Multi-unmanned aerial vehicle cooperative scheduling and task planning method for user privacy protection

Abstract

The embodiment of the invention provides a multi-unmanned aerial vehicle cooperative scheduling and task planning method for user privacy protection, and the method comprises the steps: defining a corresponding scene, fuzzifying the position information of a ground user in the scene, reporting the fuzzified position information to an unmanned aerial vehicle system, enabling the ground user to adjust the accuracy of the reported position information according to the privacy protection intensity of the ground user, and carrying out the task planning. The unmanned aerial vehicle system estimates the weight of the ground area based on the position information reported by the ground user, and performs multi-unmanned aerial vehicle cooperative scheduling and task planning; defining the total utility of the unmanned aerial vehicle and the total utility of the ground user based on the scene; constructing optimization targets of the unmanned aerial vehicle system and the ground user on the basis, regarding the unmanned aerial vehicle system and the ground user as mutually opposite subjects, optimizing the optimization targets of the unmanned aerial vehicle system and the ground user, and constructing a game model corresponding to the scene; and solving the game model by adopting a Nash equilibrium algorithm or a double auction algorithm. In this way, collaborative scheduling and task planning can be realized on the premise of protecting user privacy.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicles, and particularly to a multi-unmanned aerial vehicle collaborative scheduling and task planning method for user privacy protection. Background Art

[0002] With the rapid development of unmanned aerial vehicle technology, multi-unmanned aerial vehicle systems have been widely applied in fields such as logistics distribution, environmental monitoring, disaster relief, and intelligent transportation. Compared with single unmanned aerial vehicle systems, multi-unmanned aerial vehicle systems can improve task efficiency and system flexibility through collaborative work. However, multi-unmanned aerial vehicle systems face various complex problems in actual deployment. Especially in dynamic networks and uncertain environments, the research on collaborative scheduling and task planning is of great significance.

[0003] Currently, in multi-unmanned aerial vehicle systems, the collaborative scheduling and task planning of unmanned aerial vehicles need to comprehensively consider multiple factors, including the flight energy consumption, service utility, and regional demand of unmanned aerial vehicles. However, the privacy protection requirements of ground users introduce additional restrictive conditions, requiring unmanned aerial vehicles to not only meet the service quality but also ensure the security of user privacy data during task planning. Up to now, the research on this problem is still in its infancy, and further exploration of efficient collaborative scheduling and task planning methods is still needed to meet the actual application requirements of multi-unmanned aerial vehicle systems in complex environments. Summary of the Invention

[0004] In a first aspect, an embodiment of the present invention provides a multi-unmanned aerial vehicle collaborative scheduling and task planning method for user privacy protection. The method includes:

[0005] Define a multi-unmanned aerial vehicle collaborative scheduling and task planning scenario for user privacy protection; in the scenario, it includes an unmanned aerial vehicle system composed of multiple unmanned aerial vehicles, multiple ground users, ground areas accessible to multiple ground users and unmanned aerial vehicles. The location information of ground users is reported to the unmanned aerial vehicle system after being blurred by adding Gaussian noise. Ground users adjust the accuracy of the reported location information according to their own privacy protection intensity. The unmanned aerial vehicle system estimates the weights of ground areas based on the location information reported by ground users, and performs multi-unmanned aerial vehicle collaborative scheduling and task planning;

[0006] Define the total utility of unmanned aerial vehicles and the total utility of ground users based on the scenario; among them, the total utility of unmanned aerial vehicles consists of service utility and flight cost, and the total utility of ground users consists of privacy protection utility and service quality utility;

[0007] Construct an optimization objective for the unmanned aerial vehicle system based on the total utility of unmanned aerial vehicles, construct an optimization objective for ground users based on the total utility of ground users, regard the unmanned aerial vehicle system and ground users as mutually opposing entities, and each optimize its own optimization objective to construct a game model corresponding to the scenario;

[0008] The game model is solved using the Nash equilibrium algorithm or the double auction algorithm.

[0009] In some realizable ways of the first aspect, in the said scenario, there are in total UAVs, ground users, ground users and the reachable area of the UAVs;

[0010] Set of UAVs Set of ground users Set of ground areas

[0011] Discrete time instants \(t = 1, 2, \ldots, T\), where \(T\) is the number of time instants;

[0012] The position of UAV \(i\) at time instant \(t\) where, are respectively the \(x\)-axis coordinate, \(y\)-axis coordinate, and \(z\)-axis coordinate of UAV \(i\) at time instant \(t\);

