CN113411765A - Mobile intelligent terminal energy consumption optimization method based on multi-sensor cooperative sensing - Google Patents
Mobile intelligent terminal energy consumption optimization method based on multi-sensor cooperative sensing Download PDFInfo
- Publication number
- CN113411765A CN113411765A CN202110561576.5A CN202110561576A CN113411765A CN 113411765 A CN113411765 A CN 113411765A CN 202110561576 A CN202110561576 A CN 202110561576A CN 113411765 A CN113411765 A CN 113411765A
- Authority
- CN
- China
- Prior art keywords
- sensor
- data
- energy consumption
- heterogeneous
- sensors
- 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.)
- Granted
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/38—Services specially adapted for particular environments, situations or purposes for collecting sensor information
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/02—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP]
- H04L67/025—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP] for remote control or remote monitoring of applications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/06—Protocols specially adapted for file transfer, e.g. file transfer protocol [FTP]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/02—Arrangements for optimising operational condition
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/06—Testing, supervising or monitoring using simulated traffic
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W28/00—Network traffic management; Network resource management
- H04W28/02—Traffic management, e.g. flow control or congestion control
- H04W28/0215—Traffic management, e.g. flow control or congestion control based on user or device properties, e.g. MTC-capable devices
- H04W28/0221—Traffic management, e.g. flow control or congestion control based on user or device properties, e.g. MTC-capable devices power availability or consumption
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W28/00—Network traffic management; Network resource management
- H04W28/02—Traffic management, e.g. flow control or congestion control
- H04W28/06—Optimizing the usage of the radio link, e.g. header compression, information sizing, discarding information
-
- 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
Abstract
In order to reduce the energy consumption of the mobile intelligent terminal in the sensing activity, the invention provides a mobile intelligent terminal energy consumption optimization method based on multi-sensor cooperative sensing. The method is based on a cloud edge-side collaborative computing mode, data processing tasks of sensing tasks are delivered to a cloud end to be carried out, and therefore sensing data acquisition energy consumption of the mobile intelligent terminal is optimized. In order to realize the sensing task needing participation of various heterogeneous sensor devices in the energy resource consumption-limited terminal, the method firstly analyzes the potential correlation among various heterogeneous sensors carried in the mobile intelligent terminal, then carries out magnitude description on the energy consumption generated by the heterogeneous sensors in the working process, finally provides a multi-sensor cooperative sensing framework based on the energy consumption model of the sensors and the potential correlation, and finally effectively reduces the energy consumption of the sensors in the sensing task execution process.
Description
Technical Field
The invention belongs to the field of cooperative sensing and energy consumption optimization of various heterogeneous sensors, and relates to a mobile intelligent terminal energy consumption optimization method based on cooperative sensing of multiple sensors.
Background
In recent years, with the rapid development of the internet of things and artificial intelligence technology, more and more mobile intelligent terminals are emerging continuously, and more representative mobile intelligent terminals are smart phones, unmanned automobiles and the like. The mobile intelligent terminal is usually powered by a power supply carried by the mobile intelligent terminal, and meanwhile, the mobile intelligent terminal also has the functions of data acquisition, environment perception, calculation processing and network communication. The environment sensing function is realized through a plurality of heterogeneous sensors carried by the mobile intelligent terminal, the heterogeneous sensors are generally used for sensing information of the mobile intelligent terminal or the surrounding environment, and different energy resources of the mobile intelligent device are consumed differently due to different working mechanisms of the heterogeneous sensors. However, in general, mobile intelligent terminals belong to energy resource-limited devices, and batteries equipped in the mobile intelligent terminals need to complete much work of the terminals under limited capacity. Therefore, for the sensing task based on the mobile intelligent terminal, the consumption of energy resources of the equipment is saved as much as possible. Therefore, research into methods for optimizing the energy consumption of the mobile intelligent terminal in the process of executing the perception task is needed.
