CN110493844B - Data fusion alliance game method and system for wireless sensor network - Google Patents

Data fusion alliance game method and system for wireless sensor network Download PDF

Info

Publication number
CN110493844B
CN110493844B CN201910903311.1A CN201910903311A CN110493844B CN 110493844 B CN110493844 B CN 110493844B CN 201910903311 A CN201910903311 A CN 201910903311A CN 110493844 B CN110493844 B CN 110493844B
Authority
CN
China
Prior art keywords
unmanned aerial
aerial vehicle
alliance
sensor
data
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
Application number
CN201910903311.1A
Other languages
Chinese (zh)
Other versions
CN110493844A (en
Inventor
刘贵云
潘绪槟
赵志甲
蒋文俊
彭百豪
张杰钊
唐冬
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangzhou University
Original Assignee
Guangzhou University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangzhou University filed Critical Guangzhou University
Priority to CN201910903311.1A priority Critical patent/CN110493844B/en
Publication of CN110493844A publication Critical patent/CN110493844A/en
Application granted granted Critical
Publication of CN110493844B publication Critical patent/CN110493844B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

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
    • H04W40/10—Communication route or path selection, e.g. power-based or shortest path routing based on wireless node resources based on available power or energy
    • 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
    • H04W40/20—Communication route or path selection, e.g. power-based or shortest path routing based on geographic position or location
    • 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
    • H04W40/22—Communication route or path selection, e.g. power-based or shortest path routing using selective relaying for reaching a BTS [Base Transceiver Station] or an access point
    • 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
    • H04W52/00—Power management, e.g. TPC [Transmission Power Control], power saving or power classes
    • H04W52/02—Power saving arrangements
    • H04W52/0203—Power saving arrangements in the radio access network or backbone network of wireless communication networks
    • 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 invention discloses a data fusion alliance game method and system facing a wireless sensor network, wherein the method comprises the following steps: constructing a wireless sensor network-based alliance game model, taking a Charpy value as a solution of alliance profit allocation, and determining a relay node according to the Charpy value; the method comprises the steps that an unmanned aerial vehicle is used as a sink node in a wireless sensor network to collect data, and the flight path and the flight direction of the unmanned aerial vehicle are determined; the unmanned aerial vehicle carries out preliminary data fusion on the collected data, and eliminates repeated parts in the collected data. The unmanned aerial vehicle is used as a mobile sink node in the wireless sensor network, and a proper sensor data transmission path is selected according to the value of the sharpril, so that the energy consumption of the sensor is more uniform and reasonable, each sensor node is utilized more efficiently, the life cycle and the working efficiency of the wireless sensor network are improved, the data fusion is adopted to reduce the storage capacity of the data of the unmanned aerial vehicle, and the working time of the unmanned aerial vehicle is prolonged.

