CN103249055A - Binary particle swarm algorithm based layered dispatching method for nodes of wireless sensor network - Google Patents
Binary particle swarm algorithm based layered dispatching method for nodes of wireless sensor network Download PDFInfo
- Publication number
- CN103249055A CN103249055A CN2013101719402A CN201310171940A CN103249055A CN 103249055 A CN103249055 A CN 103249055A CN 2013101719402 A CN2013101719402 A CN 2013101719402A CN 201310171940 A CN201310171940 A CN 201310171940A CN 103249055 A CN103249055 A CN 103249055A
- Authority
- CN
- China
- Prior art keywords
- network
- node
- particle
- population
- nodes
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Abstract
The invention adopts the binary particle swarm algorithm to perform layered dispatching for nodes of a wireless sensor network and belongs to the field of network technology and intelligent calculation. The method comprises the following steps: firstly, designing a method for searching an optimal node subset in the wireless sensor network based on the binary particle swarm algorithm, wherein according to the method, each particle is coded to be a 0/1 binary string with the length equal to number of the sensor nodes, 1 represents that the node enters the subset and 0 represents that the selection is not carried out; and realizing minimization of number of node subset sensors under the premise of meeting 100 percent network coverage according to a renewal formula of the binary particle swarm algorithm and a variation method of a reversion strategy. According to the method, through unceasingly calling the method for minimizing the number of the sensors of the optimal node subset, the nodes in the network are divided into disjoint subsets as far as possible so as to solve the optimization problem of layered dispatching for the network nodes. The method can effectively realize maximal layered optimization dispatching for the nodes in the wireless sensor network and plays an important role in prolonging the network service life.
Description
Technical field:
The present invention relates to wireless sensor network and computational intelligence two big fields, be specifically related to a kind of wireless sensor network node based on binary particle swarm algorithm and divide layer scheduling method.
Technical background:
(wireless sensor networks WSN) is an emerging technology and has become the popular and challenging research field of current society wireless sensor network.In numerous applications, battlefield surveillance for example, the monitoring of animal habitat ground, environment perception, family health care cares etc. need be carried out omnibearing monitoring to the scene.But under many circumstances, these environment of applications are not very friendly usually, or even abominable, therefore generally are difficult to pass through accurate mode of disposing placement sensor node in the zone that needs are monitored, and are difficult in definite position deployment transducer.In this case, general solution is by throwing in a large amount of sensor nodes in the area to be monitored at random, guaranteeing the covering fully of monitoring area by the mode of redundancy covering.Yet, a large amount of sensor nodes may cause the node life-span to reduce owing to the Communication Jamming between the node, therefore how research dispatches the sensor node of wireless sensor network effectively, save the network energy consumption, prolong network life, become the important research project in wireless sensor network field.
In existing a lot of researchs, occurred to prolong network and saved the technology that the problem of the energy is converted into best covering problem useful life.The starting point of best covering problem technical solution is: in view of the sensor node that has bulk redundancy in the network, by closing the unnecessary node of a part, under node that residue is activated satisfies the prerequisite that covers fully to monitor area, can energy savings, prolong network life.The target of best covering problem is the node subclass that finds one to satisfy the minimum number that guarded region is covered fully.Like this, can under the prerequisite that satisfies gamut covering demand, close other unnecessary node, not only can save the energy resource consumption that is caused by node conflict or contiguous the interchange, and owing to part of nodes can be in resting state, can save energy consumption equally.
Though best covering problem can be saved the energy consumption of network to a certain extent, prolong network life, if can on the technical solution of best covering problem further can prolong the life-span of network more effectively.Basic point of departure of the present invention is: by the solution to best covering problem, find the subclass of the minimum number of nodes that can cover fully monitor area; By the best covering problem of continuous solution, can find and as much as possiblely can satisfy a plurality of subclass that monitor area is covered fully; These subclass have formed the many levels of wireless sensor network, and these different node layer are carried out scheduling in turn, can intuitively and effectively prolong the life-span of network.Therefore, the problem of the present invention's solution is the node layering scheduling problem of wireless sensor network.