The multi-sensor cooperative sensing refers to the situation that a plurality of heterogeneous sensors are used for jointly completing a certain sensing task. Since the sensing capability of the combination of multiple heterogeneous sensors is very strong, the strong sensing capability has been applied to different fields such as unmanned vehicles, public health monitoring and historical relic protection. The document "Sato Y, Kurihara S, Fukuda S, et al.height Estimation based on Sensor Data on Smartphone [ C ]. Proceedings of the 15th International Conference on Advances in Mobile Computing and multimedia 2017: 102-. However, this document does not optimize for the large consumption of energy resources that may result from using multiple heterogeneous sensors, resulting in a large amount of energy resources being consumed.
The document "Du R, Gkatzikis L, Fischione C, et al. energy efficient sensor activation for water distribution network based on comprehensive sensing [ J ]. IEEE Journal on Selected Areas in Communications,2015,33(12):2997 and 3010." proposes a mobile intelligent terminal energy-saving sensing scheduling scheme based on a compressed sensing technology, which implements monitoring of water supply network information of cities on the basis of energy resource saving by activating only one section of sensor nodes in each time slot to execute sensing tasks. The method is characterized in that the energy consumption of the overall perception activity is optimized by optimizing the data communication traffic of the sensors, but under the scene that a plurality of heterogeneous sensors are required to jointly realize cooperative perception, the method reduces the richness of data when multi-dimensional compression is carried out on heterogeneous data, and cannot meet the data requirement of a perception task.
The document "Pan M S, Li K Y. precision targets estimation uses Smartphone Sensors [ C ]. Proceedings of the 11th International Conference on Computer Modeling and simulation.2019: 196-. The experimental result shows that the scheme can accurately predict the action track of the user, and can predict the position information of the user only through the inertial sensor instead of the position sensor, so that the energy resource of the intelligent mobile phone device is effectively saved. This approach replaces the sensors needed for sensing activity with other sensors, which, while satisfying the overall reduction in power consumption, can result in additional sensor power consumption.
The above documents simply introduce the multi-sensor cooperative sensing and the corresponding energy consumption optimization technology of the existing mobile intelligent terminal. The existing optimization method for sensing energy consumption of the mobile intelligent terminal does not consider the potential correlation between the heterogeneous sensors required by the sensing task, and the potential correlation can be used for realizing the mobile intelligent terminal energy consumption optimization technology based on multi-sensor cooperative sensing.
Disclosure of Invention
Technical problem to be solved
In order to reduce the energy consumption of the mobile intelligent terminal in the sensing activity, the invention provides a mobile intelligent terminal energy consumption optimization method based on multi-sensor cooperative sensing.
Technical scheme
A mobile intelligent terminal energy consumption optimization method based on multi-sensor cooperative sensing is characterized by comprising the following steps:
step 1: the method comprises the steps that sensing data of all heterogeneous sensors in the terminal equipment are collected through the sensors;
step 2: storing and preprocessing the acquired sensing data of the sensor;
and step 3: performing a data population task on the heterogeneous sensor data file;
and 4, step 4: taking the data streams of the various heterogeneous sensors after executing the data filling task as input data of the multi-sensor cooperative sensing system, wherein the output data of the multi-sensor cooperative sensing system is complete sensing data of all heterogeneous sensors; the multi-sensor collaborative perception system learns potential association relations among various heterogeneous sensor devices, and an implicit association learning model ATT-TCN of the heterogeneous sensor is adopted;
and 5: the multi-sensor cooperative sensing system can depict the energy consumption conditions of various heterogeneous sensors in the mobile intelligent terminal, and a heterogeneous sensor energy consumption depicting model is adopted;
