LU505330B1 - Low power consumption control method for switching equipment based on business sensing and same - Google Patents
Low power consumption control method for switching equipment based on business sensing and same Download PDFInfo
- Publication number
- LU505330B1 LU505330B1 LU505330A LU505330A LU505330B1 LU 505330 B1 LU505330 B1 LU 505330B1 LU 505330 A LU505330 A LU 505330A LU 505330 A LU505330 A LU 505330A LU 505330 B1 LU505330 B1 LU 505330B1
- Authority
- LU
- Luxembourg
- Prior art keywords
- switching equipment
- business
- neural network
- recurrent neural
- bidirectional recurrent
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 230000002457 bidirectional effect Effects 0.000 claims abstract description 69
- 230000000306 recurrent effect Effects 0.000 claims abstract description 69
- 238000013528 artificial neural network Methods 0.000 claims abstract description 67
- 230000008569 process Effects 0.000 claims description 28
- 210000002569 neuron Anatomy 0.000 claims description 18
- 238000010200 validation analysis Methods 0.000 claims description 12
- 238000002372 labelling Methods 0.000 claims description 6
- 230000001537 neural effect Effects 0.000 claims description 2
- 230000006870 function Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
- G06F1/26—Power supply means, e.g. regulation thereof
- G06F1/32—Means for saving power
- G06F1/3203—Power management, i.e. event-based initiation of a power-saving mode
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Power Engineering (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Public Health (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- General Engineering & Computer Science (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
Provided are a low power consumption control method for switching equipment based on business sensing and the switching equipment, belonging to the technical field of smart grids, including the following steps of: setting a judgment standard that the switching equipment works in high load and low load, and is in a dormant state, and respectively formulating a power control scheme when the switching equipment is in the three states; establishing various business types of feature databases of the switching equipment, and summarizing various business types of processing operation requirements into a table; and establishing and training a bidirectional recurrent neural network, calculating a total value of the processing operation requirements corresponding to the business type outputted by the bidirectional recurrent neural network during the same period, comparing the total value with the judgment standard to confirm the working state thereof, and executing the corresponding power control scheme.
Description
Y20P21LU-YUVO21LU 17.10.2023
LOW POWER CONSUMPTION CONTROL METHOD FOR SWITCHING LU505330
EQUIPMENT BASED ON BUSINESS SENSING AND SAME
[0001] The present disclosure belongs to the technical field of smart grids, and particularly relates to a low power consumption control method for switching equipment based on business sensing and the switching equipment.
[0002] With the gradual application of various communication system circuit components in the power grid field, the corresponding switching equipment, such as a gateway, is also gradually applied at an end of a power transmission line. However, considering the severe working environment and the difficulty in fetching power of the switching equipment at a side of the power transmission line, therefore strict requirements are proposed for its standby time; and a related low power control scheme is temporarily unavailable for the existing switching equipment. Therefore, how to overcome the shortcomings in the prior art is a problem to be urgently solved in the technical field of the current smart grids.
[0003] The objective of the present disclosure is to solve the shortcomings in the prior art and to provide a low power consumption control method for switching equipment based on business sensing; and the method performs business sensing based on received business data, to calculate an operation processing demand required by a received business type, thereby confirming a working state thereof, executing a corresponding working scheme and meeting a low power consumption control requirement on the switching equipment.
[0004] In order to achieve the above purpose, the present disclosure adopts the following technical solution: a low power consumption control method for switching equipment based on business sensing, including the following steps of: setting a judgment standard that the switching equipment works in high load and low load, and is in a dormant state, and respectively formulating a power control scheme when the switching equipment works in the high load and low load, and is in the dormant state; establishing various business types of feature databases of the switching equipment, and summarizing various business types of processing operation requirements into a table; and 1
Y20P21LU-YUVO21LU 17.10.2023 establishing and training a bidirectional recurrent neural network, inputting a feature, 3595330 value of business data of the switching equipment into the bidirectional recurrent neural network, the bidirectional recurrent neural network outputting a business type corresponding to the business data, calculating a total value of the processing operation requirements corresponding to the business type outputted by the bidirectional recurrent neural network during the same period, comparing the total value with the judgment standard that the switching equipment works in the high load and low load, and is in the dormant state, to confirm the working state thereof, and then executing the corresponding power control scheme.
[0005] Further preferably, the judgment standard that the switching equipment works in the high load is [50%, 100%] of the full-load working, the judgment standard that the switching equipment works in the low load is [10%, 50%) of the full-load working, and the judgment standard that the switching equipment is in the dormant state is [0%, 10%) of the full-load working.
[0006] Further preferably, the specific method for establishing various business types of feature databases of the switching equipment is as follows: parsing processing is performed through message data corresponding to various business types, that is, the feature value thereof may be obtained, and each business types obtains one feature database.
[0007] Further preferably, the specific process for training the bidirectional recurrent neural network is as follows: sample data is intercepted, the sample data includes training data and validation data, the sample data is parsed to obtain the feature value thereof, and the feature value is subjected to manual labeling of the business type; and while training the bidirectional recurrent neural network, the feature value is used as input, and the business type corresponding to the manually labeled feature value is used as output; and the feature value of the training data is input to the bidirectional recurrent neural network, an output value of each nerve cell is calculated based on a forward propagation algorithm, a weight in the bidirectional recurrent neural network is updated according to the output value and based on a back propagation algorithm, the above process for calculating the output value of each nerve cell and updating the weight is repeatedly executed until a total number of executions reach a reset number of time, the feature of the validation data is input to the bidirectional recurrent neural network to obtain an accuracy of recognition, the above process for calculating the output value of each nerve cell and updating the weight is repeatedly executed until a total number of times reach a reset number of time, and the 2
Y20P21LU-YUVO21LU 17.10.2023 process for obtaining the accuracy is repeatedly executed until the obtained accuracy is, y505330 greater than or equal to a preset threshold value.
[0008] Further preferably, the type of the feature value of the business type needed to be transmitted is mutually labeled as 1, the type of the feature value of the business type needed to be processed is mutually labeled as 0, the preset number of times is 1,000 times, and the preset threshold value 1s 0.9.
[0009] Meanwhile, the present disclosure provides switching equipment, including a data module, a working state determining module and a power control module; where the data module is configured to establish various business types of feature databases of the switching equipment, and to summarize various business types of processing operation requirements into a table; the working state determining module is configured to establish and train a bidirectional recurrent neural network, to input a feature value of business data of the switching equipment into the bidirectional recurrent neural network, where the bidirectional recurrent neural network outputs a business type corresponding to the business data, to calculate a total value of the processing operation requirements corresponding to the business type outputted by the bidirectional recurrent neural network during the same period, to compare the total value with the judgment standard that the switching equipment works in the high load and low load, and is in the dormant state, to confirm the working state thereof; and the power control module is configured to formulate a power control scheme when the switching equipment works in the high load and low load, and is in the dormant state; and to execute the corresponding power control scheme after the working state determining module determines the working state.
[0010] Further preferably, the judgment standard that the switching equipment works in the high load is [50%, 100%] of the full-load working, the judgment standard that the switching equipment works in the low load is [10%, 50%) of the full-load working, and the judgment standard that the switching equipment is in the dormant state is [0%, 10%) of the full-load working.
[0011] Further preferably, the specific process for training the bidirectional recurrent neural network is as follows: sample data is intercepted, the sample data includes training data and validation data, the sample data is parsed to obtain the feature value thereof, and the feature value is subjected to manual labeling of the business type; and while training the bidirectional recurrent neural network, the feature value is used as input, and the business type corresponding to the 3
Y20P21LU-YUVO21LU 17.10.2023 manually labeled feature value 1s used as output; and LU505330 the feature value of the training data is input to the bidirectional recurrent neural network, an output value of each nerve cell is calculated based on a forward propagation algorithm, a weight in the bidirectional recurrent neural network is updated according to the output value and based on a back propagation algorithm, the above process for calculating the output value of each nerve cell and updating the weight is repeatedly executed until a total number of executions reach a reset number of time, the feature of the validation data is input to the bidirectional recurrent neural network to obtain an accuracy of recognition, the above process for calculating the output value of each nerve cell and updating the weight is repeatedly executed until a total number of times reach a reset number of time, and the process for obtaining the accuracy is repeatedly executed until the obtained accuracy is greater than or equal to a preset threshold value.
[0012] In the present disclosure, the power control scheme when the switching equipment works in the high load and low load, and is in the dormant state is formulated according to the existing method and not limited herein. That is, a power control range is available in different states, and after the range is formulated herein, each component of the switching equipment is subjected to power distribution according to the power control range, ensuring to not affect the component that shall play a role in each state.
