CN108924897A - A kind of mobile sink paths planning method based on deeply learning algorithm - Google Patents
A kind of mobile sink paths planning method based on deeply learning algorithm Download PDFInfo
- Publication number
- CN108924897A CN108924897A CN201810702377.XA CN201810702377A CN108924897A CN 108924897 A CN108924897 A CN 108924897A CN 201810702377 A CN201810702377 A CN 201810702377A CN 108924897 A CN108924897 A CN 108924897A
- Authority
- CN
- China
- Prior art keywords
- network
- value
- convolutional neural
- neural networks
- grid
- 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.)
- Withdrawn
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W40/00—Communication routing or communication path finding
- H04W40/02—Communication route or path selection, e.g. power-based or shortest path routing
- H04W40/04—Communication route or path selection, e.g. power-based or shortest path routing based on wireless node resources
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/04—Network management architectures or arrangements
- H04L41/044—Network management architectures or arrangements comprising hierarchical management structures
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W40/00—Communication routing or communication path finding
- H04W40/24—Connectivity information management, e.g. connectivity discovery or connectivity update
- H04W40/32—Connectivity information management, e.g. connectivity discovery or connectivity update for defining a routing cluster membership
-
- 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
Abstract
The present invention discloses a kind of mobile sink paths planning method based on deeply learning algorithm, the path planning of mobile sink is completed using the method for deeply study, the network state of rasterizing is mapped as RGB image to be input in depth convolutional neural networks, network parameter is constantly updated by training.In actual application, actual network state need to be only input in trained neural network, the best walking path of sink can be obtained.The method of the present invention can comprehensively consider data delay requirement and the network energy consumption of wireless sensor network, compared to traditional wireless sensor network, the invention can efficient balance network energy consumption, while improving energy efficiency.Network state is subjected to rasterizing processing, reduces the complexity of network state.
Description
Technical field
The invention belongs to wireless sensor network technology field more particularly to a kind of shiftings based on deeply learning algorithm
Dynamic sink paths planning method.
Background technique
Wireless sensor network is the aggregation node by being deployed in a large amount of sensor node in network area, acquiring information
And management node forms, and is communicated in a multi-hop fashion between sensor node, forms multihop self-organizing network.Wirelessly
Sensor network can be acquired, handle and transmit to data in region, in network's coverage area, sensor node acquisition
And data are handled, and be transmitted to other sensors node or sink node.
In traditional wireless sensor network, the position of all nodes all immobilizes, and sensor node is mostly
It is battery powered, once deployment is difficult to replacement battery.In a WSN, most typical data collection mode is sensor node number
According to base station or sink node is transmitted in a multi-hop fashion, the sensor node close to base station or sink carries more forwardings
Task, energy consumption is very fast, leads to Energy volution and hot spot occur.The introducing effective solution of mobile sink with
Upper problem is equipped with mobile device on sink node, by the movement of sink, so that continuing to the node of sink forwarding data
It changes, balanced node load reduces network energy consumption.
In the wireless sensor network based on mobile sink, sink is moved simultaneously in network area according to certain track
The data of sensor node are acquired, the movement routine and mode of sink affects the performance and working efficiency of whole network.Therefore
It makes rational planning for the movement routine of sink, enables wireless sensor network data collected in data delay requires, simultaneously
Guaranteeing that network energy consumption reaches minimum is the key that this problem.The present invention proposes a kind of sink based on deeply learning algorithm
Paths planning method can effectively improve data collection efficiency and network energy efficiency.
Summary of the invention
It is a kind of based on deeply learning algorithm the technical problem to be solved by the present invention is to be proposed for background technique
Paths planning method of the mobile sink in wireless sensor network region can comprehensively consider data delay requirement and network energy
Consumption.The present invention is acted certainly by the graphical treatment and modeling to network environment, and using deeply learning algorithm
Plan has stronger real-time.
The present invention uses following technical scheme in order to solve the above problem, and specific step is as follows:
Step 1:It is approximately a square area by wireless sensor network region, and does rasterizing processing, forms N ◇
N number of equal-sized square grid;
Step 2:Wireless sensor node is randomly dispersed in network area, and random distribution has certain amount in each grid
Sensor node, and the data type (delay requirement etc.) for assuming that each grid inner sensor node carries is identical;
Step 3:An aggregation node is elected in each grid according to certain rule, is converged in grid where sink is collected
The data of poly- node;
Step 4:Priority is carried out to data in grid according to the delay requirement of data in each grid and network energy efficiency to draw
Point;
Step 5:The network model of rasterizing is mapped as a RGB image, different colors represents different priority;
Step 6:It is input to RGB image as state in depth convolutional neural networks, and does following processing:
Step 6.1:A multilayer convolutional neural networks are constructed, including input layer, 4 layers of convolutional layer, improved are connected entirely
Connect layer and output layer, wherein traditional full articulamentum is divided into two parts, calculates separately do well value and movement advantage, and
The two is added as output Q value;
Step 6.2:Mobile sink randomly selects an action value simultaneously at current state s from possible action value list
The movement is executed, the NextState s ' of reward value r and network after obtaining execution are obtained sample value (s, a, r, s ');
Continuous collecting sample, and be stored in experience replay memory, form sample set D;
Step 6.3:Construct two networks:Depth convolutional neural networks and target depth convolutional neural networks, and initialize
State s is input to depth convolution mind by weight, stochastical sampling sample (s, a, r, the s ') in sample set D in the form of RGB image
Through in network, and the Q value of all possible actions is calculated, and corresponding s ' is input to target depth convolutional neural networks and is fallen into a trap
Calculate corresponding maximum Q value;
Step 6.4:Continuous iteration updates the parameter of depth convolutional neural networks and target depth convolutional neural networks, reaches
To after convergence, trained network parameter is obtained;
Step 7:Network state is mapped as being input in trained network after RGB image, obtains the optimal road of sink
Diameter.
As a kind of the further preferred of mobile sink paths planning method based on deeply learning algorithm of the present invention
Scheme, in step 1, the area size of the wireless sensor network of planning is 100 ◇ 100m, is divided into 10 ◇, 10 units
Lattice.
As a kind of the further preferred of mobile sink paths planning method based on deeply learning algorithm of the present invention
Scheme, in step 4, data priority division rule is:Data delay requirement is stringenter, and priority is higher;In delay requirement
On the basis of, according to CP caching data volume number divided, data volume is more, and priority is higher;And be divided into 6 it is excellent
First grade.
As a kind of the further preferred of mobile sink paths planning method based on deeply learning algorithm of the present invention
Scheme is learnt and is identified to different colours feature by depth convolutional neural networks in step 6;Deeply study
Algorithm more new formula is that (s, a)=r+ γ (max (Q (s ', a '))), wherein s indicates current state to Q, and a indicates currently to take dynamic
Work value, r indicate the reward value for taking movement a to obtain later, and s ' expression obtains after taking action value a at current state s
One state value, a ' are next action value of current state;γ is discount factor.
The invention adopts the above technical scheme compared with prior art, has the following technical effects:
Mobile sink paths planning method proposed by the present invention based on deeply study uses image and Grid Method phase
In conjunction with method network environment is handled, reduce the complexity of network state, simplify environmental treatment process;It adopts simultaneously
The method divided with data priority, has comprehensively considered data delay and network energy consumption, compared to other methods, real-time is more
Good, network efficiency is higher.
Detailed description of the invention
Fig. 1:The network structure of rasterizing
Fig. 2:RGB image based on WSN
Fig. 3:System acting space
Fig. 4:Sink path planning algorithm flow chart based on deeply study
Specific embodiment
The present invention will be further explained below with reference to the attached drawings.
The present invention plans mobile sink path using deeply learning algorithm in real time, below to deeply
The process for practising algorithm is illustrated:
The present invention selects the movement of sink using greedy strategy, i.e., action value has certain probability to produce at random
It is raw.The probability of action value is generated by constantly reducing greedy strategy, while constantly being increased by the probability that tactful network generates action value
Greatly, doing so can be avoided tactful network and falls into local optimum.
State of the invention is a RGB image, by grid (such as Fig. 1 of entire wireless sensor network region division
It is shown) it is mapped according to data priority, as shown in Fig. 2, network state complexity is lower.
When motion space, that is, sink of the invention is in a certain state, the everything value that can be taken, the present invention in sink
Can be mobile to the grid in surrounding 8 directions, therefore motion space is 8 directions, as shown in Figure 3.
Reward functions of the invention are defined according to the data priority of grid, and the data priority of grid is higher, reward
It is worth higher.
As shown in figure 4, algorithm flow of the invention is as follows:
Step 1:It is approximately a square area by wireless sensor network region, and does rasterizing processing, forms N ◇
N number of equal-sized square grid;
Step 2:Wireless sensor node is randomly dispersed in network area, and random distribution has certain amount in each grid
Sensor node, and the data type (delay requirement etc.) for assuming that each grid inner sensor node carries is identical;
Step 3:An aggregation node is elected in each grid according to certain rule, is converged in grid where sink is collected
The data of poly- node;
Step 4:Priority is carried out to data in grid according to the delay requirement of data in each grid and network energy efficiency to draw
Point:Data delay requirement is stringenter, and priority is higher;On the basis of delay requirement, according to CP caching data volume number
It is divided, data volume is more, and priority is higher;
Step 5:The network model of rasterizing is mapped as a RGB image, different colors represents different priority;
Step 6:It is input to RGB image as state in depth convolutional neural networks, and does following processing:
Step 6.1:A multilayer convolutional neural networks are constructed, including input layer, 4 layers of convolutional layer, improved are connected entirely
Connect layer and output layer, wherein traditional full articulamentum is divided into two parts, calculates separately do well value and movement advantage, and
The two is added as output Q value;
Step 6.2:Mobile sink randomly selects an action value simultaneously at current state s from possible action value list
The movement is executed, the NextState s ' of reward value r and network after obtaining execution are obtained sample value (s, a, r, s ');
Continuous collecting sample, and be stored in experience replay memory, form sample set D;
Step 6.3:Construct two networks:Depth convolutional neural networks and target depth convolutional neural networks, and initialize
State s is input to depth convolution mind by weight, stochastical sampling sample (s, a, r, the s ') in sample set D in the form of RGB image
Through in network, and the Q value of all possible actions is calculated, and corresponding s ' is input to target depth convolutional neural networks and is fallen into a trap
Calculate corresponding maximum Q value;
Step 6.4:Continuous iteration updates the parameter of depth convolutional neural networks and target depth convolutional neural networks, reaches
To after convergence, trained network parameter is obtained;
Step 7:Network state is mapped as being input in trained network after RGB image, obtains the optimal road of sink
Diameter.
Claims (4)
1. a kind of mobile sink paths planning method based on deeply learning algorithm, which is characterized in that comprise the steps of:
Step 1:It is approximately a square area by wireless sensor network region, and does rasterizing processing, it is N number of forms N ◇
Equal-sized square grid;
Step 2:Wireless sensor node is randomly dispersed in network area, and random distribution has the biography of preset quantity in each grid
Sensor node, and the data type for assuming that each grid inner sensor node carries is identical;
Step 3:An aggregation node is elected in each grid, sink collects the data of aggregation node in the grid of place;
Step 4:Priority division is carried out to data in grid according to the delay requirement of data in each grid and network energy efficiency;
Step 5:The network model of rasterizing is mapped as a RGB image, different colors represents different priority;
Step 6:It is input to RGB image as state in depth convolutional neural networks;
Step 7:Network state is mapped as being input in trained network after RGB image, obtains the optimal path of sink.
2. as described in claim 1 based on the mobile sink paths planning method of deeply learning algorithm, which is characterized in that
Step 6 is specially:
Step 6.1:A multilayer convolutional neural networks are constructed, including input layer, 4 layers of convolutional layer, improved full articulamentum
And output layer, wherein traditional full articulamentum is divided into two parts, calculates separately do well value and movement advantage, and by two
Person is added as output Q value;
Step 6.2:Mobile sink randomly selects an action value and is executed from possible action value list at current state s
The movement, the NextState s ' of reward value r and network after obtaining execution are obtained sample value (s, a, r, s ');Continue
Collecting sample, and be stored in experience replay memory, form sample set D;
Step 6.3:Construct two networks:Depth convolutional neural networks and target depth convolutional neural networks, and weight is initialized,
State s is input to depth convolutional Neural net by stochastical sampling sample (s, a, r, the s ') in sample set D in the form of RGB image
In network, and the Q value of all possible actions is calculated, and corresponding s ' is input in target depth convolutional neural networks and is calculated
Corresponding maximum Q value;
Step 6.4:Continuous iteration updates the parameter of depth convolutional neural networks and target depth convolutional neural networks, reaches receipts
After holding back, trained network parameter is obtained.
3. as described in claim 1 based on the mobile sink paths planning method of deeply learning algorithm, which is characterized in that
In step 1, the area size of the wireless sensor network of planning is 100 ◇ 100m, is divided into 10 ◇, 10 cells.
4. as described in claim 1 based on the mobile sink paths planning method of deeply learning algorithm, which is characterized in that
In step 6, different colours feature is learnt and is identified by depth convolutional neural networks;Deeply learning algorithm is more
New formula be Q (s, a)=r+ γ (max (Q (s ', a '))), wherein s indicates current state, and a indicates the action value currently taken,
R indicates the reward value for taking movement a to obtain later, and s ' expression obtains obtaining NextState after taking action value a at current state s
Value, a ' are next action value of current state;γ is discount factor.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810702377.XA CN108924897A (en) | 2018-06-30 | 2018-06-30 | A kind of mobile sink paths planning method based on deeply learning algorithm |
CN201910316246.2A CN109936865B (en) | 2018-06-30 | 2019-04-19 | Mobile sink path planning method based on deep reinforcement learning algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810702377.XA CN108924897A (en) | 2018-06-30 | 2018-06-30 | A kind of mobile sink paths planning method based on deeply learning algorithm |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108924897A true CN108924897A (en) | 2018-11-30 |
Family
ID=64422487
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810702377.XA Withdrawn CN108924897A (en) | 2018-06-30 | 2018-06-30 | A kind of mobile sink paths planning method based on deeply learning algorithm |
CN201910316246.2A Active CN109936865B (en) | 2018-06-30 | 2019-04-19 | Mobile sink path planning method based on deep reinforcement learning algorithm |
Family Applications After (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910316246.2A Active CN109936865B (en) | 2018-06-30 | 2019-04-19 | Mobile sink path planning method based on deep reinforcement learning algorithm |
Country Status (1)
Country | Link |
---|---|
CN (2) | CN108924897A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109726676A (en) * | 2018-12-28 | 2019-05-07 | 苏州大学 | The planing method of automated driving system |
CN109754075A (en) * | 2019-01-16 | 2019-05-14 | 中南民族大学 | Dispatching method, equipment, storage medium and the device of wireless sensor network node |
CN110351754A (en) * | 2019-07-15 | 2019-10-18 | 北京工业大学 | Industry internet machinery equipment user data based on Q-learning calculates unloading decision-making technique |
CN110417664A (en) * | 2019-07-31 | 2019-11-05 | 国家电网有限公司信息通信分公司 | Business route distribution method and device based on power telecom network |
CN110703766A (en) * | 2019-11-07 | 2020-01-17 | 南京航空航天大学 | Unmanned aerial vehicle path planning method based on transfer learning strategy deep Q network |
CN112188428A (en) * | 2020-09-28 | 2021-01-05 | 广西民族大学 | Energy efficiency optimization method for Sink node in sensing cloud network |
CN112867023A (en) * | 2020-12-30 | 2021-05-28 | 北京理工大学 | Method for minimizing perception data acquisition delay through dynamic scheduling of unmanned terminal |
CN113867357A (en) * | 2021-10-12 | 2021-12-31 | 河南嘉晨智能控制股份有限公司 | Low-delay path planning algorithm for industrial vehicle |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111413974B (en) * | 2020-03-30 | 2021-03-30 | 清华大学 | Automobile automatic driving motion planning method and system based on learning sampling type |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP2360629A3 (en) * | 2005-05-07 | 2012-04-11 | Stephen L. Thaler | Device for the autonomous bootstrapping of useful information |
CN104698838B (en) * | 2014-12-23 | 2017-03-29 | 清华大学 | Based on the fuzzy scheduling rule digging method that domain dynamic is divided and learnt |
US10191495B2 (en) * | 2015-12-17 | 2019-01-29 | Board Of Trustees Of The University Of Arkansas | Distributed ceiling-mounted smart cameras for multi-unmanned ground vehicle routing and coordination |
US20200034620A1 (en) * | 2016-08-05 | 2020-01-30 | Neu Robotics, Inc. | Self-reliant autonomous mobile platform |
CN106970615B (en) * | 2017-03-21 | 2019-10-22 | 西北工业大学 | A kind of real-time online paths planning method of deeply study |
CN107065881B (en) * | 2017-05-17 | 2019-11-08 | 清华大学 | A kind of robot global path planning method based on deeply study |
CN107894773A (en) * | 2017-12-15 | 2018-04-10 | 广东工业大学 | A kind of air navigation aid of mobile robot, system and relevant apparatus |
-
2018
- 2018-06-30 CN CN201810702377.XA patent/CN108924897A/en not_active Withdrawn
-
2019
- 2019-04-19 CN CN201910316246.2A patent/CN109936865B/en active Active
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109726676A (en) * | 2018-12-28 | 2019-05-07 | 苏州大学 | The planing method of automated driving system |
CN109754075A (en) * | 2019-01-16 | 2019-05-14 | 中南民族大学 | Dispatching method, equipment, storage medium and the device of wireless sensor network node |
CN110351754A (en) * | 2019-07-15 | 2019-10-18 | 北京工业大学 | Industry internet machinery equipment user data based on Q-learning calculates unloading decision-making technique |
CN110417664A (en) * | 2019-07-31 | 2019-11-05 | 国家电网有限公司信息通信分公司 | Business route distribution method and device based on power telecom network |
CN110417664B (en) * | 2019-07-31 | 2022-02-25 | 国家电网有限公司信息通信分公司 | Service route distribution method and device based on power communication network |
CN110703766A (en) * | 2019-11-07 | 2020-01-17 | 南京航空航天大学 | Unmanned aerial vehicle path planning method based on transfer learning strategy deep Q network |
CN110703766B (en) * | 2019-11-07 | 2022-01-11 | 南京航空航天大学 | Unmanned aerial vehicle path planning method based on transfer learning strategy deep Q network |
CN112188428A (en) * | 2020-09-28 | 2021-01-05 | 广西民族大学 | Energy efficiency optimization method for Sink node in sensing cloud network |
CN112188428B (en) * | 2020-09-28 | 2024-01-30 | 广西民族大学 | Energy efficiency optimization method for Sink node in sensor cloud network |
CN112867023A (en) * | 2020-12-30 | 2021-05-28 | 北京理工大学 | Method for minimizing perception data acquisition delay through dynamic scheduling of unmanned terminal |
CN113867357A (en) * | 2021-10-12 | 2021-12-31 | 河南嘉晨智能控制股份有限公司 | Low-delay path planning algorithm for industrial vehicle |
Also Published As
Publication number | Publication date |
---|---|
CN109936865A (en) | 2019-06-25 |
CN109936865B (en) | 2021-01-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108924897A (en) | A kind of mobile sink paths planning method based on deeply learning algorithm | |
CN103906164B (en) | Maritime search and rescue wireless sensor network topology and topology control method | |
CN104394566B (en) | A kind of low power consumption adaptive clustering and multi-hop wireless sensor network topology control method based on fuzzy decision | |
Wang et al. | An elite hybrid metaheuristic optimization algorithm for maximizing wireless sensor networks lifetime with a sink node | |
CN104410997B (en) | A kind of clustering topology construction method for wireless sensor network | |
CN103095577B (en) | Context-sensitive Uneven Cluster routing algorithm | |
CN107205254B (en) | Mobile sink node access and interference rejection method and system based on tight delay constraint | |
WO2018107306A1 (en) | Probability neighborhood and obstacle avoidance-based data collection method for three-dimensional uasns | |
Liu et al. | Green mobility management in UAV-assisted IoT based on dueling DQN | |
CN103974366B (en) | A kind of wireless body area network route method based on enhancing study | |
CN107580293B (en) | Sink node repositioning method based on virtual force | |
Tang et al. | A novel data retrieving mechanism in wireless sensor networks with path-limited mobile sink | |
CN104883676A (en) | Cooperative safety communication method in multi-UAV environment | |
CN105722174A (en) | Node link scheduling method of heterogeneous integrated power consumption information collection network | |
Gu et al. | A Bayesian compressive data gathering scheme in wireless sensor networks with one mobile sink | |
CN104837155A (en) | Back propagation (BP) neural network type clustered sensor network data collection method | |
CN102595546B (en) | Wireless sensor actuator network data collecting and clustering method based on event driving | |
CN109152103A (en) | A kind of pair of wireless sensor network carries out network-building method and device | |
CN104065574A (en) | Uneven clustering routing method inside wireless sensor network layer | |
CN107969008A (en) | A kind of software definition Sensor Network concentrated route computational methods | |
CN106209261B (en) | The mobile data collection method of three-dimensional UASNs based on probability neighborhood grid | |
CN103826282B (en) | Set based on dump energy divides multi-hop routing method | |
Sankar et al. | Efficient Data Transmission Technique for Transmitting the Diagnosed Signals and Images in WBSN | |
CN103369619B (en) | A kind of method based on degree self-adaptative adjustment dynamic aggregation tree | |
CN105430620B (en) | A kind of method of data capture of mobile wireless sensing network |
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 | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20181130 |
|
WW01 | Invention patent application withdrawn after publication |