the user equipment adjusts the service usage mode according to the operation level.

[0025] In some embodiments, in one embodiment of the present invention, the energy consumption level is determined by the following steps:

[0026] Obtain device operation data and service network operation data;

[0027] determining direct energy consumption based on the operating data;

[0028] determining indirect energy consumption based on the network operation data;

[0029] The energy consumption level is determined according to the direct energy consumption and the indirect energy consumption.

[0030] On the other hand, an embodiment of the present invention provides a network service dynamic optimization system, including:

[0031] The first module is used to obtain current network status information;

[0032] The second module is used to determine the operation level of the service according to the current network status information; the operation level is the priority of the current service for using network resources;

[0033] The third module is used to input the network status information into an energy consumption prediction model to determine energy consumption information;

[0034] The fourth module is used to adjust the operation level of the service with high energy consumption level if the energy consumption information is greater than a preset energy consumption threshold.

[0035] On the other hand, an embodiment of the present invention provides a network service dynamic optimization device, including:

[0036] at least one processor;

[0037] at least one memory for storing at least one program;

[0038] When the at least one program is executed by the at least one processor, the at least one processor implements the above-mentioned network service dynamic optimization method.

[0039] On the other hand, an embodiment of the present invention provides a storage medium, in which a program executable by a processor is stored. When the program executable by the processor is executed by the processor, it is used to implement the above-mentioned network service dynamic optimization method.

[0040] The method provided in the embodiment of the present application includes: obtaining current network status information; determining the operation level of the service according to the current network status information; the operation level is the priority of the current service for using network resources; inputting the network status information into the energy consumption prediction model to determine the energy consumption information; if the energy consumption information is greater than the preset energy consumption threshold, adjusting the operation level of the service with high energy consumption. The embodiment of the present application predicts the energy consumption of the service through the network status information, adjusts the operation level of the service according to the prediction result, realizes the dynamic adjustment of network resources, and is conducive to improving the operation stability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the embodiments of the present invention or the drawings of related technical solutions in the prior art are introduced below. It should be understood that the drawings introduced below are only for the convenience of clearly describing some embodiments of the technical solutions of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0042] Figure 1 A schematic diagram of a flow chart of an embodiment of a method for dynamic optimization of network services provided by the present invention;

[0043] Figure 2 A flowchart of another embodiment of the network service dynamic optimization method provided by the present invention;

[0044] Figure 3 A schematic diagram of the structure of an embodiment of the network service dynamic optimization system provided by the present invention;

[0045] Figure 4 A schematic diagram of the structure of an embodiment of the network service dynamic optimization device provided by the present invention. DETAILED DESCRIPTION

[0046] The embodiments of the present invention are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and are not to be construed as limitations of the present invention. For the step numbers in the following embodiments, they are only provided for the convenience of explanation, and the order between the steps is not limited in any way, and the execution order of each step in the embodiment can be adaptively adjusted according to the understanding of those skilled in the art.

[0047] The relevant nouns involved in this application are:

[0048] User Equipment (UE);

[0049] 5G system (5G System, 5GS).

[0050] As more and more base stations and network equipment are powered by renewable energy such as solar and wind power, energy supply becomes unstable and may sometimes be insufficient or costly. To address this issue, operators limit the energy use of the network to ensure continued operation within a limited energy budget.

[0051] When energy supply is insufficient, the network may reduce the operation of certain services, such as limiting video, data transmission, etc., to save energy and allow key services (such as emergency calls) to run longer. On the contrary, when energy is sufficient, the network can run more services.

[0052] Understandably, network energy management solutions in related technologies lack dynamic adjustment capabilities: many network systems fail to automatically adjust services according to real-time energy supply and demand changes, resulting in energy waste and service interruptions. At the same time, service priority management is inflexible: there is a lack of detailed analysis and management of energy consumption of different services, and the balance between high-energy consumption and critical services cannot be intelligently optimized.