[0013] In the present disclosure, the switching equipment generally receives the data sent by the terminal, a part of the data needs to be transmitted and the other part of data needs to be processed by the switching equipment; and the message data corresponding to various business types is subjected to parsing processing herein, and then the feature value thereof is obtained, thereby forming the feature database.
[0014] In the present disclosure, summarizing various business types of processing operation requirements into the table is specifically as follows: the transmitted business type needs to occupy the memory space of the switching equipment; the business type needed to be processed by the switching equipment needs to occupy the memory space of the switching equipment; and summarization is performed according to various business types, in order to form the table.
[0015] In the present disclosure, calculating the total value of the processing operation requirements corresponding to the business type outputted by the bidirectional recurrent neural network during the same period is specifically as follows: the bidirectional recurrent neural network may automatically obtain the corresponding business type thereof through the input data, and the total value of the processing operation requirements during this period 4
Y20P21LU-YUVO21LU 17.10.2023 may be known according to the foregoing summarization. LU505330
[0016] Compared with the prior art, the present disclosure has the following beneficial effects:\ (1) The method provided by the present disclosure performs business sensing based on received business data, calculates an operation processing demand required by a received business type, thereby confirming a working state thereof, executing a corresponding working scheme and meeting a low power consumption control requirement on the switching equipment.
[0017] (2) In the present disclosure, the bidirectional recurrent neural network is applied in the sensing recognition of the business type, the bidirectional recurrent neural network has characteristics of memory, parameter sharing and turing-complete, so the bidirectional recurrent neural network has a certain advantages when learning nonlinear characteristics of the business data stream, and the accuracy of the recognition may be improved.
[0018] To better clarify the embodiment of the present disclosure or the technical solution in the prior art, the drawings required to illustrate the embodiments or the prior art will be simply described below. It is apparent that the drawings described below merely illustrate some embodiments of the present disclosure. Those ordinarily skilled in the art can obtain other drawings according to these drawings without contributing creative labor on the basis of those drawings.
[0019] FIG. 1 shows a flow diagram of a low power consumption control method for switching equipment based on business sensing.
[0020] FIG. 2 is a structure schematic diagram of switching equipment.
[0021] The present disclosure is further described in combination with embodiments below.
[0022] Those skilled in the art shall understand that the following embodiments are merely used for explaining the present disclosure, not regarded as a limitation to the scope of the present disclosure. Those that the specific technologies or conditions are not marked in embodiments shall be performed according to the technologies or conditions described by literatures in the field or according to the product specification. All material or apparatuses, without indicating manufacturers, may all conventional products purchased on the market.
[0023] Those skilled in the art may understand that, unless otherwise specified, singular
Y20P21LU-YUVO21LU 17.10.2023 forms "a/an", "one", "the" and “this” are also intended to include the plural forms. It is further, | 505330 understood that term “include” used in the specification of the present disclosure means the feature, integer, step, operation, unit and/or component, but not excluding existing or added one or a plurality of features, integers, steps, operations, units and/or components and/or their combination. It is understood that when the unit is “connected” to another unit, it may be directly connected to other units, or there may be an intermediate unit. In addition, “connecting” used herein may include wireless connection. Terms “and/or” used herein include any unit or all combinations of one or more associated list items.
[0024] In the description of the present disclosure, “a plurality of” means two or above two, unless specific limitation otherwise. Orientation or state relationships indicated by the terms “inner, “upper”, “lower” and the like are based on the orientation or state relationships as shown in the drawings, for ease of describing the present disclosure and simplifying the description only, rather than indicating or implying that the mentioned apparatus or element necessarily has a particular orientation and must be constructed and operated in the particular orientation. Therefore, these terms should not be understood as limitations to the present disclosure.
[0025] In the description of the present disclosure, it is also noted that, unless specific regulation and limitation otherwise, terms “install”, “connect” and “set” should be generally understood, for example, may a fixed connection, or a detachable connection, or an integrated connection, may a mechanical connection or an electric connection, may a direct connection or an indirect connection through an intermediation. Those of ordinary skill in the art may understand the specific meaning of the terms in the disclosure according to specific conditions.
[0026] Those skilled in the art may understood, unless otherwise defined, all terms (including technical terms and scientific terms) used here have the same meaning as the general understanding of those of ordinary skill in the art. It is also understood that, for example, those terms defined in a general dictionary shall be understood as the same meaning consistent with that in the text of the prior art, and unless being defined herein, it cannot be explained in an ideal or formal meaning.
[0027] Embodiment 1
This embodiment provides a low power consumption control method for switching equipment based on business sensing, including the following steps of: setting a judgment standard that the switching equipment works in high load and low load, and is in a dormant state, and respectively formulating a power control scheme when the 6
Y20P21LU-YUVO21LU 17.10.2023 switching equipment works in the high load and low load, and is in the dormant state; LU505330 establishing various business types of feature databases of the switching equipment, and summarizing various business types of processing operation requirements into a table; and establishing and training a bidirectional recurrent neural network, inputting a feature value of business data of the switching equipment into the bidirectional recurrent neural network, the bidirectional recurrent neural network outputting a business type corresponding to the business data, calculating a total value of the processing operation requirements corresponding to the business type outputted by the bidirectional recurrent neural network during the same period, comparing the total value with the judgment standard that the switching equipment works in the high load and low load, and is in the dormant state, to confirm the working state thereof, and then executing the corresponding power control scheme.
[0028] Embodiment 2
This embodiment provides a low power consumption control method for switching equipment based on business sensing, as shown in FIG. 1, including the following steps of: setting a judgment standard that the switching equipment works in high load and low load, and is in a dormant state, and respectively formulating a power control scheme when the switching equipment works in the high load and low load, and is in the dormant state; establishing various business types of feature databases of the switching equipment, and summarizing various business types of processing operation requirements into a table; and establishing and training a bidirectional recurrent neural network, inputting a feature value of business data of the switching equipment into the bidirectional recurrent neural network, the bidirectional recurrent neural network outputting a business type corresponding to the business data, calculating a total value of the processing operation requirements corresponding to the business type outputted by the bidirectional recurrent neural network during the same period, comparing the total value with the judgment standard that the switching equipment works in the high load and low load, and is in the dormant state, to confirm the working state thereof, and then executing the corresponding power control scheme.
[0029] In a specific implementation process, the judgment standard that the switching equipment works in the high load is [50%, 100%] of the full-load working, the judgment standard that the switching equipment works in the low load is [10%, 50%) of the full-load working, and the judgment standard that the switching equipment is in the dormant state is [0%, 10%) of the full-load working. 7
Y20P21LU-YUVO21LU 17.10.2023
[0030] The specific method for establishing various business types of feature databases of, y505330 the switching equipment is as follows: parsing processing is performed through message data corresponding to various business types, that 1s, the feature value thereof may be obtained, and each business types obtains one feature database.
[0031] In a specific implementation process, the specific process for training the bidirectional recurrent neural network is as follows: sample data is intercepted, the sample data includes training data and validation data, the sample data is parsed to obtain the feature value thereof, and the feature value is subjected to manual labeling of the business type; and while training the bidirectional recurrent neural network, the feature value is used as input, and the business type corresponding to the manually labeled feature value is used as output; and the feature value of the training data is input to the bidirectional recurrent neural network, an output value of each nerve cell is calculated based on a forward propagation algorithm, a weight in the bidirectional recurrent neural network is updated according to the output value and based on a back propagation algorithm, the above process for calculating the output value of each nerve cell and updating the weight is repeatedly executed until a total number of executions reach a reset number of time, the feature of the validation data is input to the bidirectional recurrent neural network to obtain an accuracy of recognition, the above process for calculating the output value of each nerve cell and updating the weight is repeatedly executed until a total number of times reach a reset number of time, and the process for obtaining the accuracy is repeatedly executed until the obtained accuracy is greater than or equal to a preset threshold value.
[0032] The type of the feature value of the business type needed to be transmitted is mutually labeled as 1, the type of the feature value of the business type needed to be processed is mutually labeled as 0, the preset number of times is 1,000 times, and the preset threshold value is 0.9.
[0033] Embodiment 3
This embodiment provides switching equipment, as shown in FIG.2, including: a data module, a working state determining module and a power control module; where the data module is configured to establish various business types of feature databases of the switching equipment, and to summarize various business types of processing operation requirements into a table; the working state determining module is configured to establish and train a bidirectional recurrent neural network, to input a feature value of business data of the switching equipment 8
Y20P21LU-YUVO21LU 17.10.2023 into the bidirectional recurrent neural network, where the bidirectional recurrent neural LU505330 network outputs a business type corresponding to the business data, to calculate a total value of the processing operation requirements corresponding to the business type outputted by the bidirectional recurrent neural network during the same period, to compare the total value with the judgment standard that the switching equipment works in the high load and low load, and is in the dormant state, to confirm the working state thereof; and the power control module is configured to formulate a power control scheme when the switching equipment works in the high load and low load, and is in the dormant state; and to execute the corresponding power control scheme after the working state determining module determines the working state.
