CN112714488A - Network energy saving method and device based on energy consumption data - Google Patents
Network energy saving method and device based on energy consumption data Download PDFInfo
- Publication number
- CN112714488A CN112714488A CN202011540759.0A CN202011540759A CN112714488A CN 112714488 A CN112714488 A CN 112714488A CN 202011540759 A CN202011540759 A CN 202011540759A CN 112714488 A CN112714488 A CN 112714488A
- Authority
- CN
- China
- Prior art keywords
- energy consumption
- network
- energy
- consumption data
- saving
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W52/00—Power management, e.g. TPC [Transmission Power Control], power saving or power classes
- H04W52/02—Power saving arrangements
- H04W52/0203—Power saving arrangements in the radio access network or backbone network of wireless communication networks
- H04W52/0206—Power saving arrangements in the radio access network or backbone network of wireless communication networks in access points, e.g. base stations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of communication, aims to solve the problem of excessive consumption of power resources of the conventional network base station, and provides a network energy-saving method and device based on energy consumption data, and the scheme mainly comprises the following steps: acquiring historical network energy consumption data of each energy consumption unit based on a time sequence through an intelligent energy consumption management platform; the training unit respectively trains according to historical network energy consumption data of each energy consumption unit based on the time sequence to respectively obtain a neural network model for predicting the network energy consumption of each energy consumption unit; and predicting energy consumption data of the corresponding energy consumption units in the prediction time period according to the neural network model, generating a corresponding energy-saving strategy according to the energy consumption data of each energy consumption unit in the prediction time period, and executing energy-saving operation by the energy-saving operation unit according to the energy-saving strategy. The invention not only enables the network base station to meet the network performance requirements of users, but also greatly reduces the power resource consumption of the network base station.
Description
Technical Field
The invention relates to the technical field of communication, in particular to a network energy-saving method and device based on energy consumption data.
Background
In the field of industrial internet, the aims of energy conservation and consumption reduction of industrial equipment are fulfilled, green development is realized, cost reduction and efficiency improvement are realized, and the method is a key direction for enterprise development.
Due to the characteristics of the 5G network in the aspects of performance and wireless transmission, the energy consumption of the 5G network base station is 3-5 times of that of the 4G network, and the high energy consumption causes overhigh operation cost and excessive consumption of power resources at the initial stage of 5G service promotion. Therefore, in network operation, the 5G base station is urgently required to perform energy saving operation.
Disclosure of Invention
The invention aims to solve the problem of excessive consumption of power resources of the conventional network base station, and provides a network energy-saving method and device based on energy consumption data.
The technical scheme adopted by the invention for solving the technical problems is as follows: the network energy-saving method based on the energy consumption data comprises the following steps:
step 1, acquiring historical network energy consumption data of each energy consumption unit based on a time sequence through an intelligent energy consumption management platform;
step 2, training is respectively carried out according to historical network energy consumption data of each energy consumption unit based on the time sequence, and a neural network model for carrying out network energy consumption prediction on each energy consumption unit is respectively obtained;
and 3, predicting the energy consumption data of the corresponding energy consumption units in the prediction time period according to the neural network model, generating a corresponding energy-saving strategy according to the energy consumption data of each energy consumption unit in the prediction time period, and executing energy-saving operation according to the energy-saving strategy.
Further, step 2 is preceded by:
and obtaining an operation log and statistical data of the network manager, comparing the historical network energy consumption data with the operation log and the statistical data, and deleting the historical network energy consumption data in the abnormal time period.
Further, step 2 is preceded by:
and determining the time period of network operation and maintenance and network optimization, and deleting the historical network energy consumption data in the time period of network operation and network optimization.
Further, the historical energy consumption data includes at least: current, voltage and power.
Further, the method also comprises the following steps: and acquiring real-time energy consumption data of each energy consumption unit in real time, and correcting the corresponding neural network model according to the real-time energy consumption data.
On the other hand, the invention also provides a network energy-saving device based on energy consumption data, which comprises:
the intelligent energy consumption management platform is used for acquiring historical network energy consumption data of each energy consumption unit based on time series;
the training unit is used for respectively training according to historical network energy consumption data of each energy consumption unit based on the time sequence to respectively obtain a neural network model for predicting the network energy consumption of each energy consumption unit;
and the energy-saving operation unit is used for predicting the energy consumption data of the corresponding energy consumption units in the prediction time period according to the neural network model, generating a corresponding energy-saving strategy according to the energy consumption data of each energy consumption unit in the prediction time period, and executing energy-saving operation according to the energy-saving strategy.
The invention has the beneficial effects that: according to the energy consumption data-based network energy saving method and device, energy consumption prediction of independent hardware levels is carried out based on the energy consumption data acquired by the energy consumption Internet of things, and the overall load condition of a network is accurately analyzed, so that network energy saving is carried out, and the power resource consumption of a network base station is reduced.