step 6: the multi-sensor cooperative sensing system finally performs optimization operation for reducing energy consumption aiming at a high-energy consumption sensor in the mobile intelligent terminal: specifically, a heterogeneous sensor data estimation model is utilized to estimate data of a high energy consumption sensor by utilizing data of a low energy consumption sensor having a certain correlation with the high energy consumption sensor; the adopted heterogeneous sensor data estimation model comprises four components: one transform Encoder and three transform Decoder; the mode of realizing the multitasker model in the model selects a hidden layer of a shared model, and the hidden layer of the data learned in a Transformer Encoder can be shared into three Transformer Decoder by the method; the three transform Decoder decoders are responsible for executing data estimation tasks on three different axes, namely an x axis, a y axis and a z axis, of the specific sensor; for a Transformer Encoder in a model, input data is a plurality of heterogeneous sensor time sequence data streams after preprocessing operation, wherein mixed data of a low-energy consumption sensor with potential relevance to a high-energy consumption sensor to be estimated and data of a high-energy consumption sensor after sampling frequency is reduced is represented by X; wherein a parameter λ ∈ [0,1] is introduced to control the number of samples from the high energy consuming sensors contained in the input X; when λ ═ 0, it means that all samples from the high energy consumption sensors are excluded from X, only the data of the low energy consumption sensors having correlation with the high energy consumption sensors are included; the higher the lambda is, the more samples are collected from the high-energy consumption sensor, and meanwhile, the integral perception energy consumption of the mobile intelligent terminal is increased;
and 7: finally, the multi-sensor cooperative sensing system utilizes the parameter lambda to control the data ratio of the high-energy consumption sensor in the data collected from the mobile intelligent terminal, namely, the data sampling frequency of the high-energy consumption sensor is adjusted, and the energy consumption condition of the mobile intelligent terminal is optimized in this way.
Preferably: the terminal in the step 1 is a smart phone.
Preferably: the sensor in the step 1 is a gyroscope sensor, a gravity sensor or a direction sensor.
Preferably: the file type of the stored sensor data in the step 2 is a CSV file.
Preferably: the data filling task in the step 3 is specifically as follows: selecting the sensor S with the highest sampling frequency1The sensing time node is used as a time reference, and other sensors perform data time alignment operation according to the time node of the sensor; the process of data time alignment can be divided into two parts of time alignment and data filling: first time-aligned, according to S1The sensing data of other sensors are represented on different time nodes by using the sampling time node as reference time; after the time alignment operation, the data of all the heterogeneous sensors are aligned according to a uniform time node; next, performing data filling operation, wherein the specific filling logic is to fill the sensing data of the sensor at the last time; all sensors have the same data length after final data preprocessing.
Preferably: in the step 4, the heterogeneous sensor implicit association learning model ATT-TCN comprises four components: causal convolution, dilation convolution, residual concatenation and attention mechanism.
Preferably: in the step 5, the heterogeneous sensor energy consumption characterization model summarizes various factors influencing the heterogeneous sensor equipment energy consumption condition as follows: the energy consumption of the heterogeneous sensor device is controlled by the state control system, and the energy consumption of the heterogeneous sensor device is controlled by the state control system.
Advantageous effects
The invention provides a mobile intelligent terminal energy consumption optimization method based on multi-sensor cooperative sensing. And secondly, performing data filling operation on the acquired data to ensure that the data acquisition time of different heterogeneous sensors is consistent and all the sensors have data at the same time point. Then, the acquired sensing data streams of the heterogeneous sensors are used for executing the multi-sensor cooperative sensing system, and the system firstly utilizes the implicit association of the heterogeneous sensors to learn the potential correlation relationship among various heterogeneous sensor devices mounted in the mobile intelligent terminal. Secondly, the system uses a heterogeneous sensor energy consumption characterization model to characterize the energy consumption conditions of various heterogeneous sensors in the mobile intelligent terminal. Finally, the system utilizes the parameter lambda to control the data ratio of the high-energy consumption sensor in the collected data from the mobile intelligent terminal, namely, the data sampling frequency of the high-energy consumption sensor is adjusted, and the energy consumption condition of the mobile intelligent terminal is optimized in this way. And finally, the aim of reducing the perception energy consumption of the mobile intelligent terminal in the process of executing the perception task is fulfilled.
