CN114096010B - Monitoring-oriented underwater sensor network energy continuous management method - Google Patents
Monitoring-oriented underwater sensor network energy continuous management method Download PDFInfo
- Publication number
- CN114096010B CN114096010B CN202111282375.8A CN202111282375A CN114096010B CN 114096010 B CN114096010 B CN 114096010B CN 202111282375 A CN202111282375 A CN 202111282375A CN 114096010 B CN114096010 B CN 114096010B
- Authority
- CN
- China
- Prior art keywords
- energy
- underwater sensor
- monitoring
- state information
- sensor node
- 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.)
- Active
Links
- 238000007726 management method Methods 0.000 title claims abstract description 48
- 238000012544 monitoring process Methods 0.000 claims abstract description 56
- 238000000034 method Methods 0.000 claims abstract description 43
- 230000008569 process Effects 0.000 claims abstract description 21
- 238000013528 artificial neural network Methods 0.000 claims abstract description 17
- 238000003062 neural network model Methods 0.000 claims abstract description 6
- 238000012549 training Methods 0.000 claims abstract description 6
- 239000002245 particle Substances 0.000 claims description 18
- 238000012937 correction Methods 0.000 claims description 11
- 230000009471 action Effects 0.000 claims description 9
- 238000001914 filtration Methods 0.000 claims description 9
- 230000005540 biological transmission Effects 0.000 claims description 8
- 230000000694 effects Effects 0.000 claims description 7
- 230000008859 change Effects 0.000 claims description 6
- 238000005259 measurement Methods 0.000 claims description 5
- 238000011084 recovery Methods 0.000 claims description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 4
- 230000001133 acceleration Effects 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 230000007704 transition Effects 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000004927 fusion Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W72/00—Local resource management
- H04W72/04—Wireless resource allocation
- H04W72/044—Wireless resource allocation based on the type of the allocated resource
- H04W72/0473—Wireless resource allocation based on the type of the allocated resource the resource being transmission power
-
- 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
- G06N3/08—Learning methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B13/00—Transmission systems characterised by the medium used for transmission, not provided for in groups H04B3/00 - H04B11/00
- H04B13/02—Transmission systems in which the medium consists of the earth or a large mass of water thereon, e.g. earth telegraphy
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W84/00—Network topologies
- H04W84/18—Self-organising networks, e.g. ad-hoc networks or sensor networks
-
- 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)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The invention discloses a monitoring-oriented underwater sensor network energy continuous management method, which comprises the following steps: constructing an energy model of an underwater sensor node of the underwater sensor network; constructing an objective function and a constraint function of an energy continuous management scheme based on an underwater sensor node energy model; constructing a cost function for energy continuous management, and setting different process states to obtain corresponding energy efficiency data; and training a neural network model according to the initial prediction information of the monitoring target and the obtained energy efficiency data, and solving an energy continuous management scheme. The method can utilize the advantages of the neural network, and can obtain an energy continuous management scheme more efficiently and in real time under the condition of limited energy resources, so as to realize high-energy-efficiency monitoring.
Description
Technical Field
The invention belongs to the technology of energy management of an underwater sensor network, and particularly relates to a monitoring-oriented underwater sensor network energy continuous management method.
Background
The underwater sensor network is a sensor network which uses the related technology of the wireless sensor network as a reference and is applied to the underwater. In the monitoring process, the underwater sensor network can monitor a monitoring target of a monitoring area by utilizing sensor nodes integrated with various functions, acquire data and process the data, and then the processed data is sent to a fusion center in a hydroacoustic communication mode to perform data fusion, so that more and more accurate data are obtained. The underwater sensor network has the characteristics of flexible distribution, comprehensive dimension, low equipment cost and strong concealment, and can play a great role in the military and civil fields.
However, due to the limitation of the special underwater environment, the underwater sensor node is difficult to replace a battery, and the situation that the energy is limited exists. At the same time, the transmission of the underwater acoustic signal consumes more energy than the transmission of the terrestrial radio signal. Therefore, the energy problem of the underwater sensor network directly affects the service life of the underwater sensor network, and further indirectly affects the monitoring performance, and the underwater sensor network needs to be subjected to energy management.