In order to solve the layered optimization scheduling of wireless sensor network, the present invention has adopted a kind of binary particle cluster algorithm.Binary particle swarm algorithm belongs to a kind of optimization algorithm with ability of searching optimum in computational intelligence field.Though particle cluster algorithm is simple owing to its concept, flow process succinctly is widely used in the optimization problem in a plurality of fields, it is exactly to fall into easily to possess optimum that there is a defective in this optimization algorithm.Therefore, in the present invention, when the node that adopts binary particle swarm algorithm to wireless sensor network carries out the layering optimizing scheduling, will be in conjunction with mutation operator based on the counter-rotating strategy of characteristics design of problem, be used for strengthening the diversity of algorithm, avoid algorithm to fall into the defective of local optimum easily.
In the present invention, at a large amount of redundant sensor node that exists in the wireless sensor network, recycle binary particle swarm algorithm, in each circulation, seek the optimal sensor node subclass (satisfying the subset of sensor nodes of the minimum number that monitor area is covered fully) in the network.This method is encoded to 0/1 binary string that length equals sensor node quantity with the particle of binary particle swarm algorithm, and 1 expression selects this node to enter subclass, and 0 expression is not selected; The variation method of the more new formula by binary particle swarm algorithm and a kind of strategy that reverses is implemented in and satisfies complete network and cover minimizing of node subclass number of sensors under the prerequisite.By constantly calling " the minimized method of optimum node subclass number of sensors ", be disjoint subset as much as possible with the node division in the network, and then solved the optimization problem of network node layering scheduling.The mutation operation of the present invention's design can strengthen the algorithm diversity, avoids algorithm to fall into the defective of local optimum easily.In conjunction with mutation operation, the binary particle swarm algorithm that the present invention uses can be efficiently carried out maximized hierarchy optimization scheduling to the node of wireless sensor network, to prolonging network life important effect is arranged.
Summary of the invention:
The present invention dispatches the node layering that binary particle swarm algorithm is used for wireless sensor network, and concrete content step is described below:
(1) for given network N etw, its maximum number of plies K=0 is set, check then whether the sensor node collection S in the network can cover network area 100%.If can, then carry out following step; If can not, but then export maximum hierarchy number K=0, terminator.
(2) using binary particle swarm algorithm to find out one group from the sensor node collection S of network N etw can carry out the 100% optimum node subclass S* that covers to the network area, and concrete flow process is as follows:
Step 1) generates the population that N particle forms particle cluster algorithm at random, and the position of each particle i and velocity encoded cine are expressed as X respectively
i=[x
I1, x
I2..., x
ID] and V
i=[v
I1, v
I2..., v
ID]; Wherein D is code length, and is identical with interstitial content in the network; Position X
iIn the value of each dimension be that 1 this node of expression is chosen in the subclass, be that 0 expression is not selected; The locative situation of change of speed.In initialized process, the present invention requires to guarantee to have at least in the population particle to satisfy 100% of whole network is covered, otherwise need produce population again.Owing to checked that network can be carried out 100% covering by all the sensors node before producing population, therefore can guarantee the success of this method.After the population that generation meets the demands, assess the adaptive value (adaptive value is the quantity of selecteed sensor node in the solution of particle representative, and this quality that is worth the bright solution of novel more is more high) of all particles, with the historical optimal location P of each particle i in season
i=[p
I1, p
I2..., p
ID] be current location X
i, and the position G=[g of global optimum of whole population is set
1, g
2..., g
D] be best that in all historical optimal locations.Attention is in assessment particle fitness function value, for satisfying the particle that network 100% covers, being the fitness function value by calculating its sensor node quantity of choosing among the node subclass S*, is number of nodes among all node set S of whole network otherwise its fitness function value is set.