Drawings
The drawings are only for purposes of illustrating particular embodiments and are not to be construed as limiting the invention, wherein like reference numerals are used to designate like parts throughout.
Fig. 1 is a framework diagram of a method for optimizing energy consumption of a mobile intelligent terminal based on multi-sensor cooperative sensing in the embodiment of the invention.
FIG. 2 is a flow chart of the execution of data stuffing tasks during the data pre-processing phase in an example of the present invention.
FIG. 3 is a structural diagram of a heterogeneous sensor implicit association learning model constructed in an embodiment of the invention.
FIG. 4 is a diagram of a heterogeneous sensor energy consumption characterization model constructed in accordance with an embodiment of the present invention.
FIG. 5 is a diagram of a heterogeneous sensor energy consumption characterization model constructed in accordance with an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
The invention provides a mobile intelligent terminal energy consumption optimization method based on multi-sensor cooperative sensing. The method is based on a cloud edge-side collaborative computing mode, data processing tasks of sensing tasks are delivered to a cloud end to be carried out, and therefore sensing data acquisition energy consumption of the mobile intelligent terminal is optimized. In order to realize the sensing task needing participation of various heterogeneous sensor devices in the energy resource consumption-limited terminal, the method firstly analyzes the potential correlation among various heterogeneous sensors carried in the mobile intelligent terminal, then carries out magnitude description on the energy consumption generated by the heterogeneous sensors in the working process, finally provides an efficiency-driven multi-sensor cooperative sensing system based on the energy consumption model of the sensors and the potential correlation, and finally effectively reduces the energy consumption of the sensors in the sensing task execution process.
The invention provides a multi-factor-based heterogeneous sensor energy consumption evaluation model for describing the energy consumption conditions of various heterogeneous sensors carried in a mobile intelligent terminal in detail. In order to implement detailed depiction of energy consumption conditions in a life cycle of a sensor and simultaneously divide high and low energy consumption of the sensor according to the energy consumption state of the sensor, a heterogeneous sensor multi-factor energy efficiency depiction method is designed and constructed. According to the method, the energy consumption condition of the current sensor can be deduced according to different states in the life cycle process of the sensor, and the sensor in the current mobile intelligent terminal is divided into different categories such as a high-energy consumption sensor and a low-energy consumption sensor according to different energy consumption states of heterogeneous sensors. The energy consumption analysis example of the heterogeneous sensor is carried out aiming at experimental equipment, and experimental results show that the method can be used for describing the energy consumption condition of the heterogeneous sensor in a fine granularity.
The invention provides a heterogeneous sensor data estimation method for reducing energy consumption of a high-energy consumption sensor carried in a mobile intelligent terminal. The method is based on the principle that the sensing energy consumption of the mobile intelligent terminal can be effectively reduced by reducing the sampling frequency of the high-energy-consumption sensor, and the data missing from the high-energy-consumption sensor is estimated by using the low-energy-consumption sensor which is in a correlation relation with the high-energy-consumption sensor, so that the energy consumption of the sensing task is reduced while the sensing task is accurately completed. The balance between energy resource consumption and perception data precision is realized, and the energy consumption optimization requirement of the current energy resource limited device in the high-energy-consumption perception task scene is met.
In order to realize the task, the invention adopts the following technical scheme: the method for optimizing the energy consumption of the mobile intelligent terminal based on the multi-sensor cooperative sensing comprises the following steps:
the method comprises the steps of firstly, acquiring sensing data of all heterogeneous sensors in the mobile intelligent terminal equipment, and completing the sensing data by using a sensor data acquisition application program installed on the mobile intelligent terminal.
And step two, sending the acquired sensing data of the heterogeneous sensor to a server side for storage in a network transmission mode, wherein the sensor data is stored in a CSV file format. And after all the files are uploaded, the data acquisition task of the mobile intelligent terminal is finished.
And thirdly, carrying out data preprocessing operation on the acquired heterogeneous sensor data file to reduce the influence of invalid data. And deleting the sensor files without the acquired data by data preprocessing, and only leaving the sensor data files with the acquired data.