In the prior art, the underwater sensor node can convert energy generated by water flow movement into electric energy by utilizing piezoelectric conversion through the energy collecting device, so as to realize energy recovery. The energy of the underwater sensor node is changed along with time, and the energy condition at the current moment can influence the future. Therefore, for the scene of monitoring the underwater sensor network used for a long time, the energy and the monitoring effect of the underwater sensor network need to be comprehensively considered, and the energy of the underwater sensor network is continuously managed. The traditional dynamic programming solving method is too long in time consumption, cannot meet the requirement of real-time performance and needs innovation.
Based on the above problems, an effective method is needed to realize the continuous management of the energy of the underwater sensor network.
Disclosure of Invention
The invention aims to: the invention aims to provide a monitoring-oriented underwater sensor network energy continuous management method, which can be used for distributing consumed energy while controlling the working state of an underwater sensor node so as to realize the underwater sensor network energy continuous management.
The technical scheme is as follows: the invention discloses a monitoring-oriented underwater sensor network energy continuous management method, which comprises the following steps:
s1, constructing an energy model of an underwater sensor node of an underwater sensor network;
s2, constructing an objective function and a constraint function of an energy continuous management scheme based on an energy model of the underwater sensor node;
S3, constructing a cost function for energy continuous management, and setting different process states to obtain corresponding energy efficiency data;
And S4, training a neural network model according to the prediction state information of the monitoring target and the energy efficiency data obtained in the S3, and solving an energy continuous management scheme.
Further, the step S1 specifically includes:
the underwater sensor node has two working states, namely an activated state and a standby state; in an activated state, the underwater sensor node executes a monitoring task, acquires measurement data related to a target by using a sensing module, and sends the measurement data out by using a transmission module; in a standby state, the underwater sensor node executes an energy recovery task, and the energy collection module collects energy by utilizing water flow movement;
according to the working state, constructing an energy model of the underwater sensor node by the following expression:
Wherein e i,k+1 is the energy of the underwater sensor node i at the moment k+1; e i,k is the energy of the underwater sensor node i at the moment k; The energy required by the operation of the module is perceived at the moment k; /(I) The energy required by the operation of the module is transmitted for the moment k; /(I)The energy collection module collects energy at the moment k, the energy collection accords with a one-order Markov process, is divided into L grades, and meets the requirementRespectively representing the collected different energy levels; the corresponding transition probability is For/>By/>Become/>Probability of (2); e max represents the upper energy limit of the underwater sensor node; p i is an operating state selection function, p i =1 in the active state, and p i =0 in the standby state; /(I)Representation returnAnd the minimum in e max.
Further, the step S2 specifically includes:
defining energy efficiency The monitoring effect under the change of unit energy is achieved;
Wherein, Is mutual information and represents monitoring effect, and is transmitted by energy/>Is a function of (1); Δe i,k＝ei,k-ei,k-1 is the energy change at the moment adjacent to the underwater sensor node i;
The objective of energy continuous management is to maximize the energy efficiency of the underwater sensor network in the monitoring time, and the corresponding objective function expression is:
Wherein K is the monitoring time length, M is the number of underwater sensor nodes forming an underwater sensor network, and M is more than or equal to 4;
The method is limited by the high dimensionality of the underwater scene, and at least 4 underwater sensor nodes are needed to participate in monitoring in order to ensure the stability of monitoring; therefore, an active node number constraint is constructed, and the corresponding expression is:
The energy consumed by the measuring module and the transmission module cannot exceed the current energy due to the limitation of the energy of the underwater sensor node; thus, the energy constraint per unit time is constructed, and the corresponding expression is:
where e i,T represents the maximum energy that node i can provide at time T, T ε {1,2, …, K }.
Further, the step S3 specifically includes:
Defining a process state c k, including e i,k and Wherein/>Denoted as energy collected by the energy collection module at time k-1;
defining decision action, i.e. energy continuous management scheme, comprising p i, And/>
Under the condition that the constraint function in the step S2 is satisfied, constructing a cost function for energy continuous management, wherein the corresponding expression is:
Wherein, Q k(ck) is the energy efficiency data corresponding to the process state c k at the k moment, and the process state c k under different monitoring moments is brought to obtain the corresponding energy efficiency data Q k(ck).