[0034] Embodiment 4
This embodiment provides switching equipment, as shown in FIG.2, the specific scheme is as follows: including a data module, a working state determining module and a power control module; where the data module is configured to establish various business types of feature databases of the switching equipment, and to summarize various business types of processing operation requirements into a table; the working state determining module is configured to establish and train a bidirectional recurrent neural network, to input a feature value of business data of the switching equipment into the bidirectional recurrent neural network, where the bidirectional recurrent neural network outputs a business type corresponding to the business data, to calculate a total value of the processing operation requirements corresponding to the business type outputted by the bidirectional recurrent neural network during the same period, to compare the total value with the judgment standard that the switching equipment works in the high load and low load, and is in the dormant state, to confirm the working state thereof; and the power control module is configured to formulate a power control scheme when the switching equipment works in the high load and low load, and is in the dormant state; and to execute the corresponding power control scheme after the working state determining module determines the working state.
[0035] In a specific implementation process, the judgment standard that the switching equipment works in the high load is [50%, 100%] of the full-load working, the judgment standard that the switching equipment works in the low load is [10%, 50%) of the full-load working, and the judgment standard that the switching equipment is in the dormant state is 9
Y20P21LU-YUVO21LU 17.10.2023 [0%, 10%) of the full-load working. LU505330
[0036] In a specific implementation process, the specific process for training the bidirectional recurrent neural network is as follows: sample data is intercepted, the sample data includes training data and validation data, the sample data is parsed to obtain the feature value thereof, and the feature value is subjected to manual labeling of the business type; and while training the bidirectional recurrent neural network, the feature value is used as input, and the business type corresponding to the manually labeled feature value is used as output; and the feature value of the training data is input to the bidirectional recurrent neural network, an output value of each nerve cell is calculated based on a forward propagation algorithm, a weight in the bidirectional recurrent neural network is updated according to the output value and based on a back propagation algorithm, the above process for calculating the output value of each nerve cell and updating the weight is repeatedly executed until a total number of executions reach a reset number of time, the feature of the validation data is input to the bidirectional recurrent neural network to obtain an accuracy of recognition, the above process for calculating the output value of each nerve cell and updating the weight is repeatedly executed until a total number of times reach a reset number of time, and the process for obtaining the accuracy is repeatedly executed until the obtained accuracy is greater than or equal to a preset threshold value.
[0037] The type of the feature value of the business type needed to be transmitted is mutually labeled as 1, the type of the feature value of the business type needed to be processed is mutually labeled as 0, the preset number of times is 1,000 times, and the preset threshold value is 0.9.
[0038] In the several embodiments provided in this application, it should be understood that the disclosed system, device and method may be implemented through other manners. For example, the embodiment of the device described above is merely an example. For example, the unit division is merely logical function division and may be other division in actual implementation. For example, a plurality of units or components may be combined or integrated into another system, or some features may be ignored or not performed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections may be implemented by using some interfaces. The indirect couplings or communication connections between the devices or units may be implemented in electronic, mechanical, or other forms.
[0039] The units described as separate parts may or may not be physically separate, and
Y20P21LU-YUVO21LU 17.10.2023 parts displayed as units may or may not be physical units, namely, may be located in one, 3505330 location, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the objective of the solutions of the embodiments.
[0040] In addition, functional units in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may have separate physical existence, or two or more units may be integrated in one unit. The integrated module may be implemented in a software form, or may be implemented in form of hardware and software function unit.
[0041] If the integrated unit is achieved in the form of software function units and sold or used as independent products, the function may be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present disclosure essentially, or the part contributing to the related art, or all or some of the technical solutions may be implemented in a form of a software product. The computer software product is stored in a storage medium, and includes a plurality of instructions for instructing a computer device (which may be a personal computer, a server, a network device, or the like) to perform all or some of the steps of the methods described in the embodiments of the present disclosure. The foregoing storage medium includes various media capable of storing a program code, such as a U disk, a mobile hard disk, a read only memory (ROM), a random access memory (RAM), a magnetic disk and a compact disc.
[0042] The basic principles, main characteristics and advantages of the present disclosure are shown and described above. Those skilled in the art shall understand that the present disclosure is not limited by the above embodiments, the above embodiments and specification describe the principles of the present disclosure merely. Various changes and improvements will be made without deviating from the spirit and scope of the present the disclosure, and all of these fall within the scope of protection of the present disclosure. The scope of protection of the present disclosure is defined by the appended claims and their equivalents. 11
Claims (8)
1. A low power consumption control method for switching equipment based on business sensing, comprising the following steps of: setting a judgment standard that the switching equipment works in high load and low load, and is in a dormant state, and respectively formulating a power control scheme when the switching equipment works in the high load and low load, and is in the dormant state; establishing various business types of feature databases of the switching equipment, and summarizing various business types of processing operation requirements into a table; and establishing and training a bidirectional recurrent neural network, inputting a feature value of business data of the switching equipment into the bidirectional recurrent neural network, the bidirectional recurrent neural network outputting a business type corresponding to the business data, calculating a total value of the processing operation requirements corresponding to the business type outputted by the bidirectional recurrent neural network during the same period, comparing the total value with the judgment standard that the switching equipment works in the high load and low load, and is in the dormant state, to confirm the working state thereof, and then executing the corresponding power control scheme.
2. The low power consumption control method for the switching equipment based on the business sensing according to claim 1, wherein the judgment standard that the switching equipment works in the high load is [50%, 100%] of the full-load working, the judgment standard that the switching equipment works in the low load is [10%, 50%) of the full-load working, and the judgment standard that the switching equipment is in the dormant state is [0%, 10%) of the full-load working.
3. The low power consumption control method for the switching equipment based on the business sensing according to claim 1, wherein the specific method for establishing various business types of feature databases of the switching equipment is as follows: parsing processing is performed through message data corresponding to various business types, that is, the feature value thereof is obtained, and each business types obtains one feature database.
4. The low power consumption control method for the switching equipment based on the business sensing according to claim 1, wherein the specific process for training the 12
Y20P21LU-YUVO21LU 17.10.2023 bidirectional recurrent neural network is as follows: LU505330 sample data is intercepted, the sample data comprises training data and validation data, the sample data is parsed to obtain the feature value thereof, and the feature value is subjected to manual labeling of the business type; and while training the bidirectional recurrent neural network, the feature value is used as input, and the business type corresponding to the manually labeled feature value is used as output; and the feature value of the training data is input to the bidirectional recurrent neural network, an output value of each nerve cell is calculated based on a forward propagation algorithm, a weight in the bidirectional recurrent neural network is updated according to the output value and based on a back propagation algorithm, the above process for calculating the output value of each nerve cell and updating the weight is repeatedly executed until a total number of executions reaches a reset number of times, the feature of the validation data is input to the bidirectional recurrent neural network to obtain an accuracy of recognition, the above process for calculating the output value of each nerve cell and updating the weight is repeatedly executed until a total number of times reaches a reset number of times, and the process for obtaining the accuracy is repeatedly executed until the obtained accuracy is greater than or equal to a preset threshold value.
5. The low power consumption control method for the switching equipment based on the business sensing according to claim 4, wherein the type of the feature value of the business type needed to be transmitted is mutually labeled as 1, the type of the feature value of the business type needed to be processed is mutually labeled as 0, the preset number of times is 1,000 times, and the preset threshold value is 0.9.
6. Switching equipment, comprising a data module, a working state determining module and a power control module; wherein the data module is configured to establish various business types of feature databases of the switching equipment, and to summarize various business types of processing operation requirements into a table; the working state determining module is configured to establish and train a bidirectional recurrent neural network, to input a feature value of business data of the switching equipment into the bidirectional recurrent neural network, wherein the bidirectional recurrent neural 13
Y20P21LU-YUVO21LU 17.10.2023 network outputs a business type corresponding to the business data, to calculate a total valueLU505330 of the processing operation requirements corresponding to the business type outputted by the bidirectional recurrent neural network during the same period, to compare the total value with the judgment standard that the switching equipment works in the high load and low load, and is in the dormant state, to confirm the working state thereof; and the power control module is configured to formulate a power control scheme when the switching equipment works in the high load and low load, and is in the dormant state; and to execute the corresponding power control scheme after the working state determining module determines the working state.