And step four, executing a data filling task on the heterogeneous sensor data file, wherein an execution flow chart of the data filling task is shown in fig. 2. Selecting the sensor S with the highest sampling frequency1The sensing time node is used as a time reference, and other sensors perform data time alignment operation according to the time node of the sensor. The process of data time alignment can be divided into two parts of time alignment and data filling. First time-aligned, according to S1The sampling time node of (2) is used as a reference time to represent the perception data of other sensors on different time nodes. After the time alignment operation, the data of all heterogeneous sensors are aligned according to a uniform time node. Next, a data filling operation is performed, and the specific filling logic is to fill in the last sensing data of the sensor. Last pass dataAll sensors after preprocessing have the same data length.
And step five, taking the data streams of the various heterogeneous sensors after the data filling task is executed as input data of the multi-sensor cooperative sensing system in the mobile intelligent terminal energy consumption optimization method based on the multi-sensor cooperative sensing provided by the invention, wherein the output data of the multi-sensor cooperative sensing system is complete sensing data of all the heterogeneous sensors.
Step six, the multi-sensor cooperative sensing system firstly learns the potential association relationship among various heterogeneous sensor devices, and an implicit association learning model ATT-TCN of the heterogeneous sensor is used, wherein the structure diagram of the model is shown in FIG. 3. The model comprises four components: causal convolution, dilation convolution, residual concatenation and attention mechanism. Consists of two layers: a time convolutional network layer, an attention layer.
And step seven, the multi-sensor cooperative sensing system can depict the energy consumption conditions of various heterogeneous sensors in the mobile intelligent terminal, a heterogeneous sensor energy consumption depicting model is used, and the model is shown in the structural diagram of fig. 4. The model summarizes various factors affecting the energy consumption situation of the heterogeneous sensor device as follows: the energy consumption of activation and wake-up, the energy consumption of data processing, the energy consumption of network communication and the energy consumption of state control are four parts, and each part is an independent factor to influence the energy consumption of the whole heterogeneous sensor. The energy consumption factors of the four parts operate alternately and finally influence the energy consumption of the heterogeneous sensor device.
And step eight, the multi-sensor cooperative sensing system finally performs optimization operation for reducing energy consumption aiming at the high-energy consumption sensor in the mobile intelligent terminal. In particular, a heterogeneous sensor data estimation model is utilized to estimate data of a high energy consuming sensor using data of a low energy consuming sensor having a certain correlation with the high energy consuming sensor. The heterogeneous sensor data estimation model used is shown in fig. 5, and comprises four components: one transform Encoder and three transform Decoder. The mode of realizing the multitasker model in the model selects a hidden layer of a shared model, and the hidden layer of the data learned in a Transformer Encoder can be shared into three Transformer Decoder by the method. Three transform Decoder decoders are responsible for performing data estimation tasks on three different axes, namely the x-axis, the y-axis and the z-axis, of a particular sensor. For the Transformer Encoder in the model, the input data is a plurality of heterogeneous sensor time sequence data streams after preprocessing operation, wherein the data comprises a mixture of data of a low-energy consumption sensor having potential relevance with a high-energy consumption sensor to be estimated and data of a high-energy consumption sensor after reducing the sampling frequency, and the mixture is represented by X. Where a parameter λ ∈ [0,1] is introduced to control the number of samples from the high energy consuming sensors contained in the input X. When λ is 0, it means that all samples from the high energy consumption sensor are excluded from X, and only data of the low energy consumption sensor having correlation with the high energy consumption sensor is included. The higher the λ, the more samples are collected from the high energy consumption sensor, which will also increase the overall perceived energy consumption of the mobile smart terminal.
Finally, the multi-sensor cooperative sensing system utilizes the parameter lambda to control the data ratio of the high-energy consumption sensor in the data collected from the mobile intelligent terminal, namely, the data sampling frequency of the high-energy consumption sensor is adjusted, and the energy consumption condition of the mobile intelligent terminal is optimized in this way.
