Energy consumption intelligent management and control method and system based on multi-modal network and related device

Abstract

The present disclosure provides a multi-modal network-based energy consumption intelligent management and control method and system, a computer readable storage medium and an electronic device, relating to the technical field of communication. The method comprises: receiving, by a multi-modal network data lake, current network data uploaded by a network device when a network state changes from a cross-domain service layer; periodically sending, by the cross-domain service layer, a resource query request to the multi-modal network data lake, the resource query request being used to query the current network data and historical network data of the network device; predicting, by the cross-domain service layer, network data at the next moment based on the current network data and the historical network data, and formulating a corresponding cross-domain energy saving strategy according to the network data; and issuing, by the cross-domain service layer, the cross-domain energy saving strategy to the network device to execute the cross-domain energy saving strategy. The method improves network energy saving effectiveness and operation and maintenance efficiency, and realizes multi-modal network-based energy consumption intelligent management and control.

Description

Technical Field

[0001] This disclosure relates to the field of communication technology, and in particular to a method, system, computer-readable storage medium, and electronic device for intelligent energy consumption management based on multimodal networks. Background Technology

[0002] To break through the traditional single-bearer structure development model of networks and form a diversified network development paradigm that meets the needs of diversified vertical industries, a new network architecture—multimodal intelligent network architecture—was proposed in 2020. Multimodality is reflected in the multiple modes of network elements such as addressing and routing, switching mode, interconnection method, network element form, and transmission protocol.

[0003] Traditional network energy consumption management models typically rely on simple models or pre-set thresholds. These models or thresholds are often based on empirical values, only categorized into a limited number of scenario types, and have conservative parameters, resulting in limited energy-saving effectiveness. They are ill-suited to today's complex and ever-changing network environments and struggle to balance energy efficiency with user experience. Therefore, future network architectures require a smart energy consumption management method that supports multimodal networks to achieve intelligent and efficient network energy management.

[0004] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0005] The purpose of this disclosure is to provide a method, system, computer-readable storage medium, and electronic device for intelligent energy consumption management based on multimodal networks, so as to at least solve the technical problems of low energy-saving efficiency and poor user experience caused by the inability of current network energy consumption management models to cope with complex and ever-changing network environments.

[0006] Other features and advantages of this disclosure will become apparent from the following detailed description, or may be learned in part from practice of this disclosure.

[0007] The technical solution disclosed herein is as follows:

[0008] According to one aspect of this disclosure, an intelligent energy consumption management method based on a multimodal network is provided. The method includes: a multimodal network data lake receiving current network data uploaded by network devices when the network state changes from a cross-domain service layer; the cross-domain service layer periodically sending resource query requests to the multimodal network data lake, the resource query requests being used to query the current network data and historical network data of the network devices; the cross-domain service layer predicting the network data at the next moment based on the current network data and historical network data, and formulating corresponding cross-domain energy-saving strategies based on the network data; and the cross-domain service layer distributing the cross-domain energy-saving strategies to the network devices for execution.

[0009] In some embodiments of this disclosure, the steps of the cross-domain service layer predicting the network data at the next moment based on current network data and historical network data, and formulating corresponding cross-domain energy-saving strategies based on the network data include: the cross-domain service layer preprocessing, extracting features, modeling, training and evaluating the extracted historical network data to establish a load and energy consumption prediction model; the cross-domain service layer inputting the collected current network data into the trained neural network-based load and energy consumption prediction model for cross-domain collaborative correlation analysis and positioning; and the cross-domain service layer formulating cross-domain energy-saving strategies based on the resources involved in the network devices.

[0010] In some embodiments of this disclosure, the network device executes a cross-domain energy-saving strategy to obtain a cross-domain execution result, and feeds the cross-domain execution result back to the cross-domain service layer. The cross-domain execution result includes: the current network data after the network device executes the task; the cross-domain service layer sends the cross-domain execution result to the multimodal network data lake.

[0011] In some embodiments of this disclosure, the method may further include: optimizing a neural network-based load and energy consumption prediction model by the cross-domain service layer based on the cross-domain execution results.

[0012] In some embodiments of this disclosure, the network device includes a data layer network device and a control layer network device. Before the step of the multimodal network data lake receiving the current network data uploaded by the network device when the network state changes from the cross-domain service layer, the method further includes: the data layer network device reporting the current network data to the control layer network device for aggregation when the network state changes; and the control layer network device reporting the aggregated network data to the cross-domain service layer.

[0013] In some embodiments of this disclosure, the step of the cross-domain service layer distributing the cross-domain energy-saving policy to the network device for execution includes: the cross-domain service layer distributing the cross-domain energy-saving policy to the control layer network device for execution to obtain the pre-processed energy-saving policy; and the control layer network device sending the pre-processed energy-saving policy to its respective corresponding data layer network device.

[0014] In some embodiments of this disclosure, the data layer network device executes a cross-domain energy-saving strategy to obtain a cross-domain execution result, and sends the cross-domain execution result to the control layer network device for aggregation; the control layer network device feeds back the aggregation result to the cross-domain service layer, and the cross-domain execution result includes: the current network data after the data layer network device executes the task; the cross-domain service layer sends the cross-domain execution result to the multimodal network data lake.

[0015] In some embodiments of this disclosure, the cross-domain service layer includes a state awareness module and a resource adaptation module. The steps of the cross-domain service layer predicting the network data at the next moment based on current network data and historical network data, and formulating corresponding cross-domain energy-saving strategies based on the network data, include: the state awareness module of the cross-domain service layer preprocessing, extracting features, modeling, training and evaluating the extracted historical network data to establish a load and energy consumption prediction model; inputting the collected current network data into the pre-trained neural network-based load and energy consumption prediction model for cross-domain collaborative correlation analysis and location to obtain prediction results; sending the prediction results to the resource adaptation module; and the resource adaptation module formulating cross-domain energy-saving strategies based on the resources involved in the network devices.

[0016] In some embodiments of this disclosure, network data includes network configuration data and network indicator data collected from the network management system. The network configuration data includes network topology and device location-related parameters. The network indicator data includes the utilization rate and capacity of components such as CPU and memory that describe resources, the service request rate, service time, load cycle and traffic rate that describe the load, and the data throughput, service bandwidth and transmission latency that describe the performance. The network data also includes data information of the power system and environmental parameters from temperature and humidity sensors.

[0017] According to another aspect of this disclosure, an intelligent energy consumption management and control system based on a multimodal network is provided. The system includes: a network device layer, a cross-domain service layer, and a multimodal network data lake. The multimodal network data lake is used to receive network data uploaded by network devices in the network device layer when the network state changes, from the cross-domain service layer. The cross-domain service layer is used to periodically send resource query requests to the data lake, which are used to query the current network data and historical network data of the network devices in the network device layer. Based on the current network data and historical network data, the system predicts the network data for the next moment and formulates corresponding cross-domain energy-saving strategies according to the network data. The system also distributes the cross-domain energy-saving strategies to the network devices in the network device layer for execution.

[0018] According to another aspect of this disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the above-described intelligent energy management method based on a multimodal network by executing the executable instructions.

[0019] According to another aspect of this disclosure, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the above-described intelligent energy consumption management method based on a multimodal network.

[0020] This disclosure proposes an intelligent energy-saving control method that supports multimodal networks, enabling it to support future multimodal network architectures and meet the needs of network operation and maintenance in complex and ever-changing network environments.

[0021] Furthermore, the cross-domain service layer in this embodiment can predict the energy consumption index at the next moment and adopt a multi-domain network collaborative energy-saving control strategy, thereby improving operation and maintenance efficiency and energy-saving efficiency, and realizing comprehensive management and control of multi-domain network energy consumption.

[0022] Furthermore, by enabling multi-domain networks to work together, the load on each individual domain network is reduced, ensuring network stability and improving the user experience.

[0023] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0024] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure. It is obvious that the drawings described below are merely some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0025] Figure 1 This diagram illustrates a flow chart of an intelligent energy consumption management method based on a multimodal network, according to an embodiment of this disclosure.

[0026] Figure 2 The diagram shows a flowchart of the energy consumption state perception and prediction method in an energy consumption intelligent management and control method based on multimodal networks in an embodiment of this disclosure.

[0027] Figure 3 This diagram illustrates an energy consumption state sensing and prediction model according to an embodiment of the present disclosure.

[0028] Figure 4 This diagram illustrates a first application example of an intelligent energy consumption management method based on a multimodal network, as described in this disclosure.

[0029] Figure 5 This diagram illustrates a second application example of an intelligent energy consumption management method based on a multimodal network, as described in this disclosure.

[0030] Figure 6 This diagram illustrates the network architecture of an intelligent energy consumption management system based on a multimodal network, as described in an embodiment of this disclosure.

[0031] Figure 7 This diagram illustrates an electronic device using a multimodal network-based intelligent energy consumption management method according to an embodiment of the present disclosure. Detailed Implementation

[0032] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, they are provided so that this disclosure will be more comprehensive and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0033] Furthermore, the accompanying drawings are merely illustrative of this disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0034] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this disclosure, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0035] In view of the technical problems existing in the above-mentioned related technologies, the present disclosure provides a routing node quality monitoring method to solve at least one or all of the above-mentioned technical problems.

[0036] It should be noted that the nouns or terms used in the embodiments of this application can be referenced from each other and will not be repeated here.

[0037] The following will describe in more detail each step of the energy consumption intelligent management method based on multimodal networks in this exemplary embodiment, with reference to the accompanying drawings and embodiments.

[0038] Figure 1 This diagram illustrates a flowchart of an intelligent energy consumption management method based on a multimodal network, as described in an embodiment of this disclosure. Figure 1 As shown, method 100 may include the following steps:

[0039] In step S110, the multimodal network data lake receives current network data uploaded by network devices when the network state changes from the cross-domain service layer.

[0040] The network devices can come from one or more of a single-domain or multi-domain network, such as an IP domain, a transport network domain, and a passive optical network domain.

[0041] In the case of multiple domains, the addressing and routing modes of network devices in each domain can be the same or different. The addressing and routing modes can include multiple modes based on identifiers such as IP, content, identity, and geospatial information.

[0042] In step S120, the cross-domain service layer periodically sends resource query requests to the multimodal network data lake. The resource query requests are used to query the current network data and historical network data of the network devices.

[0043] Among them, current network data and historical network data are current network load and energy consumption data and historical network load and energy consumption data, respectively.

[0044] In step S130, the cross-domain service layer predicts the network data for the next moment based on the current network data and historical network data, and formulates corresponding cross-domain energy-saving strategies based on the network data.

[0045] Among them, cross-domain energy-saving strategies can, for example, intelligently hibernate the control commands of network element devices in the corresponding domain network when the network load is too low; and intelligently wake up or migrate the load to the control commands of network element devices in the corresponding domain network when the network load is too high.

[0046] In step S140, the cross-domain service layer distributes the cross-domain energy-saving policy to the network devices for execution.

[0047] Among them, cross-domain energy-saving strategies include cross-domain energy-saving strategies corresponding to each domain network in a single-domain network or a multi-domain network.

[0048] The present invention discloses an intelligent energy-saving control method that supports multimodal networks, which can support future multimodal network architectures and meet the needs of network operation and maintenance in complex and ever-changing network environments.

[0049] Furthermore, the cross-domain service layer in this disclosure can predict energy consumption indicators at the next moment and adopt a multi-domain network collaborative energy-saving control strategy, thereby improving operation and maintenance efficiency and energy-saving efficiency, and realizing comprehensive management and control of multi-domain network energy consumption.

[0050] Furthermore, by enabling multi-domain networks to work together, the load on each individual domain network is reduced, ensuring network stability and improving the user experience.

[0051] In some embodiments of this disclosure, step S130 may also, for example... Figure 2 This illustrates a method for sensing and predicting network energy consumption status, such as... Figure 2 As shown, method 200 may include the following steps:

[0052] In step S210, the cross-domain service layer preprocesses, extracts features, models, trains, and evaluates the extracted historical network data to establish load and energy consumption prediction models.

[0053] In step S220, the cross-domain service layer inputs the collected current network data into the trained load and energy consumption prediction model for cross-domain collaborative correlation analysis and localization.

[0054] Among them, collaborative correlation analysis and location refers to the cross-domain service layer locating one or more domains from a multi-domain network based on the reported network data to perform cross-domain collaborative correlation analysis.

[0055] In step S230, the cross-domain service layer formulates a cross-domain energy-saving strategy based on the resources involved in the network device.

[0056] The method of this disclosure can summarize, model, and predict network data from network devices, realizing collaborative analysis and evaluation of network data.

[0057] Specific processes, for example Figure 3 As shown, the cross-domain service layer senses historical network data fed back from network devices in single-domain or multi-domain networks; it generates an AI prediction model for load and energy consumption by preprocessing, feature extraction, modeling, training, and evaluation of the historical network data; it then inputs the sensed current network data into the trained AI prediction model to obtain the load and energy consumption prediction data for the next moment; and finally, it formulates a cross-domain energy-saving strategy based on the prediction data.

[0058] In some embodiments of this disclosure, the cross-domain service layer can be further divided into a state-aware module and a resource adaptation module. The method may then further include: the state-aware module of the cross-domain service layer preprocessing, extracting features, and training and evaluating the extracted historical network data to establish a load and energy consumption prediction model; inputting the collected current network data into the trained neural network-based load and energy consumption prediction model for cross-domain collaborative correlation analysis and location to obtain prediction results; sending the prediction results to the resource adaptation module; and the resource adaptation module formulating cross-domain energy-saving strategies based on the resources involved in the network devices of a single-domain network or a multi-domain network.

[0059] By deploying dedicated modules to predict network consumption in the next moment and formulate control strategies, intelligent energy consumption management is achieved, while improving the utilization efficiency and sharing level of hardware resources, and making it more convenient to formulate cross-domain energy-saving strategies.

[0060] In some embodiments of this disclosure, such as Figure 3 As shown, network data (i.e., network load and energy consumption data) may include: network configuration data and network indicator data of network devices (such as servers) 310 collected from the network management system. The network configuration data includes network topology, device location-related parameters, etc.; the network indicator data includes resource descriptions such as CPU and memory utilization and capacity; load descriptions such as service request rate, service time, load cycle time, and traffic rate; and performance descriptions such as data throughput, service bandwidth, and transmission latency. In addition, it also includes data information from power systems 320 such as meters, batteries, distribution boxes, and engines, and environmental parameters from various environmental sensors 330 such as temperature and humidity sensors.

[0061] By integrating multi-dimensional data on devices and resources within the network, a more realistic and comprehensive reflection of the actual network situation can be achieved.

[0062] In some embodiments of this disclosure, after step S140 is executed, the method of this disclosure may further include: the network device executing a cross-domain energy-saving strategy to obtain a cross-domain execution result, and feeding back the cross-domain execution result to the cross-domain service layer, wherein the cross-domain execution result includes: the current network data after the network device executes the task; and the cross-domain service layer sending the cross-domain execution result to the multimodal network data lake.

[0063] The cross-domain execution result can also include a return value indicating whether the execution was successful. After receiving the execution result, the cross-domain service layer first determines whether the execution was successful. If the execution is successful, the cross-domain service layer sends the network data after the task execution to the multimodal network data lake to update the current network data, so as to ensure the reliability of the data and facilitate the formulation of effective cross-domain energy-saving strategies in advance. If the execution is unsuccessful, the cross-domain service layer can re-formulate the cross-domain energy-saving strategy based on the current network data and repeat the above steps until the execution is successful.

[0064] In some embodiments of this disclosure, after the network device executes a cross-domain energy-saving strategy to obtain cross-domain execution results and feeds these results back to the cross-domain service layer, the cross-domain service layer can further optimize the load and energy consumption prediction model based on the neural network based on the cross-domain execution results. Using the method of this disclosure, the cross-domain service layer can adjust the correction magnitude of the prediction model parameters according to the different energy consumption conditions of the network data, thereby further improving the prediction accuracy of the optimized cross-domain service layer. Furthermore, the method of this disclosure automatically constructs a monitoring model, i.e., a load and energy consumption prediction model based on a neural network, based on the closed-loop data corresponding to the network scenario and network data, thereby achieving comprehensive analysis of all network devices in a multimodal network without relying on manual adjustments, thus improving the efficiency of network prediction.

[0065] In some embodiments of this disclosure, the network device can also be divided into a data layer network device and a control layer network device. By splitting the centralized network device into a data layer and a control layer, the problem of concentrated traffic and difficulty in management can be solved, and the reliability of the implementation of this method can be guaranteed.

[0066] Specifically, before the step of the multimodal network data lake receiving current network data uploaded by network devices when the network state changes from the cross-domain service layer in this method, the method may further include: the data layer network device reporting the current network data to the control layer network device for aggregation when the network state changes; and the control layer network device reporting the aggregated network data to the cross-domain service layer.

[0067] Furthermore, after the cross-domain service layer generates the cross-domain energy-saving strategy, the method may further include: the cross-domain service layer distributing the cross-domain energy-saving strategy to the control layer network device of the single-domain network or multi-domain network to execute the cross-domain energy-saving strategy to obtain the pre-processed energy-saving strategy; and the control layer network device of the single-domain network or multi-domain network sending the pre-processed energy-saving strategy to its respective corresponding data layer network device.

[0068] Furthermore, after the data layer network device executes the cross-domain energy-saving strategy, the method may further include: the data layer network device of the single-domain network or multi-domain network executes the cross-domain energy-saving strategy to obtain the cross-domain execution result, and sends the cross-domain execution result to the control layer network device of the single-domain network or multi-domain network for aggregation; the control layer network device of the single-domain network or multi-domain network feeds back the aggregation result to the cross-domain service layer, the cross-domain execution result including: the current network data after the data layer network device of the single-domain network or multi-domain network executes the task; and the cross-domain service layer sends the cross-domain execution result to the multimodal network data lake.

[0069] To further illustrate the intelligent energy consumption management method based on multimodal networks disclosed herein, the following description uses module instruction interaction diagrams of single-domain and multi-domain networks as examples:

[0070] Figure 4 An embodiment of the method disclosed herein applied to a single-domain network is shown, involving modules including: a data layer network device 400a, a control layer network device 400b, a cross-domain service layer state awareness module 400c, a resource adaptation module 400d, and a multimodal data lake 400e. The method flow is as follows:

[0071] In step S402, the data layer network device 400a of the single-domain network reports the current network data to the control layer network device 400b for aggregation when the network status changes.

[0072] There can be one or more data layer network devices.

[0073] In step S404, the control layer network device 400b reports the aggregated network data to the cross-domain service layer state awareness module 400c.

[0074] In step S406, the multimodal network data lake 400e receives current network data from the state awareness module 400c of the cross-domain service layer.

[0075] In step S408, the multimodal network data lake 400e updates the current network data.

[0076] In step S410, the state awareness module 400c of the cross-domain service layer periodically sends resource query requests to the multimodal network data lake 400e. These resource query requests are used to query the current network data and historical network data of the network devices.

[0077] In step S412, the multimodal network data lake 400e returns current network data and historical network data to the state awareness module 400c of the cross-domain service layer.

[0078] In step S414, the state perception module 430 performs load and energy consumption prediction.

[0079] In some embodiments of this disclosure, the specific process may include: preprocessing, feature extraction, model training and evaluation of the extracted historical network data by the state awareness module 400c of the cross-domain service layer to establish a load and energy consumption prediction model; inputting the collected current network data into the trained neural network-based load and energy consumption prediction model to perform cross-domain collaborative correlation analysis and location to obtain prediction results.

[0080] In step S416, the prediction results are sent to the resource adaptation module 400d of the cross-domain service layer.

[0081] In step S418, the resource adaptation module 400d of the cross-domain service layer formulates a cross-domain energy-saving strategy based on the resources involved in the network devices in the single-domain network.

[0082] For details on the process of prediction and perception based on network data, please refer to [link to relevant documentation]. Figure 2 and Figure 3 The description and related embodiments are not repeated here.

[0083] In step S420, the cross-domain service layer resource adaptation module 400d sends the cross-domain energy-saving strategy to the control layer network device 400b of the single-domain network to execute the cross-domain energy-saving strategy and obtain the pre-processed energy-saving strategy.

[0084] In step S422, the control layer network device 400b of the single-domain network sends the preprocessed energy-saving strategy to the corresponding data layer network device 400a.

[0085] In step S424, the data layer network device 400a of the single-domain network executes the cross-domain energy-saving strategy to obtain the cross-domain execution result, and sends the cross-domain execution result to the control layer network device 400b for aggregation.

[0086] In step S426, the control layer network device 400b feeds back the summary results to the cross-domain service layer state awareness module 430. The cross-domain execution results include the current network data after the data layer network device 400a of the single-domain network has executed the task.

[0087] In some embodiments of this disclosure, the cross-domain service layer optimizes the neural network-based load and energy consumption prediction model based on the cross-domain execution results of the single-domain network.

[0088] In step S428, the state awareness module 430 of the cross-domain service layer sends the cross-domain execution result to the multimodal network data lake.

[0089] Figure 5An embodiment of the method disclosed herein applied to a multi-domain network is shown, involving the following modules: Domain A-data layer network device 500a, Domain A-control layer network device 500b, Domain B-data layer network device 500c, Domain B-control layer network device 500d, a cross-domain service layer state awareness module 500e, a resource adaptation module 500f, and a multimodal data lake 500h. The method flow is as follows:

[0090] In step S502, when the network status changes, the domain A-data layer network device 500a reports the current network data to the domain A-control layer network device 500b for aggregation.

[0091] In step S504, the domain A-control layer network device 500b reports the aggregated network data to the cross-domain service layer state awareness module 500e.

[0092] In step S506, when the network status changes, the domain B-data layer network device 500c reports the current network data to the domain B-control layer network device 500d for aggregation.

[0093] In step S508, the domain B-control layer network device 500d reports the aggregated network data to the cross-domain service layer state awareness module 500e.

[0094] In step S510, the multimodal network data lake 500h receives the current network data uploaded by the state awareness module 500e from the cross-domain service layer state awareness module 500e.

[0095] In step S512, the current network data is updated by the multimodal network data lake 500h.

[0096] In step S514, the state awareness module 500e of the cross-domain service layer periodically sends resource query requests to the multimodal network data lake 500h. These resource query requests are used to query the current network data and historical network data of network devices in domain A and domain B.

[0097] In step S516, the multimodal network data lake 500h returns the current network data and historical network data to the state awareness module 500e of the cross-domain service layer.

[0098] In step S518, the state awareness module 500e of the cross-domain service layer preprocesses, extracts features, models, trains and evaluates the extracted historical network data to establish a load and energy consumption prediction model; the collected current network data is input into the trained neural network-based load and energy consumption prediction model to perform cross-domain collaborative correlation analysis and localization to obtain the prediction results.

[0099] In step S520, the state awareness module 500e of the cross-domain service layer sends the prediction result to the resource adaptation module 500f.

[0100] In step S522, the resource adaptation module 500f of the cross-domain service layer formulates a cross-domain energy-saving strategy for domains A and B based on the resources and devices involved in domains A and B.

[0101] In step S524, the cross-domain service layer resource adaptation module 500f sends the cross-domain energy-saving policy of domain B to the domain B-control layer network device 500d to execute the cross-domain energy-saving policy.

[0102] In step S526, the domain B-control layer network device 500d sends the preprocessed energy-saving strategy to its respective domain B-data layer network device 500c.

[0103] In step S528, the cross-domain energy-saving strategy is executed by the domain B-data layer network device 500c to obtain the cross-domain execution result, and the cross-domain execution result is sent to the domain B-control layer network device 500d for aggregation.

[0104] In step S530, the cross-domain service layer resource adaptation module 500f distributes the cross-domain energy-saving policy of domain A to the domain A-control layer network device 500b to execute the cross-domain energy-saving policy.

[0105] In step S532, the preprocessed energy-saving strategy is sent by the domain A-control layer network device 500b to the corresponding domain B-data layer network device 500a.

[0106] In step S534, the cross-domain energy-saving strategy is executed by the domain A-data layer network device 500a to obtain the cross-domain execution result, and the cross-domain execution result is sent to the domain A-control layer network device 500b for aggregation.

[0107] In some embodiments of this disclosure, the cross-domain service layer optimizes the neural network-based load and energy consumption prediction model based on the cross-domain execution results of the multi-domain network.

[0108] In step S536, the state awareness module 500e of the cross-domain service layer sends the cross-domain execution result to the multimodal network data lake 500h.

[0109] Figure 6 This diagram illustrates a network architecture of an intelligent energy consumption management system based on a multimodal network, according to an embodiment of this disclosure. Figure 6As shown, system 600 may include: a network device layer 610, a cross-domain service layer 620, and a multimodal network data lake 630. The multimodal network data lake 630 is used to receive network data uploaded by network devices in the network device layer 610 when the network state changes, from the cross-domain service layer 620. The cross-domain service layer 620 is used to periodically send resource query requests to the data lake, which are used to query the current network data and historical network data of the network devices in the network device layer 610; predict the network data for the next moment based on the current and historical network data, and formulate corresponding cross-domain energy-saving strategies based on the network data; and distribute the cross-domain energy-saving strategies to the network devices in the network device layer 610 for execution.

[0110] In some embodiments of this disclosure, the network devices in the network device layer may come from one or more of a single-domain or multi-domain network, such as an IP domain, a transport network domain, and a passive optical network domain.

[0111] In the case of multiple domains, the addressing and routing modes of network devices in each domain can be the same or different. The addressing and routing modes can include multiple modes based on identifiers such as IP 6102a / 6102b, content 6104a / 6104b, identity 6106a / 6106b, and geospatial 6108a / 6108b.

[0112] In some embodiments of this disclosure, the cross-domain service layer 620 is also used to preprocess, extract features, model, train and evaluate the extracted historical network data, and establish a load and energy consumption prediction model; the cross-domain service layer inputs the collected current network data into the trained neural network-based load and energy consumption prediction model for cross-domain collaborative correlation analysis and positioning; and formulates cross-domain energy-saving strategies based on the resources involved in the network devices of the network device layer 610.

[0113] In some embodiments of this disclosure, the network device layer 610 is further configured to execute cross-domain energy-saving strategies to obtain cross-domain execution results and feed back the cross-domain execution results to the cross-domain service layer. The cross-domain execution results include: the current network data after the network device of the network device layer 610 executes the task; and the cross-domain service layer is further configured to send the cross-domain execution results to the multimodal network data lake.

[0114] In some embodiments of this disclosure, the cross-domain service layer 620 is also used to optimize the neural network-based load and energy consumption prediction model based on the cross-domain execution results.

[0115] In some embodiments of this disclosure, the network device layer 610 may further include a control layer 610a and a data layer 610b. In this case, the network device layer 610 may also be used to: have the data layer 610b network device report the current network data to the control layer 610a network device for aggregation when the network state changes; and have the control layer 610a network device report the aggregated network data to the cross-domain service layer.

[0116] In some embodiments of this disclosure, the cross-domain service layer 620 can also be used to distribute cross-domain energy-saving policies to the control layer 610a network device to execute the cross-domain energy-saving policies and obtain pre-processed energy-saving policies; and the control layer 610a network device can send the pre-processed energy-saving policies to their respective data layer 610b network devices.

[0117] In some embodiments of this disclosure, the data layer 610b is also used to execute cross-domain energy-saving strategies to obtain cross-domain execution results, and send the cross-domain execution results to the control layer 610a network device for aggregation; the control layer 610a network device feeds back the aggregation results to the cross-domain service layer, and the cross-domain execution results include: the current network data after the data layer 610b network device executes the task; the cross-domain service layer 620 sends the cross-domain execution results to the multimodal network data lake 630.

[0118] In some embodiments of this disclosure, the cross-domain service layer 620 includes a state awareness module 6202 and a resource adaptation module 6204. The cross-domain service layer 620 can also be used for: preprocessing, feature extraction, model training, and evaluation of extracted historical network data by the state awareness module 6202 to establish a load and energy consumption prediction model; inputting the collected current network data into the trained neural network-based load and energy consumption prediction model for cross-domain collaborative correlation analysis and location to obtain prediction results; sending the prediction results to the resource adaptation module 6204; and having the resource adaptation module 6204 formulate cross-domain energy-saving strategies based on the resources involved in the network devices.

[0119] In some embodiments of this disclosure, network data includes network configuration data and network indicator data collected from the network management system. The network configuration data includes network topology and device location-related parameters. The network indicator data includes the utilization rate and capacity of components such as CPU and memory that describe resources, the service request rate, service time, load cycle and traffic rate that describe the load, and the data throughput, service bandwidth and transmission latency that describe the performance. The data information of the power system and the environmental parameters of temperature and humidity sensors are also included.

[0120] Regarding the energy consumption intelligent management and control system 600 based on multimodal networks in the above embodiments, the specific methods by which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0121] Those skilled in the art will understand that various aspects of this disclosure can be implemented as a system, method, or program product. Therefore, various aspects of this disclosure can be specifically implemented in the following forms: a completely hardware implementation, a completely software implementation (including firmware, microcode, etc.), or a combination of hardware and software aspects, collectively referred to herein as a "circuit," "module," or "system."

[0122] The following reference Figure 7 To describe an electronic device 700 according to such an embodiment of the present disclosure. Figure 7 The electronic device 700 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.

[0123] like Figure 7 As shown, the electronic device 700 is manifested in the form of a general-purpose computing device. The components of the electronic device 1000 may include, but are not limited to: at least one processing unit 710, at least one storage unit 720, and a bus 730 connecting different system components (including storage unit 720 and processing unit 710).

[0124] The storage unit stores program code that can be executed by the processing unit 710, causing the processing unit 710 to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of this disclosure. For example, the processing unit 710 can perform actions such as... Figure 1 In step S110, the multimodal network data lake receives current network data uploaded by network devices when the network state changes from the cross-domain service layer; in step S120, the cross-domain service layer periodically sends resource query requests to the multimodal network data lake, which are used to query the current network data and historical network data of the network devices; in step S130, the cross-domain service layer predicts the network data at the next moment based on the current network data and historical network data, and formulates corresponding cross-domain energy-saving strategies based on the network data; in step S140, the cross-domain service layer distributes the cross-domain energy-saving strategies to the network devices for execution.

[0125] Storage unit 720 may include readable media in the form of volatile storage units, such as random access memory (RAM) 721 and / or cache memory 722, and may further include read-only memory (ROM) 723.

[0126] The storage unit 720 may also include a program / utility 724 having a set (at least one) of program modules 725, including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0127] Bus 730 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0128] Electronic device 700 can also communicate with one or more external devices (e.g., keyboard, pointing device, Bluetooth device, etc.), one or more devices that enable a user to interact with electronic device 700, and / or any device that enables electronic device 700 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 750. Furthermore, electronic device 700 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 760. As shown, network adapter 760 communicates with other modules of electronic device 700 via bus 730. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 700, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0129] In exemplary embodiments of this disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the methods described above is stored. In some possible implementations, various aspects of this disclosure may also be implemented as a program product including program code that, when the program product is run on a terminal device, causes the terminal device to perform the steps of the various exemplary embodiments of this disclosure described in the "Exemplary Methods" section above.

[0130] The program product for implementing the above-described method according to embodiments of the present disclosure may employ a portable compact disc read-only memory (CD-ROM) and include program code, and may run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto. In this document, the readable storage medium may be any tangible medium containing or storing a program that may be used or used in conjunction with an instruction execution system, server, terminal, or device.

[0131] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, server, terminal, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable 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 thereof.

[0132] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting programs for use by or in conjunction with an instruction execution system, server, terminal, or device.

[0133] The program code contained on the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0134] Program code for performing the operations of this disclosure can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device 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 computing device (e.g., via the Internet using an Internet service provider).

[0135] According to one aspect of this disclosure, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the methods provided in various optional implementations of the above embodiments.

[0136] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0137] Furthermore, although the steps of the method in this disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps may be omitted, multiple steps may be combined into one step, and / or a step may be broken down into multiple steps.

[0138] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, mobile terminal, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0139] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the appended claims.

Claims

1. A method for intelligent energy consumption management based on multimodal networks, characterized in that, The method includes: The multimodal network data lake receives current network data uploaded by network devices when the network state changes from the cross-domain service layer. The network devices come from single-domain or multi-domain networks. The cross-domain service layer includes a state awareness module and a resource adaptation module. The state awareness module of the cross-domain service layer periodically sends resource query requests to the multimodal network data lake. The resource query requests are used to query the current network data and historical network data of the network devices. The resource adaptation module of the cross-domain service layer predicts the network data for the next moment based on the current network data and historical network data, and formulates corresponding cross-domain energy-saving strategies based on the network data; and The cross-domain service layer distributes the cross-domain energy-saving policy to the network device for execution.

2. The energy consumption intelligent management and control method based on multimodal networks according to claim 1, characterized in that, The steps of the cross-domain service layer predicting the network data for the next moment based on the current network data and historical network data, and formulating corresponding cross-domain energy-saving strategies based on the network data, include: The cross-domain service layer preprocesses, extracts features from, models, trains, and evaluates the extracted historical network data to establish a load and energy consumption prediction model. The cross-domain service layer inputs the collected current network data into a pre-trained neural network-based load and energy consumption prediction model for cross-domain collaborative correlation analysis and localization; and The cross-domain service layer formulates the cross-domain energy-saving strategy based on the resources involved in the network device.

3. The energy consumption intelligent management and control method based on multimodal networks according to claim 1, characterized in that, The method further includes: The network device executes the cross-domain energy-saving strategy to obtain a cross-domain execution result, and feeds the cross-domain execution result back to the cross-domain service layer. The cross-domain execution result includes: the current network data after the network device executes the task. The cross-domain service layer sends the cross-domain execution result to the multimodal network data lake.

4. The energy consumption intelligent management and control method based on multimodal networks according to claim 2, wherein the network device executes the cross-domain energy-saving strategy to obtain the cross-domain execution result, and feeds back the cross-domain execution result to the cross-domain service layer, and after the step of the network device collecting current network data after executing the task, the method further includes: The cross-domain service layer optimizes the neural network-based load and energy consumption prediction model based on the cross-domain execution results.

5. The energy consumption intelligent management and control method based on multimodal networks according to claim 1, characterized in that, The network devices include data layer network devices and control layer network devices. Before the step of the multimodal network data lake receiving current network data uploaded by the network devices when the network state changes from the cross-domain service layer, the method further includes: When the network state changes, the data layer network device reports the current network data to the control layer network device for aggregation. The control layer network device reports the aggregated network data to the cross-domain service layer.

6. The energy consumption intelligent management and control method based on multimodal networks according to claim 5, characterized in that, The steps by which the cross-domain service layer distributes the cross-domain energy-saving policy to the network device for execution include: The cross-domain service layer distributes the cross-domain energy-saving policy to the control layer network device for execution to obtain a pre-processed energy-saving policy; and The control layer network devices send the preprocessing energy-saving strategy to their respective data layer network devices.

7. The energy consumption intelligent management and control method based on multimodal networks according to claim 6, characterized in that, The method further includes: The data layer network device executes the cross-domain energy-saving strategy to obtain the cross-domain execution result, and sends the cross-domain execution result to the control layer network device for aggregation; The control layer network device feeds back the aggregated results to the cross-domain service layer. The cross-domain execution results include: the current network data after the data layer network device executes the task. The cross-domain service layer sends the cross-domain execution result to the multimodal network data lake.

8. The intelligent energy consumption control method based on multimodal networks according to claim 1, characterized in that, The steps of the resource adaptation module of the cross-domain service layer predicting the network data for the next moment based on the current network data and historical network data, and formulating corresponding cross-domain energy-saving strategies based on the network data include: The state-aware module of the cross-domain service layer preprocesses, extracts features, models, trains, and evaluates the extracted historical network data to establish a load and energy consumption prediction model; the collected current network data is input into the pre-trained neural network-based load and energy consumption prediction model for cross-domain collaborative correlation analysis and localization to obtain prediction results; the prediction results are then sent to the resource adaptation module; and The resource adaptation module formulates the cross-domain energy-saving strategy based on the resources involved in the network device.

9. The intelligent energy consumption management method based on multimodal networks according to claim 1, characterized in that, The network data includes network configuration data and network indicator data collected from the network management system. The network configuration data includes network topology and device location-related parameters. The network indicator data includes CPU and memory component utilization and capacity, which describe resources; service request rate, service time, load cycle and traffic rate, which describe load; and data throughput, service bandwidth and transmission latency, which describe performance. The network data also includes power system data and environmental parameters from temperature and humidity sensors.

10. An intelligent energy consumption management and control system based on multimodal networks, characterized in that, The system includes: a network device layer, a cross-domain service layer, and a multimodal network data lake. The cross-domain service layer includes a state awareness module and a resource adaptation module. The multimodal network data lake is used to receive network data uploaded by network devices from the network device layer when the network state changes, wherein the network devices come from a single-domain or multi-domain network. The state awareness module of the cross-domain service layer is used to periodically send resource query requests to the data lake. The resource query requests are used to query the current network data and historical network data of the network devices in the network device layer. The resource adaptation module of the cross-domain service layer is used to predict the network data at the next moment based on the current network data and historical network data, and formulate corresponding cross-domain energy-saving strategies according to the network data; and to send the cross-domain energy-saving strategies to the network devices of the network device layer to execute the cross-domain energy-saving strategies.

11. An electronic device, characterized in that, include: processor; as well as Memory for storing the executable instructions of the processor; The processor is configured to execute the energy consumption intelligent management method based on a multimodal network as described in any one of claims 1 to 9 by executing the executable instructions.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the intelligent energy consumption control method based on multimodal networks as described in any one of claims 1 to 9.

Images