Step 2) to each particle i, by its historical optimal location P
iThe speed V of the position G of global optimum with population
iUpgrade.For V
iEach the dimension v
Id(1≤d≤D), more new formula is accordingly: v
Id=v
Id+ c
1* r
1* (p
Id-x
Id)+c
2* r
2* (g
d-x
Id); C wherein
1And c
2Be 2.0, r
1And r
2Be the random number between interval [0,1].
Step 3) is used the position X of following policy update particle i
iUpgrade: to each dimension x
Id, at first calculate
Generate the random number r between interval [0,1] then, if r≤p then establishes x
Id=1, otherwise establish x
Id=0.
Step 4) is used the position X after the variation strategy upgrades particle i
iMake a variation: select certain one dimension of particle at random, the value that will tie up is reversed then, and namely 0 becomes 1,1 and becomes 0.
Position X after step 5) is upgraded particle i
iCarry out the assessment of adaptive value.Similarly, if new position X
iRepresented solution can satisfy 100% of network and cover, and is the fitness function value by calculating its sensor node quantity of choosing among the node subclass S* then, is number of nodes among all node set S of whole network otherwise its fitness function value is set.After the assessment adaptive value, if new fitness function value is than its historical optimal location P
iThe fitness function value better, then with P
iBe set to X
i, judge new P simultaneously
iWhether more excellent than the position G of global optimum of population, if then G is replaced with P
i
Step 6) is carried out above step 2 repeatedly), 3), 4) and 5) up to satisfying end condition, then the solution intermediate value of global optimum position G representative be 1 those tie up corresponding sensor node and represent to be chosen among the optimum node subclass S*.
(3) sensor node among the optimum node subclass S* is labeled as can not uses node among the sensor node collection S of network N etw, remaining sensor node form a new set of node S=S S*, and form a new network N etw.Simultaneously, K=K+1 is set;
(4) check whether the sensor node collection S in the network can cover network area 100%.If can, then forward step (2) to and continue to carry out; If can not, but then export maximum hierarchy number K, terminator.
Description of drawings:
Fig. 1 is based on the flow chart of the wireless sensor network node layering scheduling of binary particle swarm algorithm
Fig. 2 optimizes the flow chart of the optimum node subclass of wireless sensor network based on binary particle swarm algorithm
Embodiment:
Further the method for invention is described below in conjunction with accompanying drawing.
In Fig. 1, provided the top-level flow figure based on the wireless sensor network node layering scheduling of binary particle swarm algorithm.
Suppose to have a wireless sensor network Netw, disposed a large amount of sensor nodes by the mode of broadcasting sowing at random in the network area, S represents with node set.
Use the inventive method that whether the node of this wireless sensor network is carried out at first wanting the decision node S set can satisfy 100% of network N etw being covered before the layering scheduling, if can not, then can not carry out layering to node and dispatch.In this case, directly export maximum hierarchy number K=0 and termination routine.
Whether the decision node S set can satisfy the method that network 100% is covered is that grid point covers determining method.At first network is carried out the division of grid, each grid g is with the coordinate position (x at its grid center
g, y
g) expression.Each sensor node s among the S
iCoordinate position be (x
i, y
i), covering radius is R.By following formula:
Can judge sensor node s
iCovering gate lattice point g whether.Therefore, for any one grid point g, as long as there is at least one sensor node s
i∈ S can cover, and can think that then g can be covered by set of network nodes.If can both be capped each grid point g in the whole network, think that then network is covered by 100%.
According to Fig. 1, method of the present invention then enters the process of " using binary particle swarm algorithm to seek the optimum node subclass of wireless sensor network S* " after judging that network can be covered by 100%.The feature of this process is to use a kind of optimization algorithm to seek an optimum node subclass, and under the prerequisite that satisfies network 100% covering, the sensor node quantity that antithetical phrase is concentrated is carried out minimized optimization.The sensor node set of supposing current network Netw is S, and number of nodes is D, and then concrete operating process and is described in detail as follows as shown in Figure 2:
Step 1) generates the population that N particle forms particle cluster algorithm at random, and the position of each particle i and velocity encoded cine are expressed as X respectively
i=[x
I1, x
I2..., x
ID] and V
i=[v
I1, v
I2..., v
ID]; Wherein D is code length, and is identical with interstitial content in the network; Position X
iIn the value of each dimension be that 1 this node of expression is chosen in the subclass, be that 0 expression is not selected; The locative situation of change of speed.In initialized process, the present invention requires to guarantee to have at least in the population particle to satisfy 100% of whole network is covered, otherwise need produce population again.Owing to checked that network can be carried out 100% covering by all the sensors node before producing population, therefore can guarantee the success of this method.After the population that generation meets the demands, assess the adaptive value (adaptive value is the quantity of the selecteed sensor node in the solution of particle representative, and this quality that is worth the bright solution of novel more is more high) of all particles, with the historical optimal location P of each particle i in season
i=[p
I1, p
I2..., p
ID] be current location X
i, and the position G=[g of global optimum of whole population is set
1, g
2..., g
D] be best that in all historical optimal locations.Attention is in assessment particle fitness function value, for satisfying the particle that network 100% covers, being the fitness function value by calculating its sensor node quantity of choosing among the node subclass S*, is number of nodes among all node set S of whole network otherwise its fitness function value is set.
Step 2) to each particle i, by its historical optimal location P
iThe speed V of the position G of global optimum with population
iUpgrade.For V
iEach the dimension v
Id(1≤d≤D), more new formula is accordingly: v
Id=v
Id+ c
1* r
1* (p
Id-x
Id)+c
2* r
2* (g
d-x
Id); C wherein
1And c
2Be 2.0, r
1And r
2Be the random number between interval [0,1].
Step 3) is used the position X of following policy update particle i
iUpgrade: to each dimension x
Id, at first calculate
Generate the random number r between interval [0,1] then, if r≤p then establishes x
Id=1, otherwise establish x
Id=0.
Step 4) is used the position X after the variation strategy upgrades particle i
iMake a variation: select certain one dimension of particle at random, the value that will tie up is reversed then, and namely 0 becomes 1,1 and becomes 0.
Position X after step 5) is upgraded particle i
iCarry out the assessment of adaptive value.Similarly, if new position X
iRepresented solution can satisfy 100% of network and cover, and is the fitness function value by calculating its sensor node quantity of choosing among the node subclass S* then, is number of nodes among all node set S of whole network otherwise its fitness function value is set.After the assessment adaptive value, if new fitness function value is than its historical optimal location P
iThe fitness function value better, then with P
iBe set to X
i, judge new P simultaneously
iWhether more excellent than the position G of global optimum of population, if then G is replaced with P
i
Carry out above step 2 repeatedly), 3), 4) and 5) up to satisfying end condition, then the solution intermediate value of global optimum position G representative be 1 those tie up corresponding sensor node and represent to be chosen among the optimum node subclass S*.
Return the flow process of Fig. 1, method of the present invention afterwards, can think that node subclass S* forms a new layer, just obtains maximum number of plies K=K+1 by " using binary particle swarm algorithm to seek the optimum node subclass of wireless sensor network S* ".For the layering that other nodes beyond the node subclass S* are continued, method of the present invention is labeled as the sensor node among the optimum node subclass S* can not use node among the sensor node collection S of network N etw, then among the S remaining sensor node form a new set of node S=S S*, and formed a new network N etw.
At this moment, the judgement that method of the present invention covers new network N etw again judges that can new node set S carry out 100% covering to new network N etw.Form a new layer if of course, then continue " using binary particle swarm algorithm to seek the optimum node subclass of wireless sensor network S* "; Otherwise output maximum hierarchy number K at this moment.So iteration is judged and is optimized, till final node set S can't carry out 100% covering to network N etw.The K that at this time obtains is the maximum hierarchy number that the inventive method obtains.The resulting optimum node subclass S* of iteration " the use binary particle swarm algorithm is sought the optimum node subclass of wireless sensor network S* " is that each layer needs the sensor node of scheduling to gather each time.
Claims (4)
1. the wireless sensor network node based on binary particle swarm algorithm with mutation operation divides layer scheduling method, it is characterized in that but sensor node quantity by minimizing each layer is to reach the maximized purpose of node hierarchy number, simultaneously by in particle cluster algorithm, introducing mutation operation to strengthen the algorithm diversity, avoid algorithm to fall into the defective of local optimum easily, this method mainly may further comprise the steps:
(1) for given network N etw, its maximum number of plies K=0 is set, check then whether the sensor node collection S in the network can cover network area 100%, if can, then carry out following step; But otherwise output maximum hierarchy number K=0, terminator;
(2) using binary particle swarm algorithm to find out one group from the sensor node collection S of network N etw can carry out the 100% optimum node subclass S* that covers to the network area, and concrete flow process is as follows:
A) generate the population that N particle forms particle cluster algorithm at random, the position of each particle i and velocity encoded cine are expressed as X respectively
i=[x
I1, x
I2..., x
ID] and V
i=[v
I1, v
I2..., v
ID]; Wherein D is code length, and is identical with interstitial content in the network; Position X
iIn the value of each dimension be that 1 this node of expression is chosen in the subclass, be that 0 expression is not selected; The locative situation of change of speed; Assess the adaptive value of all particles, this adaptive value is the quantity of selecteed sensor node in the solution of particle representative, and this quality that is worth the bright solution of novel more is more high; Historical optimal location P with seasonal particle i
i=[p
I1, p
I2..., p
ID] be current location X
i, the position G=[g of global optimum of whole population
1, g
2..., g
D] be best that in all historical optimal locations;
B) to each particle i, by its historical optimal location P
iThe speed V of the position G of global optimum with population
iUpgrade; For V
iEach the dimension v
Id, 1≤d≤D wherein, more new formula is accordingly: v
Id=v
Id+ c
1* r
1* (p
Id-x
Id)+c
2* r
2* (g
d-x
Id); C wherein
1And c
2Be 2.0, r
1And r
2Be the random number between interval [0,1];
C) the position X of the following policy update particle i of use
iUpgrade: to each dimension x
Id, at first calculate
Generate the random number r between interval [0,1] then, if r≤p then establishes x
Id=1, otherwise establish x
Id=0;
D) use variation tactful in the position X after the particle i renewal
iMake a variation, strengthen the diversity of algorithm;
E) to the position X after the particle i renewal variation
iCarry out the assessment of adaptive value, if new fitness function value is than its historical optimal location P
iThe fitness function value better, then with P
iBe set to X
i, judge new P simultaneously
iWhether more excellent than the position G of global optimum of population, if then G is replaced with P
i
F) carry out above step b), c repeatedly), d) with e) up to satisfying end condition, then the solution intermediate value of global optimum position G representative be 1 those tie up corresponding sensor node and represent to be chosen among the optimum node subclass S*;
(3) sensor node among the optimum node subclass S* is labeled as can not uses node among the sensor node collection S of network N etw, remaining sensor node form a new set of node S=S S*, and form a new network N etw; K=K+1 is set;
(4) check whether the sensor node collection S in the network can cover network area 100%, if can, then forward step (2) to and continue to carry out; If can not, but then export maximum hierarchy number K, terminator.
2. based on the particle cluster algorithm initialization of population method described in the step (2)-a) of claim 1, it is characterized in that must guarantee to have at least in the population particle to satisfy covers 100% of whole network; Concrete method is to carry out the judgement of coverage rate after producing population at random, if there is particle to satisfy 100% of whole network is not covered, and then needs to produce again population; Owing to checked that network can be carried out 100% covering by all the sensors node before producing population, therefore can guarantee the success of this method.
3. based on step (2)-a) and the e of claim 1) described in particle fitness function value appraisal procedure, only it is characterized in that effectively assessing satisfying the particle that network 100% covers; Concrete method is for satisfying the particle that network 100% covers, and is the fitness function value by calculating its sensor node quantity of choosing among the node subclass S*, is number of nodes among all node set S of whole network otherwise its fitness function value is set.
4. based on the particle cluster algorithm variation method described in the step (2)-d) of claim 1, its feature is in the diversity that strengthens algorithm by the mode that increases random perturbation; Concrete method is: select certain one dimension of particle at random, the value that will tie up is reversed then, and namely 0 becomes 1,1 and becomes 0.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013101719402A CN103249055A (en) | 2013-04-25 | 2013-04-25 | Binary particle swarm algorithm based layered dispatching method for nodes of wireless sensor network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013101719402A CN103249055A (en) | 2013-04-25 | 2013-04-25 | Binary particle swarm algorithm based layered dispatching method for nodes of wireless sensor network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103249055A true CN103249055A (en) | 2013-08-14 |
Family
ID=48928221
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2013101719402A Pending CN103249055A (en) | 2013-04-25 | 2013-04-25 | Binary particle swarm algorithm based layered dispatching method for nodes of wireless sensor network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103249055A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103889022A (en) * | 2014-04-15 | 2014-06-25 | 河海大学 | Method for constructing condition monitoring network routing of photovoltaic power generation system |
| CN106703866A (en) * | 2017-03-09 | 2017-05-24 | 辽宁工程技术大学 | Method for distributing mine wind speed sensor |
| CN106886156A (en) * | 2017-05-03 | 2017-06-23 | 杭州电子科技大学 | Feed pipe gateway valve method based on binary system multi-objective particle swarm algorithm |
| CN111093216A (en) * | 2019-12-25 | 2020-05-01 | 北京石油化工学院 | Wireless sensor network node scheduling method based on improved binary particle swarm optimization |
| CN111542011A (en) * | 2020-04-27 | 2020-08-14 | 中山大学 | Layered wireless sensor network clustering routing method based on particle swarm optimization |
| CN115696354B (en) * | 2022-10-26 | 2024-04-19 | 金陵科技学院 | High-speed rail mobile communication system network coverage method based on improved particle swarm |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101448267A (en) * | 2008-12-31 | 2009-06-03 | 中山大学 | Wireless sensor network node coverage optimization method based on particle swarm algorithm |
-
2013
- 2013-04-25 CN CN2013101719402A patent/CN103249055A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101448267A (en) * | 2008-12-31 | 2009-06-03 | 中山大学 | Wireless sensor network node coverage optimization method based on particle swarm algorithm |
Non-Patent Citations (4)
| Title |
|---|
| ZHI-HUI ZHAN等: "《2012 Conference on Technologies and Applications of Artificial Intelligence》", 18 November 2012, article "Extended Binary Particle Swarm Optimization Approach for Disjoint Set Covers Problem in Wireless Sensor Networks", pages: 327-331 * |
| ZHI-HUI ZHAN等: "《Simulated Evolution and Learning》", 31 December 2010, article "Solving the Optimal Coverage Problem in WirelessSensor Networks Using Evolutionary ComputationAlgorithms", pages: 166-176 * |
| 刘杨、田学锋、詹志辉: "《南京大学学报（自然科学）》", 31 July 2011, article "粒子群优化算法惯量权重控制方法的研究" * |
| 陈有青、徐蔡星、钟文亮、张军: "《计算机工程与应用》", 1 April 2008, article "一种改进选择算子的遗传算法" * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103889022A (en) * | 2014-04-15 | 2014-06-25 | 河海大学 | Method for constructing condition monitoring network routing of photovoltaic power generation system |
| CN103889022B (en) * | 2014-04-15 | 2018-06-19 | 河海大学 | A kind of photovoltaic generating system status monitoring network route constructing method |
| CN106703866A (en) * | 2017-03-09 | 2017-05-24 | 辽宁工程技术大学 | Method for distributing mine wind speed sensor |
| CN106886156A (en) * | 2017-05-03 | 2017-06-23 | 杭州电子科技大学 | Feed pipe gateway valve method based on binary system multi-objective particle swarm algorithm |
| CN106886156B (en) * | 2017-05-03 | 2019-09-24 | 杭州电子科技大学 | Water supplying pipe gateway valve method based on binary system multi-objective particle swarm algorithm |
| CN111093216A (en) * | 2019-12-25 | 2020-05-01 | 北京石油化工学院 | Wireless sensor network node scheduling method based on improved binary particle swarm optimization |
| CN111542011A (en) * | 2020-04-27 | 2020-08-14 | 中山大学 | Layered wireless sensor network clustering routing method based on particle swarm optimization |
| CN115696354B (en) * | 2022-10-26 | 2024-04-19 | 金陵科技学院 | High-speed rail mobile communication system network coverage method based on improved particle swarm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103249055A (en) | Binary particle swarm algorithm based layered dispatching method for nodes of wireless sensor network | |
| US10320627B2 (en) | Cooperative coverage method of information perception for distributed network | |
| Liu et al. | Deep learning based optimization in wireless network | |
| Han et al. | A comparative study of routing protocols of heterogeneous wireless sensor networks | |
| Piovesan et al. | Joint load control and energy sharing for renewable powered small base stations: A machine learning approach | |
| CN103313263A (en) | Wireless sensor network node hierarchical scheduling method based on genetic algorithm | |
| John et al. | A survey of energy-aware cluster head selection techniques in wireless sensor network | |
| Agarwal et al. | Network lifetime enhanced tri‐level clustering and routing protocol for monitoring of offshore wind farms | |
| Alejandrino et al. | A hybrid data acquisition model using artificial intelligence and IoT messaging protocol for precision farming | |
| CN108184241A (en) | Towards the isomery directional sensor network node scheduling method of different priorities target | |
| CN102761881A (en) | Method for solving optimal coverage control set of static node in wireless sensor network | |
| Mittal et al. | Harmony Search Algorithm Based Threshold-sensitive Energy-Efficient Clustering Protocols for WSNs. | |
| Kalaikumar et al. | FABC-MACRD: Fuzzy and artificial Bee colony based implementation of MAC, clustering, routing and data delivery by cross-layer approach in WSN | |
| Benelhouri et al. | An improved gateway-based energy-aware multi-hop routing protocol for enhancing lifetime and throughput in heterogeneous WSNs | |
| Idrees et al. | Energy-efficient Data Processing Protocol in edge-based IoT networks | |
| Lin et al. | Maximum data collection rate routing for data gather trees with data aggregation in rechargeable wireless sensor networks | |
| Jahanshahi et al. | An efficient cluster head selection algorithm for wireless sensor networks using fuzzy inference systems | |
| Verma et al. | Fuzzy‐based techniques for clustering in wireless sensor networks (WSNs): Recent advances, challenges, and future directions | |
| El-Mougy et al. | A cognitive framework for WSN based on weighted cognitive maps and Q-learning | |
| Rocha et al. | A fully-decentralized semantic mechanism for autonomous wireless sensor nodes | |
| Dahmani et al. | A green fuzzy multi-objective approach to the RNP problem for LTE networks | |
| Baroudi | Management of RF energy harvesting: A survey | |
| Abadi et al. | A survey on utilizing reinforcement learning in wireless sensor networks routing protocols | |
| García et al. | Multi-layer Fog Computing Framework for Constrained LoRa Networks Intended for Water Quality Monitoring and Precision Agriculture Systems. | |
| Liu et al. | MMSCM: A multiple mobile sinks coverage maximization based hierarchical routing protocol for mobile wireless sensor networks |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20130814 |