While the invention has been described with reference to specific embodiments, the invention is not limited thereto, and various equivalent modifications or substitutions can be easily made by those skilled in the art within the technical scope of the present disclosure.
Claims (7)
1. A mobile intelligent terminal energy consumption optimization method based on multi-sensor cooperative sensing is characterized by comprising the following steps:
step 1: the method comprises the steps that sensing data of all heterogeneous sensors in the terminal equipment are collected through the sensors;
step 2: storing and preprocessing the acquired sensing data of the sensor;
and step 3: performing a data population task on the heterogeneous sensor data file;
and 4, step 4: taking the data streams of the various heterogeneous sensors after executing the data filling task as input data of the multi-sensor cooperative sensing system, wherein the output data of the multi-sensor cooperative sensing system is complete sensing data of all heterogeneous sensors; the multi-sensor collaborative perception system learns potential association relations among various heterogeneous sensor devices, and an implicit association learning model ATT-TCN of the heterogeneous sensor is adopted;
and 5: the multi-sensor cooperative sensing system can depict the energy consumption conditions of various heterogeneous sensors in the mobile intelligent terminal, and a heterogeneous sensor energy consumption depicting model is adopted;
step 6: the multi-sensor cooperative sensing system finally performs optimization operation for reducing energy consumption aiming at a high-energy consumption sensor in the mobile intelligent terminal: specifically, a heterogeneous sensor data estimation model is utilized to estimate data of a high energy consumption sensor by utilizing data of a low energy consumption sensor having a certain correlation with the high energy consumption sensor; the adopted heterogeneous sensor data estimation model comprises four components: one transform Encoder and three transform Decoder; the mode of realizing the multitasker model in the model selects a hidden layer of a shared model, and the hidden layer of the data learned in a Transformer Encoder can be shared into three Transformer Decoder by the method; the three transform Decoder decoders are responsible for executing data estimation tasks on three different axes, namely an x axis, a y axis and a z axis, of the specific sensor; for a Transformer Encoder in a model, input data is a plurality of heterogeneous sensor time sequence data streams after preprocessing operation, wherein mixed data of a low-energy consumption sensor with potential relevance to a high-energy consumption sensor to be estimated and data of a high-energy consumption sensor after sampling frequency is reduced is represented by X; wherein a parameter λ ∈ [0,1] is introduced to control the number of samples from the high energy consuming sensors contained in the input X; when λ ═ 0, it means that all samples from the high energy consumption sensors are excluded from X, only the data of the low energy consumption sensors having correlation with the high energy consumption sensors are included; the higher the lambda is, the more samples are collected from the high-energy consumption sensor, and meanwhile, the integral perception energy consumption of the mobile intelligent terminal is increased;
and 7: finally, the multi-sensor cooperative sensing system utilizes the parameter lambda to control the data ratio of the high-energy consumption sensor in the data collected from the mobile intelligent terminal, namely, the data sampling frequency of the high-energy consumption sensor is adjusted, and the energy consumption condition of the mobile intelligent terminal is optimized in this way.
2. The deep learning-based heterogeneous sensor potential correlation learning method according to claim 1, wherein the terminal in step 1 is a smart phone.
3. The method for learning the potential correlation of the heterogeneous sensor based on the deep learning of claim 1, wherein the sensor in the step 1 is a gyroscope sensor, a gravity sensor or an orientation sensor.
4. The method for learning the potential relevance of the heterogeneous sensor based on deep learning of claim 1, wherein the file type of the saved sensor data in step 2 is a CSV file.