Drawings
Fig. 1 is a schematic flowchart of a network energy saving method based on energy consumption data according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a network energy saving device based on energy consumption data according to an embodiment of the present invention.
Detailed Description
Embodiments of the present invention will be described in detail below.
The invention aims to solve the problem of excessive consumption of power resources of the conventional network base station, and provides a network energy-saving method and device based on energy consumption data. The device comprises an intelligent energy consumption management platform, a training unit and an energy-saving operation unit, and the main process is as follows: acquiring historical network energy consumption data of each energy consumption unit based on a time sequence through an intelligent energy consumption management platform; the training unit respectively trains according to historical network energy consumption data of each energy consumption unit based on the time sequence to respectively obtain a neural network model for predicting the network energy consumption of each energy consumption unit; and predicting energy consumption data of the corresponding energy consumption units in the prediction time period according to the neural network model, generating a corresponding energy-saving strategy according to the energy consumption data of each energy consumption unit in the prediction time period, and executing energy-saving operation by the energy-saving operation unit according to the energy-saving strategy.
Firstly, historical network energy consumption data of each energy consumption unit based on a time sequence are acquired through an intelligent energy consumption management platform, then a neural network model is obtained through training according to the obtained historical network energy consumption data, wherein each energy consumption unit corresponds to one neural network model, then, energy consumption prediction is carried out on each energy consumption unit according to the corresponding neural network model respectively to obtain energy consumption prediction data corresponding to each energy consumption unit, and then, a corresponding energy-saving strategy is generated and executed according to the energy consumption prediction data, so that the network base station not only can meet the network performance requirements of users, but also can reduce the power resource consumption of the network base station.
Examples
The network energy saving method based on energy consumption data, as shown in fig. 1, includes the following steps:
specifically, in the energy consumption optimization process, traffic prediction and relevance judgment with respect to network performance are important components of energy consumption optimization. The AI prediction of the energy consumption data reflects the overall load condition of the network.
AI prediction based on energy consumption data mainly comprises the following steps:
step S1, acquiring historical network energy consumption data of each energy consumption unit based on time series through an intelligent energy consumption management platform;
specifically, energy consumption data of the 5G AAU radio frequency units, including current, voltage and power, are collected through an intelligent energy consumption management platform, uploaded and analyzed to an energy consumption database, and historical energy consumption data based on a time sequence are formed corresponding to each energy consumption unit.
Meanwhile, the energy consumption data of the 5G cell not only depends on the traffic volume, but also comprises signaling data energy consumption and transmission energy consumption; meanwhile, the energy consumption of wireless resources and the energy consumption of hardware resources form different energy consumption rules under the scheduling method of different devices. Therefore, the energy consumption management and the energy saving are carried out by simply considering wireless network resources, and the limitation exists.
In order to solve the above problem, the present embodiment further includes:
s11, obtaining an operation log and statistical data of the network manager, comparing the historical network energy consumption data with the operation log and the statistical data, and deleting the historical network energy consumption data in an abnormal time period.
And S12, determining a time period of network operation and maintenance and network optimization, and deleting historical network energy consumption data in the time period of network operation and network optimization.
The historical energy consumption data are cleaned through the steps S11 and S12, data in abnormal time periods are eliminated, 5G service abnormal fluctuation is eliminated, energy consumption data influence caused by short-term service fluctuation caused by parameter adjustment in the network operation and optimization process is included, and therefore the accuracy of energy consumption prediction is improved.
Step S2, training respectively according to historical network energy consumption data of each energy consumption unit based on the time sequence, and respectively obtaining a neural network model for predicting network energy consumption of each energy consumption unit;
and training according to the washed and aggregated historical energy consumption data to obtain a neural network model for energy consumption prediction, and further carrying out AI time sequence prediction.
In this embodiment, step S2 may further include: and acquiring real-time energy consumption data of each energy consumption unit in real time, and correcting the corresponding neural network model according to the real-time energy consumption data.
Specifically, the prediction effect is compared with the actual situation, the error value is calculated, the prediction error is reduced through longer-term data acquisition, data cleaning and aggregation strategies, and the dynamic model tuning is achieved.
And S3, predicting the energy consumption data of the corresponding energy consumption units in the prediction time period according to the neural network model, generating a corresponding energy-saving strategy according to the energy consumption data of each energy consumption unit in the prediction time period, and executing energy-saving operation according to the energy-saving strategy.
Specifically, the energy consumption trend in a short term (e.g., several hours) in the future and the energy consumption trend in a long term (e.g., several days) in the future are output through the neural network model, and then an energy saving strategy corresponding to the energy consumption trend is generated, where the energy saving strategy may include: closing some frequency bands, closing some time slots, closing some cells, closing some wireless transmission channels, and the like. By executing the energy-saving strategy, the network base station can not only meet the network performance requirements of users, but also greatly reduce the power resource consumption of the network base station.