Further, in step S4, training the neural network model according to the predicted state information of the monitored target and the energy efficiency data obtained in step S3 specifically includes:
The state information X k defining the monitoring target comprises information of the monitoring target on position, speed and acceleration at the moment k;
predictive status information of the monitored target Is the prediction of state information X k, and the initial predicted state information/>, of the monitoring targetPrediction state information when k=0;
predicting state information Obtained by a particle filtering technique; specifically, at k=0, the particle filtering technique will produce initial particles/>, based on a priori knowledge about the targetP epsilon {1,2, …, N }, N being the number of particles, and then calculating the initial predicted state information/>, using a formulaThe specific formula is as follows:
when k > 0, the particle filtering technique will be based on the predicted state information of the previous time Generating predicted particles/>Then, the prediction state information/>, is calculated by using a formulaThe specific formula is as follows:
The energy efficiency data Q k(ck obtained in the step S3) extracts the energy e i,k of the underwater sensor node and the energy collected by the node As input to the neural network;
the input of the trained neural network is based on the predicted state information of the monitored target Current underwater sensor node energy e i,k, energy collected by node at previous moment/>These 3 nodes constitute; the output is composed of decision actions; obtaining a relation between the process state c k and the energy continuous management scheme through the trained neural network;
further, the solving of the energy continuous management scheme in the step S4 comprises two solving stages of an offline solving stage and an online correcting stage;
Wherein the offline solution phase comprises: segmenting the monitoring time at equal intervals; inputting the obtained initial prediction state information of the monitoring target, and solving the energy continuous management scheme of each segment in parallel and offline by using a neural network; the online correction stage comprises the following steps: acquiring actual state information of a monitoring target in an actual scene; comparing the actual state information with the predicted state information, and if the actual state information and the predicted state information have larger phase difference, inputting the actual state information, and obtaining decision action again through a neural network to realize online correction so as to obtain a final energy continuous management scheme; if the actual state information and the predicted state information have smaller differences, no correction is performed.
The beneficial effects are that: compared with the prior art, the method constructs the underwater sensor node energy model of the underwater sensor network in the step 1, and ensures the application universality and accuracy of the node energy model; the objective function and the constraint function of the energy continuous management method in the step 2 are innovated, and the energy continuous management is more comprehensively considered; the self-organization and self-adaptation advantages of the neural network in the step 4 are utilized, consumed energy distribution can be carried out while the working state of the underwater sensor node is controlled, and an energy continuous management scheme is obtained more efficiently and in real time by combining the online correction stage in the step 4, so that high-energy-efficiency monitoring and underwater sensor network energy continuous management are realized.
Drawings
FIG. 1 is a flow chart of a method for continuously managing energy of an underwater sensor network according to the present invention;
Fig. 2 is an energy model diagram of an underwater sensor network node constructed by the invention.
Detailed Description
The process according to the invention is illustrated below with reference to the figures and the detailed description
As shown in fig. 1, the method for continuously managing the energy of the underwater sensor network for monitoring disclosed by the invention comprises the following steps:
step 1: constructing an energy model of an underwater sensor node of the underwater sensor network;
As shown in fig. 2, the underwater sensor node has two working states, namely an active state and a standby state; in an activated state, the underwater sensor node executes a monitoring task, acquires measurement data related to a target by using a sensing module, and sends out the data by using a transmission module; in a standby state, the underwater sensor node executes an energy recovery task, and the energy collection module collects energy by utilizing water flow movement;
according to the working state, constructing an energy model of the underwater sensor node by the following expression:
wherein e i,k is the energy of the underwater sensor node i at the moment k; The energy required by the operation of the module is perceived at the moment k; The energy required by the operation of the module is transmitted for the moment k; /(I) The energy collection module collects the energy at the moment k, and the energy collection accords with a one-order Markov process, can be divided into L grades and meets/> Respectively representing the collected different energy levels; the corresponding transition probability is/> For/>By/>Become/>Probability of (2); e max represents the upper energy limit of the underwater sensor node; p i is an operating state selection function, p i =1 in the active state, and p i =0 in the standby state; min { a, b } represents the minimum value of return a and b, i.e./>Representation returnAnd the minimum in e max.
Step 2: constructing an objective function and a constraint function of an energy continuous management scheme based on an underwater sensor node energy model;
defining energy efficiency The monitoring effect under the change of unit energy is achieved;
Wherein, Is mutual information and represents monitoring effect, and is transmitted by energy/>Is a function of (1); Δe i,k＝ei,k-ei,k-1 is the energy change;
The objective of energy continuous management is to maximize the energy efficiency of the underwater sensor network in the monitoring time, and the corresponding objective function expression is:
k is the monitoring duration, and M (M is more than or equal to 4) is the number of underwater sensor nodes forming the underwater sensor network.
The method is limited by the high dimensionality of the underwater scene, and at least 4 underwater sensor nodes are needed to participate in monitoring in order to ensure the stability of monitoring; therefore, an active node number constraint is constructed, and the corresponding expression is:
The energy consumed by the measuring module and the transmission module cannot exceed the current energy due to the limitation of the energy of the underwater sensor node; thus, the energy constraint per unit time is constructed, and the corresponding expression is:
where e i,T represents the maximum energy that node i can provide at time T, T ε {1,2, …, K }.
Step3: constructing a cost function for energy continuous management, and setting different process states to obtain corresponding energy efficiency data;
Defining a process state c k, including e i,k and Wherein/>Denoted as energy collected by the energy collection module at time k-1;
defining decision action, i.e. energy continuous management scheme, comprising p i, And/>
Under the condition that the constraint condition in the step 2 is met, constructing a cost function for energy continuous management, wherein the corresponding expression is:
Wherein, Q k+1(ck+1) is the energy efficiency data corresponding to the process state c k+1 at time k+1, and the energy efficiency data Q k(ck is obtained by bringing the energy efficiency data into the process state c k under different monitoring times.
Step 4: and (3) training a neural network model according to the initial prediction state information of the monitoring target and the energy efficiency data obtained in the step (3), and solving an energy continuous management scheme.
The state information X k defining the monitoring target comprises the state information of the monitoring target on the position, the speed and the acceleration at the moment k;
Monitoring predicted status information of a target Then it is the prediction of state information X k, the initial predicted state information/>, of the monitored targetPrediction state information when k=0;
predicting state information Can be obtained by particle filtering technology; specifically, at k=0, the particle filtering technique will produce initial particles/>, based on a priori knowledge about the targetP epsilon {1,2, …, N }, N being the number of particles, and then calculating the initial predicted state information/>, using a formulaThe specific formula is as follows:
when k > 0, the particle filtering technique will be based on the predicted state information of the previous time Generating predicted particles/>Then the prediction state information/>, is calculated by the formulaThe specific formula is as follows:
the energy efficiency data Q k(ck) can extract the energy e i,k of the underwater sensor node and collect the energy from the node As input to a trained neural network;
the input of the trained neural network is based on the predicted state information of the monitored target Node energy e i,k of current underwater sensor and node energy collection/>These 3 nodes constitute; the output is composed of decision actions; obtaining a relation between a process state and an energy continuous management scheme through the trained neural network;
Solving the two solving stages of the energy continuous management scheme, namely an offline solving stage and an online correction stage;
Wherein the offline solution phase comprises: segmenting the monitoring time at equal intervals; inputting the obtained initial prediction state information of the monitoring target, and solving the energy continuous management scheme of each segment in parallel and offline by using a neural network; the online correction stage comprises the following steps: acquiring actual state information of a monitoring target in an actual scene; comparing the actual state information with the predicted state information, and if the actual state information and the predicted state information have larger phase difference, inputting the actual state information, and obtaining decision action again through a neural network to realize online correction so as to obtain a final energy continuous management scheme; if the actual state information and the predicted state information have smaller differences, no correction is performed.
Claims (3)
1. The monitoring-oriented underwater sensor network energy continuous management method is characterized by comprising the following steps of:
S1, constructing an energy model of an underwater sensor node of an underwater sensor network; the method comprises the following steps:
the underwater sensor node has two working states, namely an activated state and a standby state; in an activated state, the underwater sensor node executes a monitoring task, acquires measurement data related to a target by using a sensing module, and sends the measurement data out by using a transmission module; in a standby state, the underwater sensor node executes an energy recovery task, and the energy collection module collects energy by utilizing water flow movement;
according to the working state, constructing an energy model of the underwater sensor node by the following expression:
Wherein e i,k+1 is the energy of the underwater sensor node i at the moment k+1; e i,k is the energy of the underwater sensor node i at the moment k; The energy required by the operation of the module is perceived at the moment k; /(I) The energy required by the operation of the module is transmitted for the moment k; /(I)The energy collection module collects energy at the moment k, the energy collection accords with a one-order Markov process, is divided into L grades, and meets the requirement Respectively representing the collected different energy levels; the corresponding transition probability is For/>By/>Become/>Probability of (2); e max represents the upper energy limit of the underwater sensor node; p i is an operating state selection function, p i =1 in the active state, and p i =0 in the standby state; /(I)Representation returnAnd the minimum in e max;
s2, constructing an objective function and a constraint function of an energy continuous management scheme based on an energy model of the underwater sensor node; the method comprises the following steps:
defining energy efficiency The monitoring effect under the change of unit energy is achieved;
Wherein, Is mutual information and represents monitoring effect, and is transmitted by energy/>Is a function of (1); Δe i,k＝ei,k-ei,k41 is the energy change at the moment adjacent to the underwater sensor node i;
The objective of energy continuous management is to maximize the energy efficiency of the underwater sensor network in the monitoring time, and the corresponding objective function expression is:
Wherein K is the monitoring time length, M is the number of underwater sensor nodes forming an underwater sensor network, and M is more than or equal to 4;
The method is limited by the high dimensionality of the underwater scene, and at least 4 underwater sensor nodes are needed to participate in monitoring in order to ensure the stability of monitoring; therefore, an active node number constraint is constructed, and the corresponding expression is:
The energy consumed by the measuring module and the transmission module cannot exceed the current energy due to the limitation of the energy of the underwater sensor node; thus, the energy constraint per unit time is constructed, and the corresponding expression is:
wherein e i,B represents the maximum energy that node i can provide at time T, T ε {1,2, …, K };
S3, constructing a cost function for energy continuous management, and setting different process states to obtain corresponding energy efficiency data; the method comprises the following steps:
defining a process state c k, comprising And/>Wherein/>Denoted as energy collected by the energy collection module at time k-1;
defining decision action, i.e. energy continuous management scheme, comprising p i, And/>
Under the condition that the constraint function in the step S2 is satisfied, constructing a cost function for energy continuous management, wherein the corresponding expression is:
Wherein, Q k(ck) is the energy efficiency data corresponding to the process state c k at the k moment, and the process state c k under different monitoring moments is brought to obtain the corresponding energy efficiency data Q k(ck);
And S4, training a neural network model according to the prediction state information of the monitoring target and the energy efficiency data obtained in the S3, and solving an energy continuous management scheme.
2. The method for continuously managing energy of an underwater sensor network for monitoring according to claim 1, wherein in step S4, training a neural network model according to the predicted state information of the monitored target and the energy efficiency data obtained in step S3 is specifically:
The state information X k defining the monitoring target comprises information of the monitoring target on position, speed and acceleration at the moment k;
predictive status information of the monitored target Is the prediction of state information X k, and the initial predicted state information/>, of the monitoring targetPrediction state information when k=0;
predicting state information Obtained by a particle filtering technique; specifically, at k=0, the particle filtering technique will produce initial particles/>, based on a priori knowledge about the targetN is the number of particles, and then the initial prediction state information/>' is calculated by using a formulaThe specific formula is as follows:
When k >0, the particle filtering technique will be based on the predicted state information of the previous time Generating predicted particles/>Then, the prediction state information/>, is calculated by using a formulaThe specific formula is as follows:
The energy efficiency data Q k(ck obtained in the step S3) extracts the energy e i,k of the underwater sensor node and the energy collected by the node As input to the neural network;
the input of the trained neural network is based on the predicted state information of the monitored target Current underwater sensor node energy e i,k, energy collected by node at previous moment/>These 3 nodes constitute; the output is composed of decision actions; the relationship between the process state c k and the energy-sustaining management scheme is obtained through the trained neural network.
3. The method for continuously managing energy of a monitoring-oriented underwater sensor network according to claim 1, wherein the solving of the energy continuously managing scheme in the step S4 includes two solving stages of an offline solving stage and an online correcting stage;
Wherein the offline solution phase comprises: segmenting the monitoring time at equal intervals; inputting the obtained initial prediction state information of the monitoring target, and solving the energy continuous management scheme of each segment in parallel and offline by using a neural network; the online correction stage comprises the following steps: acquiring actual state information of a monitoring target in an actual scene; comparing the actual state information with the predicted state information, and if the actual state information and the predicted state information have larger phase difference, inputting the actual state information, and obtaining decision action again through a neural network to realize online correction so as to obtain a final energy continuous management scheme; if the actual state information and the predicted state information have smaller differences, no correction is performed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111282375.8A CN114096010B (en) | 2021-11-01 | 2021-11-01 | Monitoring-oriented underwater sensor network energy continuous management method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111282375.8A CN114096010B (en) | 2021-11-01 | 2021-11-01 | Monitoring-oriented underwater sensor network energy continuous management method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114096010A CN114096010A (en) | 2022-02-25 |
| CN114096010B true CN114096010B (en) | 2024-05-07 |
Family
ID=80298428
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111282375.8A Active CN114096010B (en) | 2021-11-01 | 2021-11-01 | Monitoring-oriented underwater sensor network energy continuous management method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114096010B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014155028A1 (en) * | 2013-03-28 | 2014-10-02 | Toshiba Research Europe Limited | Allocating energy resources in a network signaling node |
| CN110191422A (en) * | 2019-04-09 | 2019-08-30 | 上海海事大学 | Ocean underwater sensor network target tracking method |
| WO2019192172A1 (en) * | 2018-04-04 | 2019-10-10 | 歌尔股份有限公司 | Attitude prediction method and apparatus, and electronic device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9734724B2 (en) * | 2014-09-02 | 2017-08-15 | University Of Malta | Method and system for recovering the energy state of an aircraft during descent |
-
2021
- 2021-11-01 CN CN202111282375.8A patent/CN114096010B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014155028A1 (en) * | 2013-03-28 | 2014-10-02 | Toshiba Research Europe Limited | Allocating energy resources in a network signaling node |
| WO2019192172A1 (en) * | 2018-04-04 | 2019-10-10 | 歌尔股份有限公司 | Attitude prediction method and apparatus, and electronic device |
| CN110191422A (en) * | 2019-04-09 | 2019-08-30 | 上海海事大学 | Ocean underwater sensor network target tracking method |
Non-Patent Citations (2)
| Title |
|---|
| IEEE Access Special Section Editorial Smart Grids: a Hub of Interdisciplinary Research;Mubashir Husain Rehmani等;《IEEE》;20151231;全文 * |
| 基于水声传感器网络的目标纯方位运动分析;王彪;曾庆军;解志斌;黄海宁;;中国造船;20110320(第01期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114096010A (en) | 2022-02-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111343650B (en) | Urban scale wireless service flow prediction method based on cross-domain data and loss resistance | |
| KR20210024106A (en) | Controller for controlling the technical system and method for configuring the controller | |
| CN112437131B (en) | Data dynamic acquisition and transmission method considering data correlation in Internet of things | |
| Shinde et al. | Environment monitoring system through Internet of Things (IOT) | |
| CN101237357B (en) | Online failure detection method for industrial wireless sensor network | |
| CN114021836A (en) | Multivariable reservoir water inflow amount prediction system based on different-angle fusion, training method and application | |
| CN114936409A (en) | Digital twinning modeling method for civil engineering structure | |
| Chen et al. | Sampling-based event-triggered and self-triggered control for linear systems | |
| Li et al. | Short-term passenger flow prediction of a passageway in a subway station using time space correlations between multi sites | |
| CN114096010B (en) | Monitoring-oriented underwater sensor network energy continuous management method | |
| Wang et al. | Short-term wind speed and power forecasting for smart city power grid with a hybrid machine learning framework | |
| Chi et al. | Comparison of two multi-step ahead forecasting mechanisms for wind speed based on machine learning models | |
| CN113344283A (en) | Energy internet new energy consumption capacity assessment method based on edge intelligence | |
| Jiang et al. | Understanding wind turbine interactions using spatiotemporal pattern network | |
| CN116578858A (en) | Air compressor fault prediction and health degree evaluation method and system based on graphic neural network | |
| Mohammadian et al. | Learning solutions for intertemporal power systems optimization with recurrent neural networks | |
| Pathiravasam et al. | Spatio-temporal characteristics based wind speed predictions | |
| Luna et al. | Super-short term wind speed prediction based on artificial neural networks for wind turbine control applications | |
| Pellegrini | Intelligent wireless sensor nodes in water monitoring systems | |
| Peng et al. | LITHIUM‐ION BATTERY REMAINING USEFUL LIFE ESTIMATION BASED ON ENSEMBLE LEARNING WITH LS‐SVM ALGORITHM | |
| Liu et al. | A fusion prognostic approach based on multi-kernel relevance vector machine and Bayesian model averaging | |
| Jiang et al. | Finite-horizon adaptive dynamic programming for collaborative target tracking in energy harvesting wireless sensor networks | |
| CN117505074B (en) | Electric precipitation control method and system based on energy-saving analysis | |
| JP7463515B2 (en) | CONTROL DEVICE FOR CONTROLLING A TECHNICAL SYSTEM AND METHOD FOR CONFIGURING A CONTROL DEVICE - Patent application | |
| Kang et al. | Real-time production performance analysis using machine degradation signals: A two-machine case |
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 |