5. The method for learning the potential relevance of the heterogeneous sensor based on the deep learning of claim 1, wherein the data filling task in the step 3 is specifically as follows: selecting the sensor S with the highest sampling frequency1The sensing time node of (2) is used as a time reference, and other sensors perform data time according to the time node of the sensorPerforming alignment operation; the process of data time alignment can be divided into two parts of time alignment and data filling: first time-aligned, according to S1The sensing data of other sensors are represented on different time nodes by using the sampling time node as reference time; after the time alignment operation, the data of all the heterogeneous sensors are aligned according to a uniform time node; next, performing data filling operation, wherein the specific filling logic is to fill the sensing data of the sensor at the last time; all sensors have the same data length after final data preprocessing.
6. The deep learning-based heterogeneous sensor potential correlation learning method of claim 1, wherein the heterogeneous sensor implicit association learning model ATT-TCN in step 4 comprises four components: causal convolution, dilation convolution, residual concatenation and attention mechanism.
7. The deep learning-based heterogeneous sensor potential correlation learning method according to claim 1, wherein the heterogeneous sensor energy consumption characterization model in step 5 summarizes various factors affecting the heterogeneous sensor device energy consumption condition as follows: the energy consumption of the heterogeneous sensor device is controlled by the state control system, and the energy consumption of the heterogeneous sensor device is controlled by the state control system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110561576.5A CN113411765B (en) | 2021-05-22 | 2021-05-22 | Mobile intelligent terminal energy consumption optimization method based on multi-sensor cooperative sensing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110561576.5A CN113411765B (en) | 2021-05-22 | 2021-05-22 | Mobile intelligent terminal energy consumption optimization method based on multi-sensor cooperative sensing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113411765A true CN113411765A (en) | 2021-09-17 |
| CN113411765B CN113411765B (en) | 2022-07-26 |
Family
ID=77679203
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110561576.5A Active CN113411765B (en) | 2021-05-22 | 2021-05-22 | Mobile intelligent terminal energy consumption optimization method based on multi-sensor cooperative sensing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113411765B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100308974A1 (en) * | 2007-03-15 | 2010-12-09 | Rowland Harry D | Wireless sensor reader |
| US20120203491A1 (en) * | 2011-02-03 | 2012-08-09 | Nokia Corporation | Method and apparatus for providing context-aware control of sensors and sensor data |
| CN107743302A (en) * | 2017-10-27 | 2018-02-27 | 南京航空航天大学 | Rate-allocation and route combined optimization algorithm in wireless sensor network based on compressed sensing |
| US20180270312A1 (en) * | 2017-03-18 | 2018-09-20 | Tata Consultancy Services Limited | Method and system for anomaly detecttion, missing data imputation and consumption prediction in energy data |
| CN108846384A (en) * | 2018-07-09 | 2018-11-20 | 北京邮电大学 | Merge the multitask coordinated recognition methods and system of video-aware |
| CN110022541A (en) * | 2019-05-22 | 2019-07-16 | 南开大学 | A kind of sparse acquisition of WSN crop growth environment information and transmission method based on NB-IoT and FPGA |
| CN111562972A (en) * | 2020-04-24 | 2020-08-21 | 西北工业大学 | Ubiquitous operating system for crowd sensing |
| CN111586615A (en) * | 2020-05-13 | 2020-08-25 | 甘肃省农业工程技术研究院 | Sampling scheduling method and system for agricultural wireless sensor network |
-
2021
- 2021-05-22 CN CN202110561576.5A patent/CN113411765B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100308974A1 (en) * | 2007-03-15 | 2010-12-09 | Rowland Harry D | Wireless sensor reader |
| US20120203491A1 (en) * | 2011-02-03 | 2012-08-09 | Nokia Corporation | Method and apparatus for providing context-aware control of sensors and sensor data |