7. The switching equipment according to claim 6, wherein the judgment standard that the switching equipment works in the high load is [50%, 100%] of the full-load working, the judgment standard that the switching equipment works in the low load 1s [10%, 50%) of the full-load working, and the judgment standard that the switching equipment is in the dormant state 1s [0%, 10%) of the full-load working.
8. The switching equipment according to claim 6, wherein the specific process for training the bidirectional recurrent neural network is as follows: sample data is intercepted, the sample data comprises training data and validation data, the sample data is parsed to obtain the feature value thereof, and the feature value is subjected to manual labeling of the business type; and while training the bidirectional recurrent neural network, the feature value is used as input, and the business type corresponding to the manually labeled feature value is used as output; and the feature value of the training data is input to the bidirectional recurrent neural network, an output value of each nerve cell is calculated based on a forward propagation algorithm, a weight in the bidirectional recurrent neural network is updated according to the output value and based on a back propagation algorithm, the above process for calculating the output value of each nerve cell and updating the weight is repeatedly executed until a total number of executions reach a reset number of time, the feature of the validation data is input to the bidirectional recurrent neural network to obtain an accuracy of recognition, the above process for calculating the output value of each nerve cell and updating the weight is repeatedly executed until a total number of times reach a reset number of time, and the process for obtaining the accuracy is repeatedly executed until the obtained accuracy is greater than or equal to a preset threshold value. 14
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| LU505330A LU505330B1 (en) | 2023-10-19 | 2023-10-19 | Low power consumption control method for switching equipment based on business sensing and same |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| LU505330A LU505330B1 (en) | 2023-10-19 | 2023-10-19 | Low power consumption control method for switching equipment based on business sensing and same |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| LU505330B1 true LU505330B1 (en) | 2024-04-19 |
Family
ID=90790723
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| LU505330A LU505330B1 (en) | 2023-10-19 | 2023-10-19 | Low power consumption control method for switching equipment based on business sensing and same |
Country Status (1)
| Country | Link |
|---|---|
| LU (1) | LU505330B1 (en) |
-
2023
- 2023-10-19 LU LU505330A patent/LU505330B1/en active IP Right Grant
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11765653B2 (en) | Load threshold determining method and apparatus | |
| CN103401937A (en) | Log data processing method and system | |
| CN113795039B (en) | Operator network switching method, device, equipment and computer readable storage medium | |
| CN109309735B (en) | Connection processing method, server, system and storage medium | |
| LU505330B1 (en) | Low power consumption control method for switching equipment based on business sensing and same | |
| US20220276845A1 (en) | Systems and methods for consistent feature flag evaluation | |
| CN112615724B (en) | POE load priority power supply management system | |
| CN114240035B (en) | Switching equipment low-power consumption control method and switching device based on service awareness | |
| CN103997509A (en) | Service oriented architecture-based service processing method and apparatus | |
| CN113645088B (en) | Automatic regulation method, system, device and medium for network card NCSI signal | |
| CN114389969B (en) | Method and device for testing client, electronic equipment and storage medium | |
| CN116305806A (en) | Verification method, device, processing equipment and medium of simulation model | |
| CN115270670A (en) | Low-power-consumption design method and device of chip, terminal and storage medium | |
| CN114138358A (en) | Application program starting optimization method, device, equipment and storage medium | |
| CN114040485B (en) | Method for remote unit to open station, baseband unit, communication system and medium | |
| CN102812616B (en) | For running method and the power automation system of power automation system | |
| CN117312100B (en) | Power consumption adjustment method, system, device, equipment and computer storage medium | |
| US20210349516A1 (en) | Energy saving device and method for saving energy in data center | |
| CN113609145B (en) | Database processing method, device, electronic equipment, storage medium and product | |
| CN115292339B (en) | Database updating method, device, electronic equipment and storage medium | |
| CN203166536U (en) | Reactive compensation filter controller in power system | |
| CN115840604B (en) | Data processing method, device, electronic equipment and computer readable storage medium | |
| CN114675736B (en) | Power management method, electronic device, storage medium and system | |
| WO2023098094A1 (en) | Method for startup of remote units, baseband unit, communication system, and medium | |
| EP2833300A1 (en) | Power management of electronic devices configured to generate analytical reports |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| FG | Patent granted |
Effective date: 20240419 |