The scheme of the invention is matched with the energy-saving function of the Guangdong mobile intelligent energy consumption management platform, so that the controllable energy-saving target of 20-70% of the 5G base stations is realized, and meanwhile, the network performance is kept stable.
Based on the above technical solution, this embodiment further provides a network energy saving device based on energy consumption data, as shown in fig. 2, including:
the intelligent energy consumption management platform is used for acquiring historical network energy consumption data of each energy consumption unit based on time series;
the training unit is used for respectively training according to historical network energy consumption data of each energy consumption unit based on the time sequence to respectively obtain a neural network model for predicting the network energy consumption of each energy consumption unit;
and the energy-saving operation unit is used for predicting the energy consumption data of the corresponding energy consumption units in the prediction time period according to the neural network model, generating a corresponding energy-saving strategy according to the energy consumption data of each energy consumption unit in the prediction time period, and executing energy-saving operation according to the energy-saving strategy.
It can be understood that, because the network energy saving device based on energy consumption data according to the embodiment of the present invention is a device for implementing the network energy saving method based on energy consumption data according to the embodiment, the device described in the embodiment is relatively simple in description because it corresponds to the method disclosed in the embodiment, and reference may be made to the partial description of the method for the relevant point.
Claims (6)
1. The network energy-saving method based on the energy consumption data is characterized by comprising the following steps:
step 1, acquiring historical network energy consumption data of each energy consumption unit based on a time sequence through an intelligent energy consumption management platform;
step 2, training is respectively carried out according to historical network energy consumption data of each energy consumption unit based on the time sequence, and a neural network model for carrying out network energy consumption prediction on each energy consumption unit is respectively obtained;
and 3, predicting the energy consumption data of the corresponding energy consumption units in the prediction time period according to the neural network model, generating a corresponding energy-saving strategy according to the energy consumption data of each energy consumption unit in the prediction time period, and executing energy-saving operation according to the energy-saving strategy.
2. The method for saving energy in a network based on energy consumption data as claimed in claim 1, wherein the step 2 is preceded by the steps of:
and obtaining an operation log and statistical data of the network manager, comparing the historical network energy consumption data with the operation log and the statistical data, and deleting the historical network energy consumption data in the abnormal time period.
3. The method for saving energy in a network based on energy consumption data as claimed in claim 1, wherein the step 2 is preceded by the steps of:
and determining the time period of network operation and maintenance and network optimization, and deleting the historical network energy consumption data in the time period of network operation and network optimization.
4. The method for network power conservation based on energy consumption data of claim 1, wherein the historical energy consumption data comprises at least: current, voltage and power.
5. The method for network power saving based on energy consumption data as claimed in claim 1, further comprising: and acquiring real-time energy consumption data of each energy consumption unit in real time, and correcting the corresponding neural network model according to the real-time energy consumption data.
6. Network economizer based on energy consumption data, its characterized in that includes:
the intelligent energy consumption management platform is used for acquiring historical network energy consumption data of each energy consumption unit based on time series;
the training unit is used for respectively training according to historical network energy consumption data of each energy consumption unit based on the time sequence to respectively obtain a neural network model for predicting the network energy consumption of each energy consumption unit;
and the energy-saving operation unit is used for predicting the energy consumption data of the corresponding energy consumption units in the prediction time period according to the neural network model, generating a corresponding energy-saving strategy according to the energy consumption data of each energy consumption unit in the prediction time period, and executing energy-saving operation according to the energy-saving strategy.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011540759.0A CN112714488A (en) | 2020-12-23 | 2020-12-23 | Network energy saving method and device based on energy consumption data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011540759.0A CN112714488A (en) | 2020-12-23 | 2020-12-23 | Network energy saving method and device based on energy consumption data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112714488A true CN112714488A (en) | 2021-04-27 |
Family
ID=75543753
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011540759.0A Pending CN112714488A (en) | 2020-12-23 | 2020-12-23 | Network energy saving method and device based on energy consumption data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112714488A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113923700A (en) * | 2021-12-13 | 2022-01-11 | 中国移动紫金(江苏)创新研究院有限公司 | Prediction method and system for endurance time of backup battery of base station |
CN114785821A (en) * | 2022-03-16 | 2022-07-22 | 陇东学院 | Urban Internet of things data processing system and method based on Hadoop |
WO2022227995A1 (en) * | 2021-04-30 | 2022-11-03 | 华为技术有限公司 | Energy-saving method and apparatus |
CN115451534A (en) * | 2022-09-02 | 2022-12-09 | 东联信息技术有限公司 | Energy-saving method for machine room air conditioner based on reinforcement learning score scene |
WO2023087138A1 (en) * | 2021-11-16 | 2023-05-25 | 株式会社Ntt都科摩 | Network energy consumption management system and method, and storage medium |
WO2023093427A1 (en) * | 2021-11-26 | 2023-06-01 | 中兴通讯股份有限公司 | Energy-saving control method and device, storage medium, and program product |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103024761A (en) * | 2011-09-26 | 2013-04-03 | 艾默生网络能源有限公司 | Establishing method for energy consumption model of base station, and energy consumption predicating method and device |
CN108848520A (en) * | 2018-05-28 | 2018-11-20 | 西安交通大学 | A kind of base station dormancy method based on volume forecasting and base station state |
CN110650463A (en) * | 2019-09-26 | 2020-01-03 | 赣南师范大学 | Agricultural Internet of things node energy consumption optimization method based on fuzzy mathematics |
-
2020
- 2020-12-23 CN CN202011540759.0A patent/CN112714488A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103024761A (en) * | 2011-09-26 | 2013-04-03 | 艾默生网络能源有限公司 | Establishing method for energy consumption model of base station, and energy consumption predicating method and device |
CN108848520A (en) * | 2018-05-28 | 2018-11-20 | 西安交通大学 | A kind of base station dormancy method based on volume forecasting and base station state |
CN110650463A (en) * | 2019-09-26 | 2020-01-03 | 赣南师范大学 | Agricultural Internet of things node energy consumption optimization method based on fuzzy mathematics |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2022227995A1 (en) * | 2021-04-30 | 2022-11-03 | 华为技术有限公司 | Energy-saving method and apparatus |
WO2023087138A1 (en) * | 2021-11-16 | 2023-05-25 | 株式会社Ntt都科摩 | Network energy consumption management system and method, and storage medium |
WO2023093427A1 (en) * | 2021-11-26 | 2023-06-01 | 中兴通讯股份有限公司 | Energy-saving control method and device, storage medium, and program product |
CN113923700A (en) * | 2021-12-13 | 2022-01-11 | 中国移动紫金(江苏)创新研究院有限公司 | Prediction method and system for endurance time of backup battery of base station |
CN114785821A (en) * | 2022-03-16 | 2022-07-22 | 陇东学院 | Urban Internet of things data processing system and method based on Hadoop |
CN115451534A (en) * | 2022-09-02 | 2022-12-09 | 东联信息技术有限公司 | Energy-saving method for machine room air conditioner based on reinforcement learning score scene |
CN115451534B (en) * | 2022-09-02 | 2024-05-24 | 东联信息技术有限公司 | Machine room air conditioner energy saving method based on reinforcement learning sub-scene |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112714488A (en) | Network energy saving method and device based on energy consumption data | |
Tikunov et al. | Traffic prediction for mobile network using Holt-Winter’s exponential smoothing | |
CN113055990B (en) | Energy saving and consumption reducing method and system for wireless base station based on big data mining and AI scheduling | |
US20230239784A1 (en) | Energy-saving method, base station, control unit, and storage medium | |
CN110381515B (en) | Method for realizing cell network flow resource index prediction based on combination and division mode | |
CN111417180A (en) | Network scheduling method and device for energy-saving management of cooperative base station | |
Gao et al. | A coverage of self-optimization algorithm using big data analytics in WCDMA cellular networks | |
Gao et al. | Machine learning based energy saving scheme in wireless access networks | |
CN116055419A (en) | Industrial Internet of things cloud edge cooperative transmission control method and process | |
Gao et al. | Accurate load prediction algorithms assisted with machine learning for network traffic | |
CN101005632A (en) | Semi speed intelligent control system | |
Wang et al. | A hybrid deep learning method based on CEEMDAN and attention mechanism for network traffic prediction | |
WO2024066720A1 (en) | Indicator threshold determination method and apparatus, storage medium, and electronic apparatus | |
CN111914000B (en) | Server power capping method and system based on power consumption prediction model | |
CN102781012B (en) | Automatic optimizing method for uplink interference | |
CN110647086B (en) | Intelligent operation and maintenance monitoring system based on operation big data analysis | |
CN103379644B (en) | Carrier wave scheduling method and system | |
CN114189904A (en) | LTE carrier frequency resource scheduling method and device | |
Feng et al. | Study on multi-network traffic modeling in distribution communication network access service | |
CN106887848B (en) | Voltage power-less real-time control method based on Fuzzy Pattern Recognition | |
CN103532233A (en) | Electricity utilization information acquisition abnormity accuracy positioning system on basis of GPRS (General Packet Radio Service) technology | |
CN113743768A (en) | Improved method for multi-station fusion | |
CN115515208A (en) | Base station energy saving method, base station energy saving system, base station and storage medium | |
Zhou et al. | Exploration of adaptive energy optimization for 5g roadside unit | |
CN113364116B (en) | New energy substation fault monitoring method and device based on communication controller |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210427 |