[0053] In this regard, an embodiment of the present application provides a dynamic and intelligent network service management system that can adjust the service operability level in real time, enable user devices to automatically respond to network status, and improve the overall energy efficiency and service reliability of the network through energy consumption prediction and flexible service optimization.

[0054] The following describes in detail a network service dynamic optimization method and system according to an embodiment of the present invention with reference to the accompanying drawings. First, the network service dynamic optimization method according to an embodiment of the present invention will be described with reference to the accompanying drawings.

[0055] Reference Figure 1 In an embodiment of the present invention, a method for dynamic optimization of network services is provided. The method for dynamic optimization of network services in an embodiment of the present invention can be applied to a terminal or a server, or can be software running in a terminal or a server. The terminal can be a tablet computer, a laptop computer, a desktop computer, etc., but is not limited to this. The server can be an independent physical server, or a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The method for dynamic optimization of network services in an embodiment of the present invention mainly includes the following steps:

[0056] S100: Obtain current network status information;

[0057] S200: Determine the operation level of the service according to the current network status information; the operation level is the priority of the current service for using network resources;

[0058] S300: inputting the network status information into an energy consumption prediction model to determine energy consumption information;

[0059] S400: If the energy consumption information is greater than a preset energy consumption threshold, adjust the operation level of the service with a high energy consumption level.

[0060] In some possible implementations, the operation level in the embodiment of the present application may include normal operation, reduced operation, and optimal operation. Among them, normal operation: when network resources are sufficient and energy supply is stable, all services are operated according to the conventional configuration, and users can enjoy a complete service experience. Reduced operation: when the network faces energy shortage or high load pressure, the system automatically switches to the "reduced operation" level. At this level, non-emergency and non-critical services may be temporarily restricted or suspended to release network resources for key functions such as emergency calls. This strategy ensures that emergency services can be continuously and with high quality even when network resources are tight. Optimal operation: when network resources are extremely abundant, energy supply is in excess, or in a specific time period (such as low peak hours at night), the system can be adjusted to the "optimal operation" level. At this time, all services can obtain higher bandwidth, lower latency and other optimized resource allocation, thereby providing users with a better service experience. Of course, the setting of the operation level and the limitation of each operation level can be adjusted according to actual needs, and this application does not make specific limitations. The energy consumption prediction model in the embodiment of the present application can be any artificial intelligence model that can perform predictions, and this application does not limit the specific architecture of the model. It is understandable that the embodiments of the present application classify each service into energy consumption levels according to the use of network resources by the service, and determine high-energy consumption, medium-energy consumption, and low-energy consumption devices. When the energy consumption information is greater than the preset energy consumption threshold, network resources cannot be provided to every demander. Therefore, it is necessary to limit the use of network resources by some services. It should be noted that the above-mentioned energy consumption level classification is an illustrative example. The high energy consumption in the high-energy consumption service in the embodiments of the present application is a relative concept and is not necessarily a specific level. In some embodiments, the operating level of the service can be adjusted according to the energy consumption ranking.

[0061] The embodiments of this application focus on the innovation of 5G network in energy management, and propose a mechanism that can dynamically adjust the operability level of network services according to the real-time energy supply situation. This mechanism automatically optimizes service priority and availability by evaluating network load, service demand and energy status, ensuring that critical services such as emergency calls can still operate stably when energy is limited, and improving the overall service quality when energy is sufficient. User equipment can receive and respond to these level adjustment instructions, and automatically adjust service usage modes to save energy, such as switching to low-energy mode or suspending non-critical tasks. In addition, the application also introduces energy consumption prediction and service warning functions, which plan service levels in advance through prediction algorithms to avoid sudden service interruptions.

[0062] The embodiment of the present application can flexibly switch service modes based on a multi-level operational model, and intuitively display the current level impact on the user device to assist users in reasonable use. By building a correlation model between services and energy consumption, intelligently optimize service configuration, maximize network energy efficiency, and ensure that key services continue to operate reliably in an energy-constrained environment.