| US20180270312A1 (en) * | 2017-03-18 | 2018-09-20 | Tata Consultancy Services Limited | Method and system for anomaly detecttion, missing data imputation and consumption prediction in energy data |
| CN107743302A (en) * | 2017-10-27 | 2018-02-27 | 南京航空航天大学 | Rate-allocation and route combined optimization algorithm in wireless sensor network based on compressed sensing |
| CN108846384A (en) * | 2018-07-09 | 2018-11-20 | 北京邮电大学 | Merge the multitask coordinated recognition methods and system of video-aware |
| CN110022541A (en) * | 2019-05-22 | 2019-07-16 | 南开大学 | A kind of sparse acquisition of WSN crop growth environment information and transmission method based on NB-IoT and FPGA |
| CN111562972A (en) * | 2020-04-24 | 2020-08-21 | 西北工业大学 | Ubiquitous operating system for crowd sensing |
| CN111586615A (en) * | 2020-05-13 | 2020-08-25 | 甘肃省农业工程技术研究院 | Sampling scheduling method and system for agricultural wireless sensor network |
Non-Patent Citations (5)
| Title |
|---|
| DONG CAO: "Text Sentiment Analysis based on Parallel TCN Model and Attention Model", 《INTERNATIONAL ACADEMY OF COMPUTER TECHNOLOGY(IACT)》 * |
| YUNJI LIANG: "Fusion of heterogeneous attention mechanisms in multi-view convolutional neural network for text classification", 《INFORMATION SCIENCES》 * |
| 万叶晶等: "一种基于时空相关性和异常检测的改进WSN节能策略", 《传感技术学报》 * |
| 胡永利等: "物联网信息感知与交互技术", 《计算机学报》 * |
| 龙浩等: "基于马尔科夫决策过程的高能效任务调度算法", 《计算机应用与软件》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113411765B (en) | 2022-07-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhang et al. | Learning-based energy-efficient data collection by unmanned vehicles in smart cities | |
| CN109753751B (en) | MEC random task migration method based on machine learning | |
| CN113064671A (en) | Multi-agent-based edge cloud extensible task unloading method | |
| Mwase et al. | Communication-efficient distributed AI strategies for the IoT edge | |
| CN110580616A (en) | Artificial intelligence cloud computing water environment management platform based on 5G and Internet of things | |
| Bai et al. | Joint optimization of computation offloading, data compression, energy harvesting, and application scenarios in fog computing | |
| Huang et al. | Smart energy management system based on reconfigurable AI chip and electrical vehicles | |
| Shi et al. | Multiuser co-inference with batch processing capable edge server | |
| CN108345934A (en) | A kind of activation device and method for neural network processor | |
| CN114169506A (en) | Deep learning edge computing system framework based on industrial Internet of things platform | |
| CN113411765B (en) | Mobile intelligent terminal energy consumption optimization method based on multi-sensor cooperative sensing | |
| CN102209369B (en) | Method based on wireless network interface selection to improve a smart phone user experience | |
| CN116828541A (en) | Edge computing dependent task dynamic unloading method and system based on multi-agent reinforcement learning | |
| CN100578538C (en) | Virtual surroundings population objects behaviors evolvement method based on gradation picture organization and transformation | |
| KR102472585B1 (en) | Big data-based modular AI engine server and driving method of the same | |
| Yang et al. | Cloud-edge-device Collaboration Mechanisms of Cloud Manufacturing for Customized and Personalized Products | |
| CN114035671A (en) | Cloud + multi-terminal cooperative energy-saving task unloading method for multi-working-mode wearable computing system | |
| Liu et al. | Joint radio map construction and dissemination in MEC networks: a deep reinforcement learning approach | |
| Wang et al. | C3Meta: A Context-Aware Cloud-Edge-End Collaboration Framework Toward Green Metaverse | |
| Xu et al. | Ddpg-based edge resource management for coal mine surveillance video analysis in cloud-edge cooperation framework | |
| O’Hare et al. | Embedding intelligent decision making within complex dynamic environments | |
| Lin et al. | Hypergraph-Based Autonomous Networks: Adaptive Resource Management and Dynamic Resource Scheduling | |
| CN112492612B (en) | Resource allocation method and device | |
| CN117557770A (en) | Target detection method and system based on integrated memory and calculation architecture | |
| Tan et al. | Toward a task offloading framework based on cyber digital twins in mobile edge computing |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |