Energy-saving and emission-reducing method and device based on network service and energy integration

Abstract

The present disclosure relates to an energy saving and emission reduction method and device based on network service and energy fusion, the method comprising: obtaining historical data of infrastructure, the infrastructure comprising network devices, refrigeration devices and power systems; training a preset model through the historical data to obtain a network service and energy fusion model; obtaining real-time data of the network devices and inputting the real-time data into the network service and energy fusion model to obtain a quantization matrix of network service and energy fusion; wherein the quantization matrix represents the corresponding relationship between different ports in the network devices and different dimension information; determining an energy saving and emission reduction strategy for the infrastructure based on the quantization matrix. Since the quantization matrix represents the corresponding relationship between different ports in the network devices and different dimension information, the energy saving and emission reduction strategy for the infrastructure can be accurately determined, avoiding possible service failures and other problems that may occur when performing shutdown and other operations on related ports in the network devices.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of artificial intelligence, and in particular, to an energy saving and emission reduction method and device based on network service and energy fusion. BACKGROUND

[0002] Network infrastructure power consumption is the main reason for energy consumption in the communication industry and the main reason for carbon emissions in the industry. By predicting the power consumption and traffic trend of the controlled area, the device port in different time periods is executed to stop and other operations to achieve the effect of energy saving and emission reduction.

[0003] In the related art, the shutdown operation generally switches user requests to the remaining available links after closing a certain physical or logical access, which may cause business failure and other problems caused by unsuccessful switching of primary and backup links. SUMMARY

[0004] The present disclosure provides an energy saving and emission reduction method and device based on network service and energy fusion.

[0005] According to a first aspect of the present disclosure, an energy saving and emission reduction method based on network service is provided, the method comprising:

[0006] obtaining historical data of infrastructure, the infrastructure comprising network devices, refrigeration devices and power systems;

[0007] training a preset model through the historical data to obtain a network service and energy fusion model;

[0008] obtaining real-time data of the network devices and inputting the real-time data into the network service and energy fusion model to obtain a network service and energy fusion quantization matrix; wherein the quantization matrix represents the corresponding relationship between different ports in the network devices and different dimension information;

[0009] determining an energy saving and emission reduction strategy for the infrastructure based on the quantization matrix.

[0010] According to a second aspect of the present disclosure, an energy saving and emission reduction device based on network service and energy fusion is provided, the device comprising:

[0011] a data acquisition module configured to obtain historical data of infrastructure, the infrastructure comprising network devices, refrigeration devices and power systems;

[0012] a training module configured to train a preset model through the historical data to obtain a network service and energy fusion model;

[0013] a quantization matrix obtaining module, configured to obtain real-time data of the network device, and input the real-time data into the network service and energy fusion model to obtain a quantization matrix of network service and energy fusion; wherein the quantization matrix represents a corresponding relationship between different ports and different dimension information in the network device;

[0014] a strategy determining module, configured to determine an energy saving and emission reduction strategy for the infrastructure based on the quantization matrix.

[0015] According to a third aspect of the present disclosure, an electronic device is provided. The electronic device comprises a memory and a processor, the memory having stored thereon a computer program, the processor implementing the method as described above when executing the program.

[0016] According to a fourth aspect of the present disclosure, a computer readable storage medium is provided, having stored thereon a computer program, the program being executed by a processor to implement the method as described above.

[0017] According to a fifth aspect of the present disclosure, a computer program product is provided, comprising a computer program, the computer program being executed by a processor to implement the method as described above.

[0018] The method and device for energy saving and emission reduction based on network service and energy fusion provided by the embodiments of the present disclosure obtain historical data of the infrastructure, train a preset model through the historical data, and obtain a network service and energy fusion model. Real-time data of the network device is obtained, and the real-time data is input into the network service and energy fusion model to obtain a quantization matrix of network service and energy fusion. Thus, an energy saving and emission reduction strategy for the infrastructure can be determined based on the quantization matrix. Since the quantization matrix represents a corresponding relationship between different ports and different dimension information in the network device, the energy saving and emission reduction strategy for the infrastructure can be accurately determined, and problems such as service failure that may occur when performing operations such as shutdown on related ports in the network device can be avoided. BRIEF DESCRIPTION OF DRAWINGS

[0019] In the following description of exemplary embodiments in conjunction with the accompanying drawings, more details, features and advantages of the present disclosure are disclosed, in which:

[0020] Figure 1 a schematic diagram of energy consumption root causes in the communication industry provided by an exemplary embodiment of the present disclosure;

[0021] Figure 2 a schematic diagram of overall architecture design for energy saving and emission reduction based on network service and energy fusion provided by an exemplary embodiment of the present disclosure;

[0022] Figure 3A network service and energy integration energy saving and emission reduction process design schematic diagram provided for an exemplary embodiment of the present disclosure;

[0023] Figure 4 A data analysis schematic diagram provided for an exemplary embodiment of the present disclosure;

[0024] Figure 5 A scenario-based energy saving strategy driving and process design schematic diagram provided for an exemplary embodiment of the present disclosure;

[0025] Figure 6 An energy saving strategy feasibility determination architecture design schematic diagram provided for an exemplary embodiment of the present disclosure;

[0026] Figure 7 A flowchart of a network service and energy integration energy saving and emission reduction method provided for an exemplary embodiment of the present disclosure;

[0027] Figure 8 A functional module schematic block diagram of a network service and energy integration energy saving and emission reduction device provided for an exemplary embodiment of the present disclosure;

[0028] Figure 9 A structural block diagram of an electronic device provided for an exemplary embodiment of the present disclosure;

[0029] Figure 10 A structural block diagram of a computer system provided for an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0030] Embodiments of the present disclosure will be described in more detail by referring to the attached drawings. Although certain embodiments of the present disclosure are shown in the drawings, it is understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein, but rather the embodiments are provided to more thoroughly and completely understand the present disclosure. It is understood that the drawings and embodiments of the present disclosure are for exemplary purposes only and are not intended to limit the scope of protection of the present disclosure.

[0031] It is understood that each step recited in the method embodiments of the present disclosure can be executed in different orders and / or in parallel. In addition, the method embodiments can include additional steps and / or omit the execution of the steps shown. The scope of the present disclosure is not limited in this respect.

[0032] The term "include" and variations thereof, as used in this document, mean "to include, without limitation." The term "based on" means "based at least in part on." The term "one embodiment" means "at least one embodiment." The term "another embodiment" means "at least one additional embodiment." The term "some embodiments" means "at least some embodiments." Related terms shall be construed accordingly. It should be noted that "a" or "an" entity as used in this document refers to one or more than one entity. The terms "first," "second," and the like as used in this document do not imply a quantity of or order for the entities so described, but instead are used to distinguish different entities.

[0033] It should be noted that the terms "one" and "a" or "an" as used in this document refer to "one or more" or "at least one," unless the context clearly indicates otherwise. Furthermore, the terms "coupled" and "connected" and variations thereof, as used in this document, mean "connected," although the use of the terms can also include "coupled," unless the context clearly indicates otherwise. As used in this document, the term "exemplary" means "an example of."

[0034] The names of the messages or information exchanged between the plurality of devices in the embodiments of the present disclosure are only for illustrative purposes, and are not intended to limit the scope of the messages or information.

[0035] It can be understood that, before using the technical solutions disclosed in the embodiments of the present disclosure, the type of personal information involved in the present disclosure, the use range, the use scenario, etc. should be informed to the user and the authorization of the user should be obtained through appropriate means according to relevant laws and regulations.

[0036] For example, in response to receiving an active request of a user, a prompt information is sent to the user to explicitly prompt the user that the operation requested to be performed will require obtaining and using personal information of the user. Thus, the user can voluntarily choose whether to provide personal information to the software or hardware such as an electronic device, an application program, a server or a storage medium, etc. performing the operation of the technical solutions of the present disclosure according to the prompt information.

[0037] As an optional but non-limiting implementation manner, in response to receiving an active request of a user, the manner of sending a prompt information to the user may, for example, be a pop-up window manner, and the prompt information may, for example, be presented in the form of text in the pop-up window. In addition, the pop-up window may, for example, carry a selection control for the user to select "agree" or "disagree" to provide personal information to the electronic device. It can be understood that the above notification and obtaining of user authorization process is only illustrative, and does not limit the implementation manners of the present disclosure, and other manners meeting relevant laws and regulations can also be applied to the implementation manners of the present disclosure.

[0038] In related technologies, power consumption and traffic trends in the controlled area are typically predicted, enabling the shutdown, hibernation, or service scheduling of physical facilities such as equipment or ports at different times. Simultaneously, based on temperature predictions for different time periods, operating parameters of the cooling system, such as frequency or temperature control, are adjusted to reduce the power consumption of the cooling system (i.e., terminal air conditioning). Ultimately, by shutting down the infrastructure in the controlled area and adjusting the operating parameters of the cooling equipment, the energy consumption of communication infrastructure is reduced.

[0039] Communication networks are fundamental to people's livelihoods and ensure emergency communication. Therefore, shutdown operations generally do not completely cut off user access, but rather disable a physical or logical access point and switch user requests to other available links. However, this operation carries certain risks, such as failures due to unsuccessful primary / backup link switching without immediate problem identification, service quality degradation due to inability to assess service quality after switching, and even the inability to remotely restart equipment after shutdown. Specifically, the relevant technologies have the following problems:

[0040] (1) Poor availability: In production networks, related technologies can usually only be applied to remote areas, networks with fewer users or fixed usage times. This is because existing prediction methods treat power consumption, traffic and temperature as linear regressions with certain trend attributes, but real networks have strong interconnected characteristics and many internal and external influencing factors, so related technologies cannot be applied to network areas with high loads.

[0041] (2) The network cannot coordinate as a whole: The communication network is a whole network composed of multiple disciplines (access network, wireless network, transmission network, core network or bearer network, etc.), while shutdown and scheduling operations can only be carried out within a single discipline. Therefore, the overall network operation will result in the waste of remaining resources other than the adjustment of nodes (for example, if a node device in the end-to-end path is shut down, the traffic of other paths will also decrease, but the operating parameters of the cooling equipment outside the area cannot be precisely controlled, so the parameters cannot be adjusted in a coordinated manner). It may even lead to network congestion after service scheduling or increased power consumption due to excessive equipment load.

[0042] (3) High trial-and-error costs: Simply shutting down or rescheduling user services carries high risks, such as network failures due to unsuccessful primary / backup switching and poor service quality resulting from service adjustments. Furthermore, the function of cooling equipment is to cool the physical equipment in a region, and adjusting the air conditioning operating parameters does not immediately change the ambient temperature of that region. Therefore, the waiting time is the commissioning time cost, and failure will increase irreparable power consumption costs. The trial-and-error costs for group-controlled cooling systems are even higher.

[0043] The primary cause of energy consumption in communication networks is the electricity consumption of network infrastructure, which creates demand for traditional energy sources, such as thermal power generation. Therefore, electricity consumption for network infrastructure is the main cause of energy consumption in the communications industry and also a major contributor to carbon emissions. The communications industry deploys a large amount of infrastructure in data centers, core buildings, aggregation rooms, and base stations. Based on the annual data on power consumption facilities published by operators and network architecture analysis, it can be concluded that the electrical energy required by network equipment to carry and forward user services, and the electrical energy required by cooling equipment to dissipate heat generated by the equipment, almost account for the total electricity consumption of the entire communications industry.

[0044] Therefore, as Figure 1 As shown, Figure 1 This diagram illustrates the root causes of energy consumption in the telecommunications industry. The "services" carried by basic communication networks are the fundamental reason for the large amount of energy consumed by operators. Therefore, in order to reduce energy consumption and operating costs in the telecommunications industry, while supporting the country's green industrial development and effectively reducing carbon emissions, this disclosure will achieve energy conservation and emission reduction goals through a model that integrates network services and energy.

[0045] In the embodiments provided in this disclosure, a network service and energy integration model is designed using artificial intelligence algorithms and the TCP / IP reference model, targeting major energy-consuming infrastructure such as transmission equipment, bearer equipment, or cooling equipment in communication network data centers, core buildings, aggregation rooms, and base stations. This leads to the construction of a method for energy conservation and emission reduction in communication networks. Ultimately, the goals of green energy saving and intelligent carbon reduction in communication networks can be achieved during either the network planning phase (before use) or the operation phase (during use).

[0046] like Figure 2 As shown, Figure 2 This is a schematic diagram of the overall architecture design for energy conservation and emission reduction based on the integration of network services and energy, provided in an embodiment of this disclosure. Specifically, it may include: an infrastructure layer, a data processing layer, a fusion model layer, an energy conservation management layer, and a verification and evaluation layer, wherein:

[0047] (1) The infrastructure layer consists of physical equipment and systems, mainly including network equipment that carries user services, cooling equipment that cools physical equipment, and power supply systems.

[0048] (2) The data processing layer collects operational data from the underlying infrastructure, including traffic data, temperature data, and power consumption data. At the same time, based on data parsing capabilities, the collected data is subjected to operations such as attribute labeling and feature parameter extraction. The main purpose is to parse and associate data such as the smallest granularity of "business type, path information, traffic volume, and power consumption" with business as the object, and use it as input parameters for the upper-layer fusion model.

[0049] (3) The fusion model layer is used to train parameters to achieve the integration of business and energy. Finally, it can output a quantitative matrix of end-to-end energy consumption, carbon emission and path information of a certain network business.

[0050] (4) The energy conservation management system matches infrastructure energy conservation and emission reduction strategies based on the quantitative matrix of the fusion model in the planning and operation and maintenance scenarios, and formulates energy conservation and emission reduction strategies.

[0051] (5) The verification and evaluation layer verifies the reliability of the business based on the digital twin pre-verification attributes and evaluates the availability by simulating the effects of energy-saving and emission-reduction strategies.

[0052] In this embodiment, artificial intelligence algorithms can be used to train the smallest granularity of services and their corresponding power consumption, ultimately forming a quantified matrix of network services and energy consumption data, thus completing the smallest granular fusion of detailed services and required energy. For example... Figure 3 As shown, Figure 3 A schematic diagram illustrating the energy-saving and emission-reduction process design for the integration of network services and energy, provided in an embodiment of this disclosure.

[0053] Specifically, 1) Data collection.

[0054] Data is collected from communication equipment such as network devices, cooling equipment, or power systems. The collection method can be either direct protocol acquisition or synchronization with the upper-layer system. The collected data is divided into real-time data and historical data. Real-time data can be used for energy-saving operation and maintenance of the production network, while historical data can be used for model training.

[0055] 2) Data analysis.

[0056] The collected network device port, traffic, temperature, and power consumption data, as well as the ambient temperature and power consumption data of the cooling equipment, are analyzed using a TCP (Transmission Control Protocol) / IP (Internet Protocol) reference model to generate feature data. This feature data can be divided into the following two parts:

[0057] (1) A set of "detailed traffic (IP prefix), traffic size, routing information, and service type" based on different physical ports of network devices. Since a network device typically has many physical ports, and each physical port has many detailed traffic flows, the service types, routing information, and traffic sizes of different detailed traffic flows are different, thus forming a set.

[0058] (2) Total power consumption and total temperature. Since it is impossible to resolve power consumption and temperature to the feature data of each network service, this part is total power consumption and total temperature. Among them, the smallest granularity of power consumption and temperature can only be realized after model training.

[0059] like Figure 4 As shown, Figure 4 This diagram illustrates data parsing as provided in an embodiment of this disclosure. Based on the TCP / IP reference model, the physical layer, network layer, transport layer, and application layer are selected. Feature data parsing is performed on the tagged data to form a preliminary quantitative model of port, IP prefix (detailed traffic), traffic volume, network service type, end-to-end routing, total power consumption, and total temperature.

[0060] 3) Fusion model training.

[0061] In this embodiment, a model can be trained on the input feature data using artificial intelligence algorithms, while total power consumption and total temperature are used as target verification data. If the verification fails, the model parameters are updated and optimized. For example, verification can be performed using the total power consumption at a certain moment as the objective function. The verification process involves comparing the "sum of power consumption for all detailed services across all ports" with the collected "total power consumption." Figure 4 The energy consumption data is the sum of the power consumption of network equipment and the power consumption of cooling equipment.

[0062] Because the feature data exhibits connectivity but a non-linear relationship, this embodiment employs a recurrent neural network (RNN) algorithm for model training. Finally, a quantized matrix of arbitrary end-to-end service traffic and energy requirements is output. Simultaneously, based on national carbon emission calculation standards, electricity consumption is converted into carbon emission values.

[0063] As shown in Table 1, Table 1 is a quantitative matrix of network service and energy integration provided in the embodiments of this disclosure. It outputs various IP prefixes and corresponding traffic volumes (bit / s), service types (such as video, web pages, games, downloads, instant messaging, or online payments), end-to-end routing information (source node IP, intermediate node IP, destination node IP, or metric / cost value) based on different ports of different devices, power consumption (kWh), temperature (Celsius, Fahrenheit), and carbon emission value (kilograms of carbon dioxide equivalent).

[0064] Table 1:

[0065]

[0066] It should be noted that the power consumption in Table 1 is the sum of the power consumption of the network device carrying a certain service and the power consumption of the cooling device for cooling that service. Therefore, the quantization matrix parameters output by the fusion model only consider the network service in a certain port and do not need to involve the relevant data of the cooling device.

[0067] 4) Energy-saving management design.

[0068] like Figure 5 As shown, Figure 5 This diagram illustrates a scenario-based energy-saving strategy driving and process design provided in this embodiment. Energy-saving scenarios include a green "network planning scenario" before network construction and an "energy-saving operation and maintenance scenario" during network operation. Furthermore, different energy-saving strategies will be generated after the network service and energy integration model is calculated based on different scenarios.

[0069] (1) Network planning scenario.

[0070] A. Based on the indicators set in advance during network planning, input key parameters, including "carbon emission threshold, new network routing interconnection design, available IP address range, and the types of services carried by the network".

[0071] B. Drive the network service and energy integration model calculation, and output the remaining variable parameters in the quantization matrix. Using the longest IP address mask as the classification set for detailed traffic (IP prefix), and combining routing design and carbon emission threshold requirements, calculate and output the number of usable device ports, the size of detailed traffic (IP prefix), power consumption, ambient temperature, and corresponding service type. The calculation result is a set, thus allowing the output of the available range of various parameters under network planning scenarios.

[0072] C. Based on carbon emission thresholds and national carbon offset accounting standards, plan the investment in clean energy.

[0073] (2) Energy-saving operation and maintenance scenario.

[0074] A. Monitoring and management is based on network operation data to automatically monitor sudden increases or decreases in energy consumption and carbon emissions, as well as situations exceeding / below thresholds, including anomaly monitoring and threshold exceeding monitoring, and to obtain monitoring data.

[0075] B. Predictive management involves forecasting energy consumption and carbon emissions over a future period, such as hours, days, weeks, or months. In this example, predictive management takes the smallest granularity of detailed business transactions as input (IP prefix), outputs a set of energy consumption and carbon emission values ​​corresponding to those transactions, and then sums the output data based on their similar attributes to obtain the final predicted values ​​for total energy consumption and carbon emissions. Therefore, predictive management includes energy consumption threshold prediction and carbon emission prediction.

[0076] C. Based on monitoring and predictive management parameters, the network service and energy integration model is driven to perform calculations. Output strategies include "end-to-end energy consumption / traffic / carbon emission / temperature-based global service scheduling strategy, ambient temperature control strategy, cold source group control parameter adjustment strategy, clean energy allocation strategy, and equipment replacement emergency early warning strategy when no effective strategy is available".

[0077] 5) Determine the feasibility of the strategy.

[0078] like Figure 6 As shown, Figure 6 This diagram illustrates the architecture design for determining the feasibility of energy-saving strategies according to embodiments of this disclosure. By constructing a digital twin pre-verification architecture, the execution of energy-saving strategies is verified in advance, including network-oriented service verification and strategy effectiveness evaluation for energy saving.

[0079] (1) Different parameters are input based on different scenarios, and different twin models are matched simultaneously. Among them, different twin models are used to simulate different real environments.

[0080] (2) The network operation status simulation is completed under different scenarios after the application of the strategy through the index simulation calculation module. By selecting the corresponding twin model and executing the corresponding strategy in the twin model, the simulation results are used to determine whether the strategy meets the requirements. If it meets the requirements, the measurement can be performed in the real environment.

[0081] (3) Both scenarios require business verification and energy-saving assessment to ensure that business policies operate while the network is energy-saving.

[0082] in:

[0083] A. Service Verification: It is necessary to verify the overall network operation and the operation when services are adjusted. The verification content includes basic routing connectivity, the rationality of end-to-end routing, service operation quality (such as latency or packet loss), and whether the traffic exceeds the threshold.

[0084] B. Energy Saving Assessment: It is necessary to verify whether the application of energy-saving strategies has resulted in reduced energy consumption and carbon emissions. The strategy is deemed effective when both verification results meet the predetermined objectives; otherwise, it is considered invalid and an alert is reported.

[0085] Therefore, based on the above embodiments, the present disclosure has the following technical effects:

[0086] (1) Service and Energy Consumption Integration: Taking specific network services as the object, this method analyzes the energy consumption of different service types, completes the construction of service and energy consumption models, and thus realizes a quantified model after integration. Unlike related technologies, taking services as the object allows for more precise and refined energy-saving strategies. A single traffic flow typically contains a large number of different services, which related technologies cannot accurately achieve.

[0087] (2) Application of the TCP / IP Reference Model: Before applying artificial intelligence technology to train the model, the TCP / IP reference model (extracting the "physical layer, network layer, transport layer, and application layer") is used to accurately analyze the feature data, providing a reliable guarantee for the input parameters of the model training. Since the communication network is originally based on the theory of this model, the required relationship between "current -> port -> bit -> routing -> service type" is completely reliable. Therefore, the availability and reliability of the energy-saving and carbon-reduction strategy after constructing the quantized model are strongly guaranteed.

[0088] (3) End-to-end network energy consumption is controllable: Related technologies can only control the energy consumption of a single node in a simple way, which will cause the services of the remaining network links to fail and the energy consumption to increase or decrease suddenly. Therefore, the model construction and training methods of this disclosure introduce network layer routing information, which can realize end-to-end energy consumption tracing and global adjustment.

[0089] (4) Wider range of applications: Related technical solutions only provide simple energy-saving strategies for networks in operation, which are actually energy-saving in operation and maintenance scenarios. However, the embodiments disclosed in this disclosure can not only provide energy-saving strategies during operation, but also be applied in the planning stage before network construction, so as to complete the planning and design of green networks in advance and achieve the goal of putting green networks into operation immediately after network construction.

[0090] Based on the above embodiments, this disclosure also provides an energy-saving and emission-reduction method based on the integration of network services and energy, such as... Figure 7 As shown, the method may include the following steps:

[0091] In step S710, historical data of the infrastructure is obtained.

[0092] This infrastructure includes network equipment, cooling equipment, and power systems.

[0093] In the embodiments, such as Figure 3 As shown, data can be collected from communication equipment such as network devices, cooling equipment, and power systems. The collected data can be divided into real-time data and historical data. Real-time data is used for energy-saving operation and maintenance of the production network, while historical data is used for model training.

[0094] In this embodiment, data can be collected from the infrastructure and input into the TCP / IP reference model. The TCP / IP reference model then parses the collected data to obtain historical data of the infrastructure. This historical data includes different dimensions of information corresponding to different ports of network devices, as well as the total power consumption and total temperature of the network devices.

[0095] Can be combined Figure 4 As shown, this embodiment is based on the TCP / IP reference model, selecting the physical layer, network layer, transport layer, and application layer. The labeled data is then parsed to generate a preliminary quantitative model containing port numbers, IP prefixes, traffic volume, network service type, end-to-end routing, total power consumption, and total temperature.

[0096] Since network communication is generally based on the encapsulation and decapsulation operations of the TCP / IP reference model, the collected data is parsed using the TCP / IP reference model in this embodiment, which makes the parsed feature data more reliable.

[0097] In step S720, the preset model is trained using historical data to obtain a network service and energy integration model.

[0098] In this embodiment, a preset model can be trained based on historical data, and the trained model can be validated using an objective function; wherein the objective function is derived based on total power consumption. If the validation is satisfied, the trained preset model is used as the network service and energy integration model.

[0099] In this embodiment, the total power consumption at a certain moment can be used as the objective function for verification. The verification process involves comparing the sum of the power consumption of all detailed services on each port of the network device with the collected total power consumption to determine whether the objective function is satisfied. If the verification is satisfied, training of the preset model can be stopped to obtain the network service and energy integration model; otherwise, training of the preset model needs to continue. The preset module can be a neural network model, such as a recurrent neural network model, etc., but the embodiment is not limited to this.

[0100] In step S730, real-time data from network devices is acquired and input into the network service and energy integration model to obtain a quantitative matrix of network service and energy integration.

[0101] The quantization matrix represents the correspondence between different ports and different dimensions of information in a network device.

[0102] In this embodiment, user-inputted target parameters can be used as real-time data. These target parameters include carbon emission thresholds, new network routing interconnection design, available IP address ranges, and the types of services carried by the network. The real-time data is then input into a network service and energy integration model to obtain a quantitative matrix of network service and energy integration. This quantitative matrix includes the number of ports in each network device, detailed traffic volume, power consumption, ambient temperature, and service type.

[0103] In the embodiments, in network planning scenarios, such as Figure 5 As shown, it can be based on indicators set in advance during network planning, and key parameters can be input, such as: carbon emission threshold, new network routing interconnection design, available IP address range and the types of services carried by the network.

[0104] By driving the network service and energy integration model calculation, the remaining variable parameters in the quantization matrix are output. The longest IP address mask is used as the classification set of detailed traffic. Combined with routing design and carbon emission threshold requirements, the number of usable device ports, detailed traffic size, power consumption, ambient temperature, and corresponding service type are calculated and output.

[0105] In step S740, energy conservation and emission reduction strategies for infrastructure are determined based on the quantization matrix.

[0106] In this embodiment, the quantization matrix of network services and energy integration can be matched with a preset strategy to obtain energy-saving and emission-reduction strategies that match the quantization matrix of network services and energy integration within the preset strategy. The preset strategy includes multiple different energy-saving and emission-reduction strategies, each corresponding to a quantization matrix with different parameters.

[0107] In the embodiments provided in this disclosure, a network service and energy integration model is obtained by acquiring historical data of the infrastructure and training a preset model using this historical data. Real-time data from network devices is acquired and input into the network service and energy integration model to obtain a quantization matrix of network service and energy integration. This allows for the determination of energy-saving and emission-reduction strategies for the infrastructure based on the quantization matrix. Since the quantization matrix represents the correspondence between different ports and different dimensions of information in network devices, this accurately determines energy-saving and emission-reduction strategies for the infrastructure, avoiding potential service failures when performing operations such as shutting down relevant ports in network devices.

[0108] Based on the above embodiments, in another embodiment provided in this disclosure, the method may further include the following steps:

[0109] In step S750, a twin model matching the energy conservation and emission reduction strategy is obtained.

[0110] In step S760, the energy-saving and emission-reduction strategy is executed through the twin model, and the simulation results of the energy-saving and emission-reduction strategy in the twin model are obtained.

[0111] In step S770, the simulation results are verified, and based on the obtained verification results, it is determined whether the energy-saving and emission-reduction strategy is an effective strategy.

[0112] In this embodiment, different twin models can be generated for different real-world environments. This allows for the selection of a twin model that matches the energy conservation and emission reduction strategy. That is, when an energy conservation and emission reduction strategy needs to be executed in a specific real-world environment, it can first be executed in the twin model corresponding to that environment. This allows for the acquisition of simulation results of the energy conservation and emission reduction strategy in the twin model, which can then be verified. If the verification is successful, it can be determined that the energy conservation and emission reduction strategy can be executed in the corresponding real-world environment; otherwise, it indicates that the energy conservation and emission reduction strategy is not suitable for execution in the corresponding real-world environment.

[0113] The embodiments disclosed herein verify the energy conservation and emission reduction strategies using twin models, which can ensure the reliability and feasibility of the energy conservation and emission reduction strategies after their application.

[0114] By dividing each function into corresponding functional modules, this disclosure provides an energy-saving and emission-reduction device based on the integration of network services and energy. This energy-saving and emission-reduction device can be a server, a terminal, or a chip applied to a server. Figure 8 This is a schematic block diagram of the functional modules of an energy-saving and emission-reduction device based on the integration of network services and energy, provided as an exemplary embodiment of this disclosure. Figure 8 As shown, this energy-saving and emission-reduction device based on the integration of network services and energy includes:

[0115] Data acquisition module 10 is used to acquire historical data of infrastructure, including network equipment, cooling equipment and power system;

[0116] Training module 20 is used to train a preset model using the historical data to obtain a network service and energy integration model;

[0117] The quantization matrix acquisition module 30 is used to acquire real-time data of the network device and input the real-time data into the network service and energy integration model to obtain the quantization matrix of network service and energy integration; wherein, the quantization matrix represents the correspondence between different ports and different dimensions of information in the network device;

[0118] The energy conservation and emission reduction strategy determination module 40 is used to determine the energy conservation and emission reduction strategy for the infrastructure based on the quantization matrix.

[0119] In another embodiment provided in this disclosure, the data acquisition module is specifically used for:

[0120] Data is collected from the infrastructure, and the collected data is input into the TCP / IP reference model;

[0121] The collected data is parsed using the TCP / IP reference model to obtain historical data of the infrastructure; wherein, the historical data includes different dimensions of information corresponding to different ports of the network device, the total power consumption and total temperature of the network device.

[0122] In another embodiment provided in this disclosure, the training module is specifically used for:

[0123] The preset model is trained based on the historical data, and the trained model is validated using the objective function; wherein the objective function is obtained based on the total power consumption.

[0124] If the verification is satisfied, the trained preset model will be used as the network service and energy integration model.

[0125] In another embodiment provided in this disclosure, the quantization matrix acquisition module is specifically used for:

[0126] The target parameters input by the user are used as the real-time data; the target parameters include carbon emission thresholds, routing interconnection design, IP address ranges, and service types.

[0127] The real-time data is input into the network service and energy integration model to obtain the quantitative matrix of network service and energy integration; wherein, the quantitative matrix of network service and energy integration includes the number of ports, detailed traffic volume, power consumption, ambient temperature and service type of each port in the network device.

[0128] In another embodiment provided in this disclosure, the energy conservation and emission reduction strategy determination module is specifically used for:

[0129] The quantization matrix of the integration of network services and energy is matched with a preset strategy; the preset strategy includes multiple different energy-saving and emission-reduction strategies, and different energy-saving and emission-reduction strategies correspond to quantization matrices with different parameters.

[0130] Obtain the energy-saving and emission-reduction strategy that matches the quantitative matrix of network service and energy integration in the preset strategy.

[0131] In another embodiment provided in this disclosure, the apparatus further includes a verification module, which is specifically used for:

[0132] Obtain a twin model that matches the energy conservation and emission reduction strategy;

[0133] The energy conservation and emission reduction strategy is executed through the twin model, and the simulation results of the energy conservation and emission reduction strategy in the twin model are obtained;

[0134] The simulation results are verified, and based on the obtained verification results, it is determined whether the energy-saving and emission-reduction strategy is an effective strategy.

[0135] The energy-saving and emission-reduction device based on the integration of network services and energy provided in this embodiment acquires historical data of the infrastructure and trains a preset model using this historical data to obtain a network service and energy integration model. By acquiring real-time data from network devices and inputting this real-time data into the network service and energy integration model, a quantization matrix of network service and energy integration is obtained. This quantization matrix allows for the determination of energy-saving and emission-reduction strategies for the infrastructure. Since the quantization matrix represents the correspondence between different ports and different dimensions of information in network devices, this accurately determines the energy-saving and emission-reduction strategies for the infrastructure, avoiding potential service failures when performing operations such as shutting down relevant ports in network devices.

[0136] This disclosure also provides an electronic device, including: at least one processor; a memory for storing processor-executable instructions; wherein the at least one processor is configured to execute the instructions to implement the methods disclosed in this disclosure.

[0137] Figure 9 This is a schematic diagram of the structure of an electronic device provided as an exemplary embodiment of this disclosure. For example... Figure 9 As shown, the electronic device 1800 includes at least one processor 1801 and a memory 1802 coupled to the processor 1801. The processor 1801 can perform the corresponding steps in the methods disclosed in the embodiments of this disclosure.

[0138] The processor 1801 described above can also be called a central processing unit (CPU), which can be an integrated circuit chip with signal processing capabilities. Each step in the method disclosed in this embodiment can be implemented by the integrated logic circuitry in the processor 1801 or by software instructions. The processor 1801 can be a general-purpose processor, a digital signal processor (DSP), an ASIC (Application Specific Integrated Circuit), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this embodiment can be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software modules can be located in the memory 1802, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The processor 1801 reads information from the memory 1802 and, in conjunction with its hardware, completes the steps of the method described above.

[0139] Furthermore, various operations / processes according to this disclosure, implemented via software and / or firmware, can be transmitted from a storage medium or network to a computer system with a dedicated hardware architecture, such as... Figure 10 The computer system 1900 shown is equipped with the programs that constitute the software. When various programs are installed, the computer system is able to perform various functions, including those described above. Figure 10 A block diagram of a computer system provided for an exemplary embodiment of this disclosure.

[0140] Computer System 1900 is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0141] like Figure 10As shown, the computer system 1900 includes a computing unit 1901, which can perform various appropriate actions and processes based on a computer program stored in a read-only memory (ROM) 1902 or a computer program loaded from a storage unit 1908 into a random access memory (RAM) 1903. The RAM 1903 may also store various programs and data required for the operation of the computer system 1900. The computing unit 1901, ROM 1902, and RAM 1903 are interconnected via a bus 1904. An input / output (I / O) interface 1905 is also connected to the bus 1904.

[0142] Multiple components in computer system 1900 are connected to I / O interface 1905, including: input unit 1906, output unit 1907, storage unit 1908, and communication unit 1909. Input unit 1906 can be any type of device capable of inputting information into computer system 1900. Input unit 1906 can receive input digital or character information and generate key signal inputs related to user settings and / or function control of the electronic device. Output unit 1907 can be any type of device capable of presenting information and may include, but is not limited to, a monitor, speaker, video / audio output terminal, vibrator, and / or printer. Storage unit 1908 may include, but is not limited to, hard disks and optical disks. Communication unit 1909 allows computer system 1900 to exchange information / data with other devices via a network such as the Internet, and may include, but is not limited to, modems, network cards, infrared communication devices, wireless communication transceivers, and / or chipsets, such as Bluetooth™ devices, WiFi devices, WiMax devices, cellular communication devices, and / or the like.

[0143] The computing unit 1901 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 1901 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 1901 performs the various methods and processes described above. For example, in some embodiments, the methods disclosed in this disclosure can be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 1908. In some embodiments, part or all of the computer program can be loaded and / or installed on an electronic device via ROM 1902 and / or communication unit 1909. In some embodiments, the computing unit 1901 can be configured to perform the methods disclosed in this disclosure by any other suitable means (e.g., by means of firmware).

[0144] This disclosure also provides a computer-readable storage medium, wherein when the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is able to perform the methods disclosed in this disclosure.

[0145] The computer-readable storage medium in this disclosure can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. The aforementioned computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specifically, the aforementioned computer-readable storage medium may include electrical connections based on one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0146] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0147] This disclosure also provides a computer program product, including a computer program, wherein the computer program, when executed by a processor, implements the methods disclosed in the embodiments of this disclosure.

[0148] In embodiments of this disclosure, computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof. These programming languages ​​include, but are not limited to, object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network (including a local area network (LAN) or a wide area network (WAN)), or it can be connected to an external computer.

[0149] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0150] The modules, components, or units described in the embodiments of this disclosure can be implemented in software or hardware. The names of the modules, components, or units do not necessarily constitute a limitation on the module, component, or unit itself.

[0151] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary hardware logic components that can be used include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0152] The above description is merely an embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0153] While specific embodiments of this disclosure have been described in detail by way of example, those skilled in the art should understand that the examples are for illustrative purposes only and not intended to limit the scope of this disclosure. Those skilled in the art should understand that modifications can be made to the above embodiments without departing from the scope and spirit of this disclosure. The scope of this disclosure is defined by the appended claims.

Claims

1. A method for energy conservation and emission reduction based on the integration of network services and energy, characterized in that, The method includes: Acquire historical data on infrastructure, including network equipment, cooling equipment, and power systems; The network service and energy integration model is obtained by training the preset model using the historical data. The network device's real-time data is acquired and input into the network service and energy integration model to obtain a quantization matrix of network service and energy integration. The quantization matrix represents the correspondence between different ports and different dimensions of information in the network device. The different dimensions of information include: IP prefix, traffic volume, service type, routing information, power consumption, temperature, and carbon emission value. Based on the quantification matrix, energy conservation and emission reduction strategies for the infrastructure are determined; The step of training a preset model using the historical data to obtain a network service and energy integration model includes: The historical data is parsed based on the physical layer, network layer, transport layer and application layer of the TCP / IP reference model to obtain characteristic data such as port, IP prefix, traffic size, service type, end-to-end routing, total power consumption and total temperature. The trained model is validated using total power consumption as the objective function. Once the validation is successful, the network service and energy integration model is obtained. The determination of energy conservation and emission reduction strategies for the infrastructure based on the quantification matrix includes: The quantization matrix of the integration of network services and energy is matched with a preset strategy; the preset strategy includes multiple different energy-saving and emission-reduction strategies, and different energy-saving and emission-reduction strategies correspond to quantization matrices with different parameters. Obtain the energy-saving and emission-reduction strategy that matches the quantitative matrix of the integration of network services and energy in the preset strategy; The energy conservation and emission reduction strategies include: a business global scheduling strategy based on end-to-end energy consumption / flow / carbon emissions / temperature, an ambient temperature control strategy, a parameter adjustment strategy for each link of cold source group control, a clean energy allocation strategy, and an emergency early warning strategy for equipment replacement when there is no effective strategy. Before implementing the selected strategy, simulation verification is performed using a digital twin model to confirm the strategy's effectiveness before execution in a real environment.

2. The method according to claim 1, characterized in that, The acquisition of historical infrastructure data includes: Data is collected from the infrastructure, and the collected data is input into the TCP / IP reference model; The collected data is parsed using the TCP / IP reference model to obtain historical data of the infrastructure; wherein, the historical data includes different dimensions of information corresponding to different ports of the network device, the total power consumption and total temperature of the network device.

3. The method according to claim 2, characterized in that, The step of training a preset model using the historical data to obtain a network service and energy integration model includes: The preset model is trained based on the historical data, and the trained model is validated using an objective function; wherein the objective function is obtained based on the total power consumption. If the verification is satisfied, the trained preset model will be used as the network service and energy integration model.

4. The method according to claim 1, characterized in that, The step of inputting the real-time data into the network service and energy integration model to obtain the quantization matrix of network service and energy integration includes: The target parameters input by the user are used as the real-time data; the target parameters include carbon emission thresholds, routing interconnection design, IP address ranges, and service types. The real-time data is input into the network service and energy integration model to obtain the quantitative matrix of network service and energy integration; wherein, the quantitative matrix of network service and energy integration includes the number of ports, detailed traffic volume, power consumption, ambient temperature and service type of each port in the network device.

5. The method according to any one of claims 1 to 4, characterized in that, The method further includes: Obtain a twin model that matches the energy conservation and emission reduction strategy; The energy conservation and emission reduction strategy is executed through the twin model, and the simulation results of the energy conservation and emission reduction strategy in the twin model are obtained; The simulation results are verified, and based on the obtained verification results, it is determined whether the energy-saving and emission-reduction strategy is an effective strategy.

6. An energy-saving and emission-reduction device based on the integration of network services and energy, characterized in that, The device includes: The data acquisition module is used to acquire historical data of the infrastructure, which includes network equipment, cooling equipment, and power systems. The training module is used to train a preset model using the historical data to obtain a network service and energy integration model. Specifically, it parses the historical data based on the physical layer, network layer, transport layer, and application layer of the TCP / IP reference model to obtain feature data such as port, IP prefix, traffic volume, service type, end-to-end routing, total power consumption, and total temperature. The trained model is then validated using total power consumption as the objective function. Once the validation is successful, the network service and energy integration model is obtained. A quantization matrix acquisition module is used to acquire real-time data from the network device and input the real-time data into the network service and energy integration model to obtain a quantization matrix of network service and energy integration; wherein, the quantization matrix represents the correspondence between different ports and different dimensions of information in the network device; An energy conservation and emission reduction strategy determination module is used to determine energy conservation and emission reduction strategies for the infrastructure based on the quantization matrix. The energy conservation and emission reduction strategy determination module is specifically used for: The quantization matrix of the integration of network services and energy is matched with a preset strategy; the preset strategy includes multiple different energy-saving and emission-reduction strategies, and different energy-saving and emission-reduction strategies correspond to quantization matrices with different parameters. Obtain the energy-saving and emission-reduction strategy that matches the quantitative matrix of the integration of network services and energy in the preset strategy; The energy conservation and emission reduction strategies include: a business global scheduling strategy based on end-to-end energy consumption / flow / carbon emissions / temperature, an ambient temperature control strategy, a parameter adjustment strategy for each link of cold source group control, a clean energy allocation strategy, and an emergency early warning strategy for equipment replacement when there is no effective strategy. The verification module is used to perform simulation verification using a digital twin model before executing the selected strategy, confirming the effectiveness of the strategy before execution in the real environment.

7. An electronic device, characterized in that, include: At least one processor; Memory for storing the at least one processor-executable instruction; The at least one processor is configured to execute the instructions to implement the method as described in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, When the instructions in the computer-readable storage medium are executed by the processor of the electronic device, the electronic device is able to perform the method as described in any one of claims 1-5.

9. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method according to any one of claims 1-5.

Images