[0063] Optionally, in an embodiment of the present invention, if the energy consumption information is greater than a preset energy consumption threshold, adjusting the running level of the service with a high energy consumption level includes:

[0064] If the energy consumption information is greater than a preset energy consumption threshold and the first service is a non-critical service, the operation level of the first service is reduced; the energy consumption level of the first service is high energy consumption;

[0065] The network status information is updated, and the step of inputting the network status information into an energy consumption prediction model to determine energy consumption information is returned.

[0066] In some possible implementations, the operating level of non-critical services with high energy consumption is reduced to alleviate the shortage of network resources. For example, the operating level of high energy consumption services can be reduced in batches, and after each operating level adjustment, the use of network resources is re-evaluated. If the demand can be met, the adjustment of the operating level is stopped.

[0067] It is understandable that if the energy consumption information is much less than the preset energy consumption threshold, the operation level of the service is adjusted. When the energy consumption information is reduced and the network resources are sufficient, the operation level of all services is increased; or the operation level of the second service is increased, and the second service is the service whose operation level was reduced last time.

[0068] A service and energy consumption association model is constructed. The model is responsible for analyzing the energy consumption of different services and intelligently adjusting the service configuration according to the current energy status. This association management not only focuses on the performance and availability of network services, but also on the effective use and sustainability of energy. The model first collects detailed energy consumption data of various services during operation, including direct energy consumption (such as device power consumption) and indirect energy consumption (such as the increase in network load caused by data transmission). Based on this data, the system classifies services and identifies high-energy-consuming services, medium-energy-consuming services, and low-energy-consuming services. At the same time, the energy consumption trend of various services under different loads and configurations is analyzed. When the network enters the "reduced operation" level, the energy management system intelligently selects and disables or restricts those non-critical services with high energy consumption based on the service classification and energy consumption analysis results. In this process, the system will give priority to retaining the operation of critical services such as emergency calls and allocate sufficient network resources to them. In this way, the system can release valuable network resources and energy, ensuring that critical services can operate normally for a long time under resource constraints. The model also has the ability to dynamically adjust service configurations in real time according to changes in network load and energy conditions. For example, after energy supply is restored, the system can automatically restore service to "normal operation" levels to provide a full user experience.

[0069] Optionally, in one embodiment of the present invention, determining the current operating level of each service according to the current network status information includes:

[0070] Determine the response time of each service according to the current network status information, and then determine the operation level;

[0071] Alternatively, according to the current network status information, the availability of each service is determined, and then the operation level is determined;

[0072] Alternatively, the throughput of each current service is determined according to the current network status information, and then the operation level is determined.

[0073] In some possible implementations, the determination of the operating level may be evaluated using a series of key performance indicators (KPIs). For example, the operating level may be determined using at least one of response time, availability, and throughput.

[0074] Optionally, in one embodiment of the present invention, the energy consumption prediction model is established by the following steps:

[0075] Determine the autoregressive term based on the current network state and the historical network state;

[0076] Determine the difference term based on the stationarity of the time series corresponding to the network state;

[0077] Determine the sliding average item based on the current forecast error and the historical forecast error;

[0078] The energy consumption prediction model is established based on the autoregressive term, the differential term and the sliding average term.

[0079] In some possible implementations, the embodiments of the present application provide energy consumption forecasting and service warning. The prediction method used in energy consumption forecasting is a prediction method based on a statistical model. It is a method that uses historical energy consumption data and manually predicts future energy consumption trends through statistical analysis. This method relies on in-depth analysis and modeling of historical data to reveal the inherent laws and trends of energy consumption changes.

[0080] The main steps of energy consumption prediction are:

[0081] S21, Data Collection: Collect historical energy consumption data, including energy consumption records for different time periods (such as day, week, month, year). Ensure the accuracy and completeness of the data, and clean and process abnormal values.

[0082] S22, Data Analysis: Statistical analysis of historical energy consumption data to identify seasonality, periodicity, trend and other characteristics of the data. Analyze key factors that affect energy consumption changes, such as weather, temperature, humidity, holidays, user behavior, etc.

[0083] S23, Model selection: According to the data analysis results, select the ARIMA model for modeling. The ARIMA model is suitable for time series data with seasonality and trend. The ARIMA model has good prediction performance, especially for time series data with linear trends and seasonal changes. Its prediction results are usually more accurate. The ARIMA model consists of three key parts:

[0084] Autoregressive part: captures the historical dependency of the sequence, that is, the relationship between the current value and the historical value.

[0085] Difference part: Dealing with non-stationarity, making the series more suitable for modeling through difference operations. Determining the number of differences (order) d is one of the key steps, which can make the originally non-stationary series become stable.

[0086] Sliding average part: reflects the relationship between the current value and the historical error term, that is, the relationship between the current prediction error and the past prediction errors.

[0087] By properly choosing the values ​​of the autoregressive term, the number of differences, and the number of moving average terms, the ARIMA model can be adapted to different types of time series data.

[0088] S24, Prediction and Evaluation: Use the established model to predict future energy consumption. Verify and evaluate the prediction results, and evaluate the accuracy and reliability of the model by comparing the actual energy consumption data with the predicted data. Make necessary adjustments and optimizations to the model based on the evaluation results to improve the accuracy of the prediction.

[0089] Optionally, in one embodiment of the present invention, the method further includes:

[0090] Obtain network energy supply and load information;

[0091] Determining the preset energy consumption threshold according to the energy supply and the load information;

[0092] issuing a service warning according to the energy consumption information and the preset energy consumption threshold;

[0093] According to the service warning, the energy consumption prediction model is adjusted.

[0094] In some possible implementations, the service warning in the embodiments of the present application uses a real-time monitoring solution to monitor the energy supply and network load in real time to ensure timely detection of energy shortages or overloads. Different energy consumption thresholds are set according to the priority of the network service and the energy supply. When the actual energy consumption approaches or exceeds the threshold, the warning mechanism is triggered.

[0095] Energy consumption forecasting and service warning can promote each other and achieve collaborative optimization. On the one hand, energy consumption forecasting can more accurately understand future energy consumption trends, thereby providing more precise time points and warning levels for service warnings; on the other hand, service warnings can timely discover potential energy use problems or abnormal situations and feed them back to the energy consumption forecasting system so that the forecasting model can be corrected and optimized to improve the accuracy of the forecast.

[0096] Optionally, in one embodiment of the present invention, the method further includes:

[0097] The adjusted operation level of the service is sent to the user equipment, so that the user equipment adjusts the service usage mode according to the operation level.

[0098] Optionally, in one embodiment of the present invention, the energy consumption level is determined by the following steps:

[0099] Obtain device operation data and service network operation data;

[0100] determining direct energy consumption based on the operating data;

[0101] determining indirect energy consumption based on the network operation data;

[0102] The energy consumption level is determined according to the direct energy consumption and the indirect energy consumption.

[0103] Reference Figure 2 As shown, the method provided in the embodiment of the present application is described in detail:

[0104] Prerequisite: 5G network service is operating normally;

[0105] Step S01: The 5G network service obtains data on the current network environment in real time through various monitoring tools (such as traffic analyzers and latency monitoring tools). This includes indicators such as bandwidth usage, latency, packet loss rate, number of connections, and network load. Monitoring tools may also include network probes and performance monitoring software, which can provide comprehensive network health status reports.

[0106] Step S02: Evaluate the operating efficiency of the current service based on the collected data. Usually a series of key performance indicators (KPIs) are used for evaluation, such as response time, availability, throughput, etc. According to different performance indicators, the current service is divided into different service levels, such as "normal operation", "reduced operation", and "optimal operation". By comparing with historical data, it is possible to identify whether the current performance is normal, whether there is a bottleneck or a downward trend.

[0107] Step S03: Use the collected network status data to predict energy consumption. This can be achieved by analyzing the energy consumption characteristics, traffic patterns and load conditions of the current device. Use prediction algorithms or statistical analysis methods to predict the energy consumption level required for network services under different workloads. Factors to consider include device power consumption, traffic changes during business peaks, and increases and decreases in service requests.

[0108] Step S04: Based on the 5G network service energy consumption prediction results and the current 5G network service level, formulate corresponding adjustment methods. For example, if the current service level needs to be reduced from "normal operation" to "reduced operation", the system needs to reduce bandwidth, optimize network routing, delete server instances, etc.

[0109] Step S05: Based on the formulated dynamic level adjustment method, adjust the network configuration to optimize the service level, for example, reduce the service level from "normal operation" to "reduced operation".

[0110] Step S06: The 5G network service sends the modified network service level to the user equipment.

[0111] Step S07: The user equipment receives indications of the network service operability level and automatically adjusts its own service usage mode according to these indications, such as switching to a low energy mode, suspending non-critical tasks or adjusting service priority to adapt to the energy status of the network.

[0112] In summary, the energy consumption prediction and service warning in the embodiment of the present application: using prediction algorithms, etc., to estimate the future energy supply in advance, and adjust the network service operability level based on the prediction results. The user device receives the warning information and adjusts its service usage behavior according to the suggestions, such as reducing the frequency of use of high-energy-consuming applications, thereby avoiding sudden service interruptions.

[0113] Service optimization of the multi-level operability model in the embodiment of the present application: introduce a multi-level service operability model, including "normal operation", "reduced operation" and "optimal operation" levels. The system can flexibly switch service modes according to the actual energy supply and network load conditions, and intuitively display the current operation level and its impact on the service on the user's device to help users make reasonable usage decisions.

[0114] Service and energy consumption association management in the embodiment of the present application: A service and energy consumption association model is constructed to analyze the energy consumption of different services and intelligently optimize service configuration based on the current energy status. The system can ensure the operation of critical and emergency services in the network and improve the overall energy efficiency of the network by disabling or limiting non-critical services with high energy consumption.

[0115] The embodiments of the present application construct a correlation model between services and energy consumption, intelligently optimize service configuration, maximize network energy efficiency, and ensure that key services continue to operate reliably in an energy-constrained environment.

[0116] The embodiment of the present application can be replaced by a neural network training model, which can automatically learn complex nonlinear relationships through large-scale data sets, thereby providing more accurate prediction results. Compared with traditional algorithms, neural networks perform better in processing multidimensional features and can capture subtle patterns and trends. Neural networks have the ability to adaptively learn and can be updated in real time as new data is continuously input. This means that it can quickly adapt to changes in the network environment and maintain the accuracy of predictions, thereby improving the response speed of services. Ability to process big data: Modern network environments generate a large amount of data, and neural networks have significant advantages in processing large-scale data. Its structure can efficiently extract key information and find patterns in massive data, making energy consumption predictions and service warnings more reliable. Multitasking: Neural networks can handle multiple tasks at the same time, such as energy consumption predictions and service fault warnings at the same time. This multitasking learning method not only improves efficiency, but also promotes information sharing between different tasks and improves the intelligence level of the overall system. Reduce maintenance costs: By using neural networks for automated predictions and warnings, manual intervention can be reduced, reducing the complexity and cost of system maintenance. The automated decision-making process makes the system run more smoothly and reduces the possibility of human error.

[0117] In summary, the above method obtains the current network status information; determines the operation level of the service based on the current network status information; the operation level is the priority of the current service for using network resources; inputs the network status information into the energy consumption prediction model to determine the energy consumption information; if the energy consumption information is greater than the preset energy consumption threshold, adjusts the energy consumption level to the operation level of the service with high energy consumption. The embodiment of the present application predicts the energy consumption of the service through the network status information, adjusts the operation level of the service according to the prediction result, realizes the dynamic adjustment of network resources, and is conducive to improving the operational stability of the system.

[0118] Secondly, refer to the attached Figure 3 A network service dynamic optimization system proposed according to an embodiment of the present invention is described.

[0119] Figure 3 1 is a schematic diagram of the structure of a network service dynamic optimization system according to an embodiment of the present invention, wherein the system specifically comprises:

[0120] The first module 310 is used to obtain current network status information;

[0121] The second module 320 is used to determine the operation level of the service according to the current network status information; the operation level is the priority of the current service for using network resources;

[0122] The third module 330 is used to input the network status information into an energy consumption prediction model to determine energy consumption information;

[0123] The fourth module 340 is configured to adjust the operation level of the service with high energy consumption level if the energy consumption information is greater than a preset energy consumption threshold.

[0124] Optionally, in one embodiment of the present invention, the system further includes a fifth module, configured to:

[0125] Determine the autoregressive term based on the current network state and the historical network state;

[0126] Determine the difference term based on the stationarity of the time series corresponding to the network state;

[0127] Determine the sliding average item based on the current forecast error and the historical forecast error;

[0128] The energy consumption prediction model is established based on the autoregressive term, the differential term and the sliding average term.

[0129] Optionally, in one embodiment of the present invention, the system further includes a sixth module, configured to:

[0130] Obtain network energy supply and load information;

[0131] Determining the preset energy consumption threshold according to the energy supply and the load information;

[0132] issuing a service warning according to the energy consumption information and the preset energy consumption threshold;

[0133] According to the service warning, the energy consumption prediction model is adjusted.

[0134] Optionally, in one embodiment of the present invention, the system further includes a seventh module, configured to send the adjusted operating level of the service to a user device, so that the user device adjusts the service usage mode according to the operating level.

[0135] Optionally, in one embodiment of the present invention, the system further includes an eighth module, configured to:

[0136] Obtain device operation data and service network operation data;

[0137] determining direct energy consumption based on the operating data;

[0138] determining indirect energy consumption based on the network operation data;

[0139] The energy consumption level is determined according to the direct energy consumption and the indirect energy consumption.

[0140] It can be seen that the contents of the above method embodiments are all applicable to the present system embodiments, the functions specifically implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0141] Reference Figure 4 The embodiment of the present invention provides a network service dynamic optimization device, including:

[0142] at least one processor 410;

[0143] At least one memory 420, used to store at least one program;

[0144] When the at least one program is executed by the at least one processor 410, the at least one processor 410 implements the network service dynamic optimization method.

[0145] Similarly, the contents of the above method embodiments are all applicable to the present device embodiments. The functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0146] An embodiment of the present invention further provides a computer-readable storage medium, in which a program executable by a processor is stored. When the program executable by the processor is executed by the processor, it is used to execute the above-mentioned network service dynamic optimization method.

[0147] Similarly, the contents of the above method embodiments are all applicable to the present storage medium embodiments. The functions specifically implemented by the present storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0148] In some selectable embodiments, the function / operation mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the function / operation involved, the two boxes shown in succession can actually be executed substantially simultaneously or the boxes can sometimes be executed in reverse order. In addition, the embodiment presented and described in the flow chart of the present invention is provided by way of example, for the purpose of providing a more comprehensive understanding of technology. The disclosed method is not limited to the operation and logic flow presented herein. Selectable embodiments are expected, wherein the order of various operations is changed and the sub-operation of a part for which is described as a larger operation is performed independently.

[0149] In addition, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise specified, one or more of the functions and / or features can be integrated into a single physical device and / or software module, or one or more functions and / or features can be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the present invention. More specifically, in view of the properties, functions and internal relationships of the various functional modules in the device disclosed herein, the actual implementation of the module will be understood within the conventional skills of the engineer. Therefore, those skilled in the art can implement the present invention set forth in the claims without excessive experimentation using ordinary techniques. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.

[0150] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several programs to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0151] The logic and / or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable programs for implementing the logical functions, and may be embodied in any computer-readable medium for use by a program execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch and execute a program from a program execution system, device or apparatus), or in conjunction with such program execution systems, devices or apparatuses. For purposes of this specification, a "computer-readable medium" may be any device that can contain, store, communicate, propagate or transmit a program for use by a program execution system, device or apparatus, or in conjunction with such program execution systems, devices or apparatuses.

[0152] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0153] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable program execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0154] In the above description of this specification, the description with reference to the terms "one embodiment / example", "another embodiment / example" or "certain embodiments / examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0155] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the claims and their equivalents.

[0156] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the embodiments. Those skilled in the art may make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of the present invention.

Claims

1. A network service dynamic optimization method, characterized in that: The following steps are involved: Get current network status information; Determine the operation level of the service according to the current network status information; the operation level is the priority of the current service for using network resources; Inputting the network status information into an energy consumption prediction model to determine energy consumption information; If the energy consumption information is greater than a preset energy consumption threshold, the operation level of the service with a high energy consumption level is adjusted.

2. The method for dynamic optimization of network services according to claim 1, characterized in that: If the energy consumption information is greater than a preset energy consumption threshold, adjusting the operation level of the service with a high energy consumption level includes: If the energy consumption information is greater than a preset energy consumption threshold and the first service is a non-critical service, the operation level of the first service is reduced; the energy consumption level of the first service is high energy consumption; The network status information is updated, and the step of inputting the network status information into an energy consumption prediction model to determine energy consumption information is returned.

3. The method for dynamic optimization of network services according to claim 2, characterized in that: Determining the current operation level of each service according to the current network status information includes: Determine the response time of each service according to the current network status information, and then determine the operation level; Alternatively, the availability of each current service is determined based on the current network status information, and then the operation level is determined; or, the throughput of each current service is determined based on the current network status information, and then the operation level is determined.

4. The method for dynamic optimization of network services according to claim 1, characterized in that: The energy consumption prediction model is established by the following steps: Determine the autoregressive term based on the current network state and the historical network state; Determine the difference term based on the stationarity of the time series corresponding to the network state; Determine the sliding average item based on the current forecast error and the historical forecast error; The energy consumption prediction model is established based on the autoregressive term, the differential term and the sliding average term.

5. The method for dynamic optimization of network services according to claim 1, characterized in that: The method further comprises: Obtain network energy supply and load information; Determining the preset energy consumption threshold according to the energy supply and the load information; issuing a service warning according to the energy consumption information and the preset energy consumption threshold; According to the service warning, the energy consumption prediction model is adjusted.

6. The method for dynamic optimization of network services according to claim 1, characterized in that: The method further comprises: The adjusted operation level of the service is sent to the user equipment, so that the user equipment adjusts the service usage mode according to the operation level.

7. The method for dynamic optimization of network services according to claim 1, characterized in that: The energy consumption level is determined by the following steps: Obtain device operation data and service network operation data; determining direct energy consumption based on the operating data; determining indirect energy consumption based on the network operation data; The energy consumption level is determined according to the direct energy consumption and the indirect energy consumption.

8. A network service dynamic optimization system, characterized in that: include: The first module is used to obtain current network status information; The second module is used to determine the operation level of the service according to the current network status information; The operation level is the priority of the current service for using network resources; The third module is used to input the network status information into an energy consumption prediction model to determine energy consumption information; The fourth module is used to adjust the operation level of the service with high energy consumption level if the energy consumption information is greater than a preset energy consumption threshold.

9. A network service dynamic optimization device, characterized in that: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the network service dynamic optimization method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a program executable by a processor, characterized in that: The processor-executable program is used to implement the network service dynamic optimization method according to any one of claims 1 to 7 when executed by the processor.

Images