Description

Data fusion alliance game method and system for wireless sensor network
Technical Field
The invention relates to the technical field of wireless sensor network communication, in particular to a wireless sensor network-oriented data fusion alliance game method and system.
Background
A Wireless Sensor Network (WSN) is a new generation of comprehensive technology that develops rapidly, and a Sensor in the existing Wireless Sensor network usually uses a battery as an energy source, the current battery capacity is limited, and the Sensor cannot be used with high power for a long time due to remote deployment position or difficulty in charging or replacing the battery due to special tasks, and once the battery energy is exhausted, data cannot be collected; in addition, in the process of transmitting data by the wireless sensor network, due to the difference of positions, the sensors have different functions in the data transmission process, so that the energy consumption is uneven, the energy of some nodes is exhausted too early, and the wireless sensor network is influenced to play a role;
on the other hand, the data transmission radius of the sensor cannot perform long-distance data transmission due to the limitation of the communication module and the power module, and can only perform transmission within a limited distance, in the prior art, the data transmission in a base station transmission mode is adopted, and a relay node is not changed in the transmission process, so that the energy consumption of the relay node is too fast, and the life cycle of the wireless sensor network is shortened; moreover, due to remote deployment positions or special tasks, multiple fixed base stations need to be deployed, the cost is high, the fixed base stations cannot balance energy consumption among the sensors, the energy consumption of the sensor unit data transmission far away from the base stations is more than that of the sensor close to the base stations, and therefore the life cycle of the wireless sensing network is over-fast finished. Therefore, in the whole wireless sensor network, it is very important to select an appropriate transmission path and transmission distance in order to save energy consumption of the sensor.
Disclosure of Invention
In order to overcome the defects and shortcomings in the prior art, the invention provides a data fusion alliance game method and system for a wireless sensor network.
In order to achieve the purpose, the invention adopts the following technical scheme:
the invention provides a data fusion alliance game method facing a wireless sensor network, which comprises the following steps:
constructing a wireless sensor network-based alliance game model, taking a Sharpy value as a solution of alliance profit allocation, and determining a relay node according to the data transmission distance or the Sharpy value;
the method comprises the steps that an unmanned aerial vehicle is used as a sink node in a wireless sensor network to collect data, and the flight path and the flight direction of the unmanned aerial vehicle are determined;
and performing data fusion on the collected data, and removing repeated parts in the collected data.
As a preferred technical solution, the specific steps of constructing the alliance game model based on the wireless sensor network are as follows:
the specific formula for the calculation of the value of the spiri is as follows:
Figure BDA0002212503710000021
wherein the content of the first and second substances,
Figure BDA0002212503710000022
expressing the Sharpril value of the alliance game, n expressing the total number of the alliance game, k ═ S | is the scale of the alliance S, namely the number of game parties contained in S, v (S) -v (S \ i }) expresses the influence of the participation or non-participation of the game party i in the alliance on the characteristic function value of the alliance S, and reflects the contribution of the game party i to the alliance S,
Figure BDA0002212503710000023
representing gambling parties i as random partiesProbability of joining in federation S when joining;
and defining a revenue function of the alliance game, wherein the revenue function represents that the revenue of the alliance S is equal to the total revenue minus the revenue of other alliances, and specifically represents that:
Figure BDA0002212503710000031
where j represents other federations not equal to federation S;
establishing a alliance game B (N, v) by all the alternative relay nodes of the sensor, wherein N represents all members in the alliance, v represents a characteristic function of the alliance, and the characteristic function of the alliance s is specifically represented as follows:
v(S)＝num-(α*ei+β*(1-di)+γ*si)
wherein, alpha, beta and gamma represent the balance coefficient of each parameter, alpha is greater than 0, beta is greater than 0, and gamma is less than 0;
defining an energy parameter eiSpecifically, it is represented as:
Figure BDA0002212503710000032
wherein E isiResidual energy of the sensor representing the alternative relay node, EiniRepresenting the initial energy of the alternative relay node, an energy parameter eiThe larger the value of (a) is, the larger the probability that the sensor is selected as the relay node is;
defining a distance parameter diSpecifically, it is represented as:
Figure BDA0002212503710000033
wherein D isiRepresents the square, Σ D, of the distance of a sensor to a sensor as an alternative relay nodeiDenotes all DiThe smaller the value of the distance parameter, the less the energy consumption of the sensor;
defining a state parameter siSpecifically, it is represented as:
Figure BDA0002212503710000034
wherein, i represents a sensor, Relay represents a Relay node, and when the sensor i is used as the Relay node, the state parameter is added by 3; and when the sensor i does not serve as the relay node, the state parameter is reduced by 1, and the higher the value of the state parameter is, the lower the probability that the sensor is selected as the relay node is.
As a preferred technical solution, the determining of the relay node according to the data transmission distance or the value of the sharpril includes the following specific steps:
if the linear distance between the sensor node and the unmanned aerial vehicle is larger than d0And the distance between the sensor node and other sensors is less than d0Selecting the flying radius d of the unmanned aerial vehicle by adopting a multi-hop mode0The sensor in the unmanned aerial vehicle is used as a relay node, and the linear distance between the sensor and the unmanned aerial vehicle is greater than d0The node sends the collected data to the relay node, and the relay node forwards the data to the unmanned aerial vehicle;
at radius d of the unmanned plane0The external sensors select the relay nodes: if at unmanned aerial vehicle flight radius d0When the number of the sensors in the unmanned aerial vehicle is less than or equal to 2, the sensor with the closest distance is selected as a relay node, and if the number of the sensors is within the flight radius d of the unmanned aerial vehicle0When the number of the sensors in the relay node is more than or equal to 3, the selectable sensor nodes form a alliance, the Charpril value of each node is calculated, and the sensor with the largest Charpril value is selected as the relay node.
As a preferred technical scheme, the determining the flight path of the unmanned aerial vehicle specifically comprises the following steps:
clustering is carried out according to the distance between the sensors, and the near merit of each cluster is calculated;
calculating the sequence of the unmanned aerial vehicle flying to the cluster by adopting a greedy algorithm;
unmanned aerial vehicle flies outside cluster: the unmanned aerial vehicle flies from the starting point or flies to the next cluster after collecting the data of one cluster, and the unmanned aerial vehicle does not enter the next cluster at the moment and flies to the next cluster in a straight line with the near-merit;
flying in unmanned aerial vehicle cluster: and when the distance between the unmanned aerial vehicle and any node in the next cluster is smaller than the threshold value, judging that the unmanned aerial vehicle reaches the next cluster, and stopping the linear flight of the unmanned aerial vehicle.
As an optimal technical scheme, the sequence of the unmanned aerial vehicle flying to the cluster is calculated by adopting a greedy algorithm, and the method specifically comprises the following steps:
drawing a circle by taking the current position of the unmanned aerial vehicle as the circle center and the distance of flying one second as the radius, drawing a point at every 45 degrees on the circle, dividing the point into 8 direction points in total, representing E1-E8, and respectively calculating the energy consumed by all nodes in the wireless sensor network for transmitting data to the unmanned aerial vehicle when the unmanned aerial vehicle flies to the 8 direction points;
after the energy consumption of the data transmitted by the 8 direction points is obtained, the energy consumption is compared, and the direction with the minimum energy consumption for transmitting the data is selected to fly.
As a preferred technical solution, the near merit of each cluster is represented as a centroid coordinate point of all members of each cluster, and the near merit straight line of the next cluster is represented as a connecting line between a start point in one current cluster and the centroid coordinate point of all members of the next cluster.
As a preferred technical scheme, the determining of the flight direction of the unmanned aerial vehicle specifically comprises the following steps:
setting the flying distance in the set time T as the radius d0Defining a data transmission circle range, calculating total energy consumed by all sensor nodes in the wireless sensor network for transmitting data to the unmanned aerial vehicle, setting the position of the unmanned aerial vehicle at the flight time T as a current position, and setting the position of the unmanned aerial vehicle at the flight time T +1 as a next position of the unmanned aerial vehicle;
determining a relay node according to the data transmission distance or the value of the xiapril;
calculating energy consumption e of wireless sensor network at current position of unmanned aerial vehicle1Energy consumption e of wireless sensor network at next position of unmanned aerial vehicle2Comparison e1And e2Judging whether the unmanned aerial vehicle continues flying or not, and when e1＞e2Then the drone continues to e2In the direction of flight when e1＜e2The unmanned aerial vehicle stops flying and collects data of all sensors in the cluster;
calculating the distance d between the unmanned aerial vehicle and the sensor in the cluster when the current position of the unmanned aerial vehicle is calculated1And the distance d between the unmanned aerial vehicle and the sensor in the cluster when the unmanned aerial vehicle is at the next position2When d is1＜d2The sensor transmits data to the unmanned aerial vehicle; when d is1＞d2And when the sensor and the unmanned aerial vehicle stop data transmission.
The invention also provides a data fusion alliance game system facing the wireless sensor network, which comprises the following steps: the system comprises a wireless sensor network alliance game model building module, a relay node selection module, a sink node selection module, an unmanned aerial vehicle flight mode selection module and a data fusion module;
the wireless sensor network alliance game model building module is used for building an alliance game model based on the wireless sensor network and taking a Charpy value as an alliance income distribution solution;
the relay node selection module is used for determining a relay node according to the data transmission distance or the value of the sharpril;
the sink node selection module is used for taking the unmanned aerial vehicle as a sink node in the wireless sensor network and collecting data;
the unmanned aerial vehicle flight mode selection module is used for determining the flight path and the flight direction of the unmanned aerial vehicle;
the data fusion module is used for carrying out data fusion on the collected data and removing repeated partial data.
Compared with the prior art, the invention has the following advantages and beneficial effects:
(1) the sensor nodes of the invention carry out alliance game, set parameters related to the residual energy of the sensor and the like to calculate the value of the sensor data, and select a proper sensor data transmission path according to the value of the sensor data, thereby leading the energy consumption of the sensor to be more uniform and more reasonable, utilizing each sensor node more efficiently and improving the life cycle and the working efficiency of the wireless sensor network.
(2) The invention simplifies the calculation by using clustering, a greedy algorithm and circle division, determines the flight path of the unmanned aerial vehicle, reduces the energy consumption of the sensor and improves the efficiency of data collection.
(3) The invention adopts the unmanned aerial vehicle as the mobile sink node in the wireless sensor network, is flexible in deployment and not limited by regions, reduces the deployment of base stations, reduces the energy consumed by the sensors for transmitting data, and prolongs the life cycle of the wireless sensor network.
(4) The invention adopts a data fusion technology, removes the same data, reduces the repeated data amount, reduces the data storage capacity of the unmanned aerial vehicle and increases the working time of the unmanned aerial vehicle.
Drawings
Fig. 1 is a schematic flowchart of a wireless sensor network-oriented data fusion alliance gaming method in this embodiment;
fig. 2 is a schematic diagram illustrating a selection process of a relay node in the wireless sensor network-oriented data fusion alliance gaming method in this embodiment;
fig. 3 is a schematic diagram of a flow of determining that the unmanned aerial vehicle enters a cluster according to this embodiment;
fig. 4 is a schematic diagram of the circle division of the flight distance of the unmanned aerial vehicle according to the embodiment;
fig. 5 is a schematic view of a flow of determining that the unmanned aerial vehicle continues to fly according to this embodiment;
FIG. 6 is a schematic diagram illustrating a determination process for the sensor to continue transmitting data according to the present embodiment;
fig. 7 is a schematic diagram of simulation results of the league game in the embodiment;
FIG. 8 is a diagram illustrating the remaining energy distribution of each sensor in the base station transmission mode according to the embodiment;
fig. 9 is a remaining energy distribution diagram of each sensor in the league gaming mode of the embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Examples
As shown in fig. 1, in this embodiment, a data convergence alliance gaming method for a wireless sensor network is provided, which includes the following steps:
constructing a wireless sensor network-based alliance game model, taking a Charpy value as a solution of alliance profit allocation, and determining a relay node according to the Charpy value;
the unmanned aerial vehicle is used as a sink node in a wireless sensor network to collect data and determine the flight path and the flight direction of the unmanned aerial vehicle, and the unmanned aerial vehicle of the embodiment is provided with a wireless transceiver module, such as a Zigbee wireless transceiver module;
the unmanned aerial vehicle carries out preliminary data fusion on the collected data, and eliminates repeated parts in the collected data.
In the wireless sensor network of this embodiment, some nodes are too far away from the sink node, the energy consumption of directly transmitting data is large or the data cannot arrive, and the data is forwarded to other nodes and then arrives at the sink node, which is beneficial to reducing the energy consumption or overcoming obstacles in distance.
In the embodiment, a league game and a charapril value are introduced in the process of selecting the relay nodes, instead of a mode of fixing the relay nodes only by considering the distance, energy consumption balance among the alternative relay nodes is achieved, and energy consumption of a certain node is not too fast, so that the life cycle of the wireless sensor network is prolonged.
In the data transmission in the existing base station transmission mode, the energy consumption of the sensor serving as the relay node is too fast due to the fixation of the relay node, so that the life cycle of the wireless sensor network is over fast, and in the embodiment, a alliance game is introduced to change the selection of the relay node when the wireless sensor network performs data transmission, so that the energy consumption among the sensors is uniform, and the life cycle is improved;
the league game is also called a cooperative game, and in game N ═ {1,2, …, N }, league S ∈ 2NThe profit function (feature function) v (S) represents the maximum profit that can be achieved by negotiating the policy of each member in the federation S. In this embodiment, the value of happril is used as a solution for alliance profit allocation, the value of happril allocates profits according to the contribution of alliance members to alliances, and has uniqueness and fairness, and the value of happril is a rationalization analysis method and vector
Figure BDA0002212503710000081
The sharpril value for the league game is calculated as follows:
Figure BDA0002212503710000082
wherein n represents the total number of the league game, k is the scale of the league S, namely the number of game parties contained in the league S, v (S) -v (S \ i }) represents the influence of the participation or non-participation of the game party i on the feature function value of the league S and just reflects the contribution of the game party i on the league S,
Figure BDA0002212503710000083
is the probability of a gambler i participating in the league S when it joins in a random manner.
The summery value of each game party is the expected contribution of the game parties to the alliance game, and is the best index for measuring the value of each game party in the alliance game;
in the league game of the embodiment, the energy parameter e is introducediThe parameter takes into account a ratio of the residual energy of the sensor serving as the candidate relay node to the initial energy, and is specifically expressed as:
Figure BDA0002212503710000091
wherein E isiResidual energy of the sensor representing the alternative relay node, EiniRepresenting the alternative relay node initial energy.
From the expression of the energy parameter, it can be seen that the more the remaining energy of the sensor, the more the energy parameter eiThe larger the probability that the sensor is selected as a relay node; otherwise the probability decreases. The introduction of the energy parameter reduces the probability of selecting the sensor with low residual energy as the relay node to a certain extent, and increases the probability of selecting other alternative sensors, so that the residual energy difference between the sensors is reduced, and the life cycle of the wireless sensing network is prolonged.
At a radius d0The energy consumption of the sensor for transmitting data is proportional to the square of the distance, so that the shorter the transmission distance, the lower the energy consumption of the sensor, for which purpose a distance parameter d is introducedi，diIs defined as:
Figure BDA0002212503710000092
wherein D isiRepresents the square, Σ D, of the distance of a sensor to a sensor as an alternative relay nodeiDenotes all DiThe sum of (1).
The distance parameter is the ratio of the square of the distance from the sensor to the candidate relay node to the sum of all squares, and if the ratio is small, the ratio indicates that the distance is close to the sensor compared with other candidate relay nodes, so that the energy consumption of the sensor is low.
In the whole wireless sensing network, if a certain sensor is used as a relay node for too many times, the energy of the sensor is consumed by other sensors, and the residual energy is less; if the number of times that a certain sensor is used as a relay node is too small, the energy consumption of the sensor is less than that of other sensors, the residual energy is more, and in order to reflect the historical state of the sensor, a state parameter s is introducedi，siIs defined as:
Figure BDA0002212503710000093
when the sensor is used as a relay node, adding 3 to the state parameter; not as a relay node, the state parameter is decremented by 1. If the state parameter is high, the number of times that the sensor is used as the relay node is large, energy consumption is fast, residual energy is less, and in the subsequent relay node selection process, the probability that the sensor is selected as the relay node is reduced, so that the nodes with low residual energy are protected, and the life cycle of the network is prolonged.
The embodiment defines an energy parameter, a distance parameter and a state parameter to embody different advantages of the sensor. In order to select a proper relay node from the sensors with different advantages, the alternative nodes are subjected to alliance game, alliance income is calculated, and a Charpy value, namely the contribution of the sensor in the alliance, is obtained through the alliance income, so that the relay node is determined.
In order to better represent the league benefits, a mathematical model about league gaming is introduced: the bank bankruptcy model:
the set N ═ {1,2, 3 … … N } represents N creditors, each creditor requesting an amount d, d ═ d { [ d ]1,d2,……dnApplying for debt
Figure BDA0002212503710000101
In order to better distribute the amount, a revenue function v(s) of the league game is defined, which is specifically expressed as:
Figure BDA0002212503710000102
the revenue function represents the revenue of federation S equal to the total revenue minus the revenue of the other federations.
And establishing a alliance game B (N, v) by all the alternative relay nodes of the sensor, wherein N represents all members in the alliance, and v represents a characteristic function of the alliance. The feature function v (S) of the federation is:
v(S)＝num-(α*ei+β*(1-di)+γ*si)
wherein, alpha, beta and gamma represent the balance coefficient of each parameter, the larger the energy parameter is, the more the residual energy is, the larger the probability of being selected is, so alpha is greater than 0; the larger the distance parameter is, the more energy is consumed, the smaller the probability of selection is, so that beta is greater than 0; the larger the state parameter is, the more times of serving as the relay node is, the less the residual energy is, the smaller the probability of being selected is, and therefore gamma is less than 0;
the total income of each alliance can be obtained through the characteristic function v (S), and the contribution of each member in the alliance is calculated according to the value of the Charapril
Figure BDA0002212503710000103
Calculating a formula to obtain the value of the summer pril of each member in the alliance, and selecting a sensor with a large value of the summer pril, namely a sensor with a large contribution as a relay node;
in this embodiment, the unmanned aerial vehicle collects data as a sink node in the wireless sensor network, and in order to reduce energy consumption of the sensor during data transmission, the data transmission can be implemented by reducing the transmission distance, so that the unmanned aerial vehicle is required to take data collection efficiency (the shorter the time required for collecting data is, the better) and energy consumption of the sensor into account in the flight process, and therefore, the flight path selection of the unmanned aerial vehicle is very important.
Determining a flight path by the unmanned aerial vehicle:
firstly, clustering all sensors based on distance, wherein the distance between the sensors is less than d0And is determined to be reachable; greater than d0And the contact is determined to be unavailable. Dividing sensors which can be contacted with each other (including through multi-hop contact) into a same cluster, and dividing a sensor which cannot be contacted with any sensor in the cluster into another cluster;
secondly, calculating the approximate advantages of each cluster, namely the mass center coordinate points of all members of each cluster, selecting the approximate points, and reducing the total energy consumption when the sensors in the clusters transmit data to the points;
thirdly, determining the sequence of the unmanned aerial vehicle flying to the cluster by using a greedy algorithm, wherein the greedy algorithm is that the unmanned aerial vehicle flies in the current 8 directions by selecting the direction with the minimum energy consumption, so that the complexity and the calculated amount are reduced, and when the unmanned aerial vehicle determines the next cluster, the cluster which is closest to the position of the unmanned aerial vehicle at the moment is selected;
fourthly, flying outside the cluster: the unmanned aerial vehicle flies from the starting point or flies to the next cluster after collecting data of one cluster, at the moment, the unmanned aerial vehicle does not enter the next cluster, and the unmanned aerial vehicle flies to the near-advantageous straight line of the next cluster, so that the next cluster can be reached at the fastest speed, and the near-advantageous straight line of the embodiment is a connecting line of the starting point in the current cluster and the mass center coordinate points of all members in the next cluster;
fifthly, flying in the cluster, as shown in fig. 3, the distance between the unmanned aerial vehicle and any node in the next cluster is less than d0The unmanned aerial vehicle is determined to reach the next cluster, and the unmanned aerial vehicle stops flying in a straight line at the moment;
the specific steps for determining the flight direction of the unmanned aerial vehicle are as follows:
(1) in order to determine the flying direction of the next second, as shown in fig. 4, firstly, taking the current position of the unmanned aerial vehicle as the center of a circle, taking the distance of flying for one second as the radius, drawing a circle, drawing a point at intervals of 45 degrees on the circle, dividing the circle into 8 points in total, representing E1-E8, calculating the position of flying for one second, and calculating the total energy consumed by all nodes in the wireless sensor network for transmitting data to the unmanned aerial vehicle when the unmanned aerial vehicle flies to the moment;
as shown in fig. 2, in this energy calculation, if there are nodes, the distance between the nodes and the unmanned aerial vehicle is greater than d0And the distance from other sensors is less than d0Then, a multi-hop form is adopted, and the radius d of the unmanned aerial vehicle is selected0The sensor in the unmanned aerial vehicle is used as a relay node, and the linear distance between the sensor and the unmanned aerial vehicle is greater than d0The node sends the collected data to the relay node, and the relay node forwards the data to the unmanned aerial vehicle, so that the situation that the transmission distance is larger than d is avoided0And too big or too big information of transmission distance of energy consumption can not send unmanned aerial vehicle to this reduces energy consumption and improves unmanned aerial vehicle data collection efficiency. When in the radius d of the unmanned plane0When other sensors select other sensors as relay nodes, if the relay nodes are at the radius d0Is internally provided with a plurality of unmanned aerial vehicles at the radius d0The sensor has multiple options. When the number of the sensors is less than or equal to 2, selecting the sensor closest to the sensors; sensingWhen the number of the devices is more than or equal to 3, the selectable nodes form a alliance, the Charpy value of each node, namely the contribution of the sensor in the alliance, is calculated, the sensor with the largest Charpy value is selected as the relay node, and the purpose of enabling energy consumption among the relay nodes to be uniform is achieved.
After the energy consumptions of the 8 points are obtained, the energy consumptions E in the point with the minimum energy consumption and the next direction with the minimum energy consumption (the minimum direction in E1\ E2\ E3 and the like) are selected according to the comparison of the sizes2；
(2) Calculating the energy consumption e required by the wireless sensor network to transmit data at the current position of the unmanned aerial vehicle1；
(3) Compare e, as shown in FIG. 51And e2If the former is smaller than the latter, the unmanned aerial vehicle does not fly forward any more, and data of all sensors in the cluster are collected at the current position; otherwise, the direction is e2Flying in the direction, wherein E2 represents the energy consumption in the next direction with the minimum energy consumption (the minimum direction in 8 candidate directions such as E1\ E2\ E3) and the steps (1), (2) and (3) are repeated;
(4) as shown in fig. 6, if it is determined in (3) that the drone is flying, the distance between the drone and the sensor in the cluster at this moment is calculated and compared with the distance between the next drone position, and if the former is smaller than the latter, the sensor now transmits data to the drone; otherwise no data is to be transferred. After the sensor sends data to the drone, the energy consumption of this sensor will not be calculated in the following direction selection calculation. Meanwhile, the coordinates of the unmanned aerial vehicle are used as the coordinates of the next sensor for sending data when the data are sent, and when the unmanned aerial vehicle flies to the moment, the sensor sends the data to the unmanned aerial vehicle, so that the calculation amount is reduced.
After the flight path of the unmanned aerial vehicle is determined, the unmanned aerial vehicle does not change the flight path in the next flight, and flies according to the determined path all the time. When the unmanned aerial vehicle flies to the corresponding position, the sensor transmits data to the unmanned aerial vehicle. The selection of the relay node has been determined using league gaming and the value of the charpy.
The unmanned aerial vehicle adopted by the embodiment is flexibly deployed, is not limited by regions, can fly a plurality of clusters, and reduces the deployment of base stations; the wireless sensor network data transmission system can carry enough communication equipment to fly for a long time to reach a destination and receive data for a long time, replaces a fixed base station as a mobile sink node in the wireless sensor network, performs primary processing on the data, reduces the communication radius when the sensor transmits the data, can greatly reduce the energy consumed by the sensor for transmitting the data, and prolongs the life cycle of the wireless sensor network.
In this embodiment, MATLAB software simulation is adopted in the league game, and the settings of simulation related parameters are shown in table 1 below,
table 1 simulation-related parameter setting table
Number of sensors 16
Number of unmanned aerial vehicles 2
Initial energy of sensor 1 Joule
Amount of data transferred at a time 1500bit
α (energy coefficient) 500
Beta (position coefficient) 1200
Gamma (State coefficient) -0.8
In the flying process of the unmanned aerial vehicle, when the total energy consumed in the next flying direction is calculated, the sensor which has transmitted data is removed, the unmanned aerial vehicle flies to the sensor which does not transmit data, and the energy consumption of the sensor is reduced. As shown in fig. 7, the unmanned aerial vehicle flight area path is shown, the displayed unmanned aerial vehicle flight path is not a straight line, the unmanned aerial vehicle directly flies above the number 3 sensor, and the data of other sensors are collected at the moment, so that only the number 3 sensor is left, the unmanned aerial vehicle can directly fly to the number 3 sensor, the energy consumption is reduced, and after the data of the number 3 sensor is collected, the unmanned aerial vehicle flies to the next cluster.
As shown in fig. 7, 8, 9, wherein the abscissa in fig. 8 and 9 represents the sensor number and the ordinate represents the remaining energy (J); 5. no. 6 and No. 14 sensors are used as relay nodes of No. 9 sensors, and No. 1, No. 2 and No. 3 sensors are used as relay nodes of No. 4 sensors. Because the league game is adopted to select the relay node, the relay node obtains the contribution of the sensor in the league by calculating the value of the Charapril and comprehensively considering the residual energy, the distance and the historical state of the sensor, so that the relay node is selected. 1. The residual energy of the sensors 2 and 3 is 0.6616 joules, 0.7243 joules and 0.7072 joules; 5. the remaining energy of the sensors No. 6 and 14 is 0.5716 joules, 0.5168 joules and 0.4541 joules. It can be seen that the residual energy difference between the relay nodes is not large, and the residual energy is uniform. The wireless sensor network can operate 9247 times in the common mode, and the alliance game mode can operate 10398 times, so that the service life is improved by 12.45%, and the life cycle of the wireless sensor network is prolonged.
In this embodiment, a data fusion step is further included, and the wireless sensor network of this embodiment adopts a combination of sensors of the same type, so that the data formats, information contents, and the like of the data collected by the sensors in the network do not have large differences, and are consistent. The sensor in the wireless sensor network randomly generates 150 integers in the interval [ 01000 ], can be described as any interested single physical state measurement data, sends the data to the unmanned aerial vehicle, the unmanned aerial vehicle performs preliminary data fusion on the collected data, the repeated part in the collected data is removed, the storage capacity of the data of the unmanned aerial vehicle is reduced, the storage space of the residual data is increased, so that more rounds of collection are facilitated, and the workload of researchers is reduced.
The simulation result shows that the unmanned aerial vehicle uses simple data fusion, can reduce the memory space of self data, increases unmanned aerial vehicle's operating duration.
In the wireless sensor network, each transmission node needs to search for a proper receiving node to send data, nodes with a common transmission target form an alliance, and the process of maximizing the benefits of a plurality of alliances is an alliance game. In the process of data transmission, a transmission path is determined by calculating a Charpy value, so that energy consumption of the sensor is uniform, and the aim of data fusion is to remove the same data to reduce data transmission amount or data storage amount.
The embodiment also provides a data fusion alliance gaming system facing the wireless sensor network, which includes: the system comprises a wireless sensor network alliance game model building module, a relay node selection module, a sink node selection module, an unmanned aerial vehicle flight mode selection module and a data fusion module;
the wireless sensor network alliance game model building module is used for building an alliance game model based on the wireless sensor network and taking a Charpy value as a solution of alliance income distribution; the relay node selection module is used for determining a relay node according to the data transmission distance or the value of the sharpril; the sink node selection module is used for taking the unmanned aerial vehicle as a sink node in the wireless sensor network and collecting data; the unmanned aerial vehicle flight mode selection module is used for determining the flight path and the flight direction of the unmanned aerial vehicle; the data fusion module is used for carrying out data fusion on the collected data and removing repeated partial data.
The sensor nodes of the embodiment are in alliance game, parameters related to sensor residual energy and the like are set to calculate a xiapril value, and a proper sensor data transmission path is selected according to the xiapril value, so that the energy consumption of the sensor is more uniform and reasonable, the sensor nodes are more efficiently utilized, and the life cycle and the working efficiency of the wireless sensor network are improved.
The above embodiments are preferred embodiments of the present invention, but the present invention is not limited to the above embodiments, and any other changes, modifications, substitutions, combinations, and simplifications which do not depart from the spirit and principle of the present invention should be construed as equivalents thereof, and all such changes, modifications, substitutions, combinations, and simplifications are intended to be included in the scope of the present invention.

Claims (7)

1. A data fusion alliance game method oriented to a wireless sensor network is characterized by comprising the following steps:
constructing a wireless sensor network-based alliance game model, taking a Sharpy value as a solution of alliance profit allocation, and determining a relay node according to the data transmission distance or the Sharpy value;
the specific steps for constructing the alliance game model based on the wireless sensor network are as follows:
the specific formula for the calculation of the value of the spiri is as follows:
Figure FDA0002951665040000011
wherein the content of the first and second substances,
Figure FDA0002951665040000012
expressing the Sharpril value of the alliance game, n expressing the total number of the alliance game, k ═ S | is the scale of the alliance S, namely the number of game parties contained in S, v (S) -v (S \ i }) expresses the influence of the participation or non-participation of the game party i in the alliance on the characteristic function value of the alliance S, and reflects the contribution of the game party i to the alliance S,
Figure FDA0002951665040000013
representing the probability of participating in the alliance S when the gambling party i alliances in a random manner;
and defining a revenue function of the alliance game, wherein the revenue function represents that the revenue of the alliance S is equal to the total revenue minus the revenue of other alliances, and specifically represents that:
Figure FDA0002951665040000014
where j represents other federations not equal to federation S;
establishing a alliance game B (N, v) by all the alternative relay nodes of the sensor, wherein N represents all members in the alliance, v represents a characteristic function of the alliance, and the characteristic function of the alliance s is specifically represented as follows:
v(S)＝num-(α*ei+β*(1-di)+γ*si)
wherein alpha, beta and gamma represent the balance coefficient of each parameter, alpha is more than 0, beta is more than 0, and gamma is less than 0;
defining an energy parameter eiSpecifically, it is represented as:
Figure FDA0002951665040000015
wherein E isiResidual energy of the sensor representing the alternative relay node, EiniRepresenting the initial energy of the alternative relay node, an energy parameter eiThe larger the value of (a) is, the larger the probability that the sensor is selected as the relay node is;
defining a distance parameter diSpecifically, it is represented as:
Figure FDA0002951665040000021
wherein D isiRepresents the square, Σ D, of the distance of a sensor to a sensor as an alternative relay nodeiDenotes all DiThe smaller the value of the distance parameter, the less the energy consumption of the sensor;
defining a state parameter siSpecifically, it is represented as:
Figure FDA0002951665040000022
wherein, i represents a sensor, Relay represents a Relay node, and when the sensor i is used as the Relay node, the state parameter is added by 3; when the sensor i is not used as a relay node, the state parameter is reduced by 1, and the higher the value of the state parameter is, the lower the probability that the sensor is selected as the relay node is;
the method comprises the steps that an unmanned aerial vehicle is used as a sink node in a wireless sensor network to collect data, and the flight path and the flight direction of the unmanned aerial vehicle are determined;
and performing data fusion on the collected data, and removing repeated parts in the collected data.
2. The wireless sensor network-oriented data fusion alliance gaming method as claimed in claim 1, wherein the relay node is determined according to the data transmission distance or the xiapril value, and the specific steps are as follows:
if the linear distance between the sensor node and the unmanned aerial vehicle is larger than d0And the distance between the sensor node and other sensors is less than d0Selecting the flying radius d of the unmanned aerial vehicle by adopting a multi-hop mode0The sensor in the unmanned aerial vehicle is used as a relay node, and the linear distance between the sensor and the unmanned aerial vehicle is greater than d0The node sends the collected data to the relay node, and the relay node forwards the data to the unmanned aerial vehicle;
at radius d of the unmanned plane0The external sensors select the relay nodes: if at unmanned aerial vehicle flight radius d0When the number of the sensors in the unmanned aerial vehicle is less than or equal to 2, the sensor with the closest distance is selected as a relay node, and if the number of the sensors is within the flight radius d of the unmanned aerial vehicle0When the number of the sensors in the relay node is more than or equal to 3, the selectable sensor nodes form a alliance, the Charpril value of each node is calculated, and the sensor with the largest Charpril value is selected as the relay node.
3. The wireless sensor network-oriented data fusion alliance gaming method as claimed in claim 1, wherein the determining of the flight path of the unmanned aerial vehicle comprises the following specific steps:
clustering is carried out according to the distance between the sensors, and the near merit of each cluster is calculated;
calculating the sequence of the unmanned aerial vehicle flying to the cluster by adopting a greedy algorithm;
unmanned aerial vehicle flies outside cluster: the unmanned aerial vehicle flies from the starting point or flies to the next cluster after collecting the data of one cluster, and the unmanned aerial vehicle does not enter the next cluster at the moment and flies to the next cluster in a straight line with the near-merit;
flying in unmanned aerial vehicle cluster: and when the distance between the unmanned aerial vehicle and any node in the next cluster is smaller than the threshold value, judging that the unmanned aerial vehicle reaches the next cluster, and stopping the linear flight of the unmanned aerial vehicle.
4. The wireless sensor network-oriented data fusion alliance gaming method as claimed in claim 3, wherein the sequence of the unmanned aerial vehicle flying to the cluster is calculated by adopting a greedy algorithm, and the specific steps are as follows:
drawing a circle by taking the current position of the unmanned aerial vehicle as the circle center and the distance of flying one second as the radius, drawing a point at every 45 degrees on the circle, dividing the point into 8 direction points in total, representing F1-E8, and respectively calculating the energy consumed by all nodes in the wireless sensor network for transmitting data to the unmanned aerial vehicle when the unmanned aerial vehicle flies to the 8 direction points;
after the energy consumption of the data transmitted by the 8 direction points is obtained, the energy consumption is compared, and the direction with the minimum energy consumption for transmitting the data is selected to fly.
5. The wireless sensor network-oriented data fusion alliance gaming method as claimed in claim 3 or 4, wherein the near-merit of each cluster is represented as a centroid coordinate point of all members of each cluster, and the near-merit straight line of the next cluster is represented as a connecting line of a starting point in a current cluster and the centroid coordinate point of all members of the next cluster.
6. The wireless sensor network-oriented data fusion alliance gaming method as claimed in claim 1, wherein the determining of the flight direction of the unmanned aerial vehicle comprises the following specific steps:
setting the flying distance in the set time T as the radius d0Defining a data transmission circle range, calculating total energy consumed by all sensor nodes in the wireless sensor network for transmitting data to the unmanned aerial vehicle, setting the position of the unmanned aerial vehicle at the flight time T as a current position, and setting the position of the unmanned aerial vehicle at the flight time T +1 as a next position of the unmanned aerial vehicle;
calculating energy consumption e of wireless sensor network at current position of unmanned aerial vehicle1Energy consumption e of wireless sensor network at next position of unmanned aerial vehicle2Comparison e1And e2Judging whether the unmanned aerial vehicle continues flying or not, and when e1＞e2Then the drone continues to e2In the direction of flight when e1＜e2The unmanned aerial vehicle stops flying and collects data of all sensors in the cluster;
calculating the distance d between the unmanned aerial vehicle and the sensor in the cluster when the current position of the unmanned aerial vehicle is calculated1And the distance d between the unmanned aerial vehicle and the sensor in the cluster when the unmanned aerial vehicle is at the next position2When d is1＜d2The sensor transmits data to the unmanned aerial vehicle; when d is1＞d2And when the sensor and the unmanned aerial vehicle stop data transmission.
7. A data fusion alliance game system oriented to a wireless sensor network is characterized by comprising: the system comprises a wireless sensor network alliance game model building module, a relay node selection module, a sink node selection module, an unmanned aerial vehicle flight mode selection module and a data fusion module;
the wireless sensor network alliance game model building module is used for building an alliance game model based on the wireless sensor network and taking a Charpy value as an alliance income distribution solution;
the specific steps for constructing the alliance game model based on the wireless sensor network are as follows:
the specific formula for the calculation of the value of the spiri is as follows:
Figure FDA0002951665040000041
wherein the content of the first and second substances,
Figure FDA0002951665040000042
expressing the Sharpril value of the alliance game, n expressing the total number of the alliance game, k ═ S | is the scale of the alliance S, namely the number of game parties contained in S, v (S) -v (S \ i }) expresses the influence of the participation or non-participation of the game party i in the alliance on the characteristic function value of the alliance S, and reflects the contribution of the game party i to the alliance S,
Figure FDA0002951665040000043
representing the probability of participating in the alliance S when the gambling party i alliances in a random manner;
and defining a revenue function of the alliance game, wherein the revenue function represents that the revenue of the alliance S is equal to the total revenue minus the revenue of other alliances, and specifically represents that:
Figure FDA0002951665040000051
where j represents other federations not equal to federation S;
establishing a alliance game B (N, v) by all the alternative relay nodes of the sensor, wherein N represents all members in the alliance, v represents a characteristic function of the alliance, and the characteristic function of the alliance s is specifically represented as follows:
v(S)＝num-(α*ei+β*(1-di)+γ*si)
wherein alpha, beta and gamma represent the balance coefficient of each parameter, alpha is more than 0, beta is more than 0, and gamma is less than 0;
defining an energy parameter eiSpecifically, it is represented as:
Figure FDA0002951665040000052
wherein E isiResidual energy of the sensor representing the alternative relay node, EiniRepresenting the initial energy of the alternative relay node, an energy parameter eiThe larger the value of (a) is, the larger the probability that the sensor is selected as the relay node is;
defining a distance parameter diSpecifically, it is represented as:
Figure FDA0002951665040000053
wherein D isiRepresents the square, Σ D, of the distance of a sensor to a sensor as an alternative relay nodeiDenotes all DiThe smaller the value of the distance parameter, the less the energy consumption of the sensor;
defining a state parameter siSpecifically, it is represented as:
Figure FDA0002951665040000054
wherein, i represents a sensor, Relay represents a Relay node, and when the sensor i is used as the Relay node, the state parameter is added by 3; when the sensor i is not used as a relay node, the state parameter is reduced by 1, and the higher the value of the state parameter is, the lower the probability that the sensor is selected as the relay node is;
the relay node selection module is used for determining a relay node according to the data transmission distance or the value of the sharpril;
the sink node selection module is used for taking the unmanned aerial vehicle as a sink node in the wireless sensor network and collecting data;
the unmanned aerial vehicle flight mode selection module is used for determining the flight path and the flight direction of the unmanned aerial vehicle;
the data fusion module is used for carrying out data fusion on the collected data and removing repeated partial data.
CN201910903311.1A 2019-09-24 2019-09-24 Data fusion alliance game method and system for wireless sensor network Active CN110493844B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910903311.1A CN110493844B (en) 2019-09-24 2019-09-24 Data fusion alliance game method and system for wireless sensor network

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910903311.1A CN110493844B (en) 2019-09-24 2019-09-24 Data fusion alliance game method and system for wireless sensor network

Publications (2)

Publication Number Publication Date
CN110493844A CN110493844A (en) 2019-11-22
CN110493844B true CN110493844B (en) 2021-05-11

Family

ID=68559123

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910903311.1A Active CN110493844B (en) 2019-09-24 2019-09-24 Data fusion alliance game method and system for wireless sensor network

Country Status (1)

Country Link
CN (1) CN110493844B (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111343180B (en) * 2020-02-25 2022-03-22 广州大学 Multi-type malicious program attack and defense method based on nonlinear chargeable sensor network model
CN112584455A (en) * 2020-12-08 2021-03-30 广州技象科技有限公司 Data transmission method, device and system for switching relay nodes and storage medium
CN113240066B (en) * 2021-05-14 2023-01-13 中国民航大学 Unmanned aerial vehicle conflict resolution method based on Shapley value and used for improving ant colony algorithm
CN114485699B (en) * 2021-12-28 2024-03-19 山东师范大学 Self-adaptive path optimization method and system for unmanned aerial vehicle self-organizing network

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105636143A (en) * 2015-12-29 2016-06-01 河海大学 Wireless sensor network clustering collaborative routing algorithm based on cooperative game
CN108601058A (en) * 2018-04-16 2018-09-28 南京邮电大学 A kind of multiobjective decision network access selection method based on game theory

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7529222B2 (en) * 2005-07-01 2009-05-05 Nec Laboratories America, Inc. Method and apparatus for medium access control for a decentralized network with adapted beamforming and power control
CN102572997B (en) * 2012-03-03 2014-07-23 南昌航空大学 Development method of Sink nodes of mobile wireless sensor network (WSN)
CN103781147B (en) * 2014-02-25 2017-11-03 哈尔滨工业大学 A kind of communication means of the Wireless Sensor Network Routing Protocol based on fan-shaped sub-clustering
CN104640141B (en) * 2015-01-30 2018-05-18 南京邮电大学 A kind of motivational techniques of more relay node cooperative games
CN106211256B (en) * 2016-07-08 2019-10-01 西北大学 A kind of Unmanned Aerial Vehicle Data collection method based on data critical node

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105636143A (en) * 2015-12-29 2016-06-01 河海大学 Wireless sensor network clustering collaborative routing algorithm based on cooperative game
CN108601058A (en) * 2018-04-16 2018-09-28 南京邮电大学 A kind of multiobjective decision network access selection method based on game theory

Also Published As

Publication number Publication date
CN110493844A (en) 2019-11-22

Similar Documents

Publication Publication Date Title
CN110493844B (en) Data fusion alliance game method and system for wireless sensor network
Ng et al. Joint auction-coalition formation framework for communication-efficient federated learning in UAV-enabled internet of vehicles
Hu et al. Cooperative internet of UAVs: Distributed trajectory design by multi-agent deep reinforcement learning
Wang et al. Minimizing data collection time with collaborative UAVs in wireless sensor networks
Saad et al. A selfish approach to coalition formation among unmanned air vehicles in wireless networks
CN104394236B (en) Node combines the distributed collaborative caching method perceived with message status
CN109309620B (en) Lightweight heterogeneous network clustering method facing edge calculation
CN105636143A (en) Wireless sensor network clustering collaborative routing algorithm based on cooperative game
Liu et al. Wireless distributed learning: A new hybrid split and federated learning approach
CN111641973A (en) Load balancing method based on fog node cooperation in fog computing network
CN104093188A (en) Novel cluster head election method for wireless sensor networks
CN114415735B (en) Dynamic environment-oriented multi-unmanned aerial vehicle distributed intelligent task allocation method
CN104168661A (en) Transmission scheduling method for network lifetime maximization that satisfies fairness condition
CN115175217A (en) Resource allocation and task unloading optimization method based on multiple intelligent agents
CN105050095A (en) Topology construction method for heterogeneous wireless sensor networks based on energy prediction
Cha et al. Fuzzy logic based client selection for federated learning in vehicular networks
Yan et al. Data offloading enabled by heterogeneous UAVs for IoT applications under uncertain environments
CN107864092A (en) A kind of cloud content distribution method, device based on multicasting technology
CN109272167B (en) Green energy cooperation method based on UUDN and Q neural network
CN110418390B (en) Data transmission optimization method and system for low-altitude remote sensing and ground sensing
Mestoukirdi et al. UAV-aided multi-community federated learning
Geng et al. A truthful mechanism for mobility management in unmanned aerial vehicles networks
CN115186878A (en) Multi-AGV online task allocation method and system
Haider et al. AI-Based Energy-Efficient UAV-Assisted IoT Data Collection with Integrated Trajectory and Resource Optimization
Basagni et al. Enabling the mobile IoT: Wake-up unmanned aerial systems for long-lived data collection

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