[0013] The actual position of each ground user \(j\) at time instant \(t\) where, are respectively the \(x\)-axis coordinate and \(y\)-axis coordinate of ground user \(j\) at time instant \(t\), and ground user \(j\) reports to the UAV system its position information after blurring by adding Gaussian noise which satisfies a Gaussian distribution with as the mean and as the variance, denoted as: is the decision variable used by ground user \(j\) at time instant \(t\) to adjust the privacy protection intensity;

[0014] Each ground area has a fixed center point \(l\) k =(x k ,y k ), where \(x k ,y k are respectively the \(x\)-axis coordinate and \(y\)-axis coordinate of the center point \(l k . To describe the actual position distribution of ground users, the following prior assumption is made: If ground user \(j\) belongs to ground area \(k\) at time instant \(t\), then its actual position follows a Gaussian distribution and has where, is the degree of fuzziness quantifying the positions of ground users within ground area \(k\);

[0015] For each ground area \(k\), at time instant \(t\), it has a weight value The UAV system needs to estimate the weight value of the ground area based on the location information reported by ground users. First, at time t, the contribution of ground user j to the weight of ground area k Sum up the contributions of all ground users to the weight of ground area k to obtain the total weight of ground area k at time t

[0016] In some realizable ways of the first aspect, at time t, the total utility of UAV i Consists of service utility And flight cost Composed of:

[0017]

[0018] At time t, the total utility of ground user j Consists of privacy protection utility And quality of service utility Composed of:

[0019]

[0020] In some realizable ways of the first aspect, the derivation process of the service utility of UAV i Is as follows:

[0021] Define the matching variable Indicates whether UAV i is assigned to ground area k at time t:

[0022]

[0023] Ideally, without considering the actual service demand of the ground area, the service utility of the UAV for the ground area is constant, that is, for each additional UAV added to the same ground area k, the service utility it provides is independent of other UAVs already in ground area k. Thus, define the service utility of UAV i for ground area k at time t as

[0024]

[0025] Where ∈ is a positive real constant to avoid division by zero error;

[0026] In actual situations, the service demand of the ground area has an upper limit. When the demand is met, the service utility provided by the UAV will decrease. It is necessary to model the service utility attenuation effect caused by the unfairness of resource allocation. First, define the number of UAVs assigned to ground area k at time t as

[0027] Calculate the location quotient of ground area k

[0028]

[0029] If it indicates that the allocated resources in the ground area k exceed its demand, and the service utility of the UAV shows a decreasing trend. Therefore, the service utility of UAV i in the ground area k is:

[0030]

[0031] The flight cost of UAV i is expanded as:

[0032]

[0033] where η i is a conversion parameter related to the flight power of UAV i, is the flight speed of UAV i at time t, and ν is the flight power exponent.

[0034] In some realizable ways of the first aspect, the privacy protection utility of the ground user j is expanded as:

[0035]

[0036] The quality of service utility of the ground user j is expanded as:

[0037]

[0038] where β is the maximum value of the quality of service utility, indicating the maximum quality of service utility that the ground user can obtain, γ is the sensitivity coefficient, used to control the steepness of the quality of service utility function, and θ is the median point of the quality of service utility function. When the value of the quality of service utility function is half of the maximum quality of service utility, that is

[0039] In some realizable ways of the first aspect, at time t, the optimization goal of the UAV system is:

[0040]

[0041] At time t, the optimization goal of the ground user is:

[0042]

[0043] where is the minimum value of the decision variable used by the ground user j to adjust the privacy protection intensity, The maximum value of the decision variable used by ground user j to adjust the privacy protection strength.

[0044] In some implementable ways of the first aspect, the Nash equilibrium algorithm is used to solve the game model, including:

[0045] For each drone i, calculate the total utility of all feasible allocations of the drones, and select the task allocation strategy that can maximize the total utility of the drones;

[0046] For each ground user j, optimize within the constraints Solve through the gradient descent algorithm of the optimal value to maximize the total utility of the ground users;

[0047] Calculate the change in the total utility of the current strategy combination. If the change value is less than the preset convergence threshold or the number of iterations is greater than the preset iteration number threshold, then stop.

[0048] In some implementable ways of the first aspect, the double auction algorithm is used to solve the game model, including:

[0049] Each drone i calculates the initial bid B i,k (t) for all ground areas k:

[0050]

[0051] Each ground user j calculates the initial willingness to pay A j (t) based on the privacy protection strength and quality of service:

[0052]

[0053] Each drone i updates its bid B i,k (t) for all ground areas k to reflect its service utility and flight cost. The higher the bid, the more competitive the service provided by the drone in that ground area;

[0054] Each ground user j updates the willingness to pay A i,k (t) based on the bid B j (t) of drone i and its own privacy protection strength. If A j (t) is higher than the bid of a certain drone, then the ground user is willing to pay for the service; otherwise, the ground user adjusts the privacy protection strength to change the willingness to pay;

[0055] For each ground area k, collect the bids B i,k (t) of each drone i and the willingness to pay A j (t) of each ground user j, and calculate the allocation strategy that maximizes the total utility of the drones

[0056] Calculate the total utility change of the current strategy combination. If the change value is less than the preset convergence threshold or the number of iterations is greater than the preset iteration number threshold, stop.

[0057] In a second aspect, an embodiment of the present invention provides a multi-UAV collaborative scheduling and task planning device for user privacy protection, and the device includes:

[0058] A definition module, configured to define a multi-UAV collaborative scheduling and task planning scenario for user privacy protection; in the scenario, it includes a UAV system composed of multiple UAVs, multiple ground users, a ground area reachable by multiple ground users and UAVs, the location information of the ground users is reported to the UAV system after being blurred by adding Gaussian noise, the ground users adjust the accuracy of the reported location information according to their own privacy protection intensity, and the UAV system estimates the weights of the ground area based on the location information reported by the ground users, and performs multi-UAV collaborative scheduling and task planning;

[0059] The definition module is further configured to define the total utility of the UAVs and the total utility of the ground users based on the scenario; wherein, the total utility of the UAVs consists of service utility and flight cost, and the total utility of the ground users consists of privacy protection utility and quality of service utility;

[0060] A construction module, configured to construct an optimization target for the UAV system based on the total utility of the UAVs, construct an optimization target for the ground users based on the total utility of the ground users, regard the UAV system and the ground users as mutually opposing entities, and each optimize its own optimization target to construct a game model corresponding to the scenario;

[0061] A solution module, configured to solve the game model by using the Nash equilibrium algorithm or the double auction algorithm.

[0062] In a third aspect, an embodiment of the present invention provides an electronic device, and the electronic device includes: at least one processor; and a memory communicatively connected to at least one processor; the memory stores instructions executable by at least one processor, and the instructions are executed by at least one processor to enable at least one processor to execute the method as described above.

[0063] In a fourth aspect, an embodiment of the present invention provides a non-transitory computer-readable storage medium storing computer instructions, and the computer instructions are used to cause a computer to execute the method as described above.

[0064] Compared with the prior art, the present invention has at least the following technical effects:

[0065] Based on the theoretical framework of game theory, the present invention innovatively constructs a non - cooperative game model between an unmanned aerial vehicle (UAV) system and ground users. In this model, the UAV system and ground users are respectively modeled as game players with opposing interest demands: the UAV system aims to maximize service utility and minimize flight costs, while ground users make decisions based on maximizing service quality utility and privacy protection utility. To solve this game model, the present invention proposes using the Nash equilibrium algorithm or the double - auction algorithm to calculate the equilibrium solution, achieving the interest balance of both game parties. This method not only effectively resolves the contradiction between ground user privacy protection and service quality requirements but also realizes the collaborative scheduling and task optimization of multiple UAV systems, significantly improving the task execution efficiency and the overall performance of the system, providing reliable theoretical support and technical guarantee for the practical application of UAV systems in complex environments.

[0066] It should be understood that the content described in the "Summary of the Invention" section is not intended to limit the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understandable through the following description. Brief Description of the Drawings

[0067] In combination with the accompanying drawings and with reference to the following detailed description, the above - mentioned and other features, advantages, and aspects of the embodiments of the present invention will become more obvious. The drawings are used to better understand the present invention and do not constitute a limitation to the present invention. In the drawings, the same or similar reference numerals represent the same or similar elements, where:

[0068] Figure 1 is a flowchart of a multi - UAV collaborative scheduling and task planning method for user privacy protection provided by an embodiment of the present invention;

[0069] Figure 2 is a structural diagram of a multi - UAV collaborative scheduling and task planning device for user privacy protection provided by an embodiment of the present invention;

[0070] Figure 3 is a structural diagram of an exemplary electronic device capable of implementing the embodiments of the present invention. Detailed Description of the Embodiments

[0071] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0072] In addition, the term "and / or" in the present invention only describes the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in the present invention generally represents an "or" relationship between the front and back associated objects.

[0073] To solve the technical problems in the background art, the embodiments of the present invention provide a multi-UAV collaborative scheduling and task planning method, device, equipment, and storage medium for user privacy protection. The following will combine the accompanying drawings to describe in detail a multi-UAV collaborative scheduling and task planning method, device, equipment, and storage medium for user privacy protection provided by the embodiments of the present invention through specific embodiments.

[0074] Figure 1 The flowchart of a multi-UAV collaborative scheduling and task planning method for user privacy protection provided by the embodiments of the present invention is shown as Figure 1 shown. The multi-UAV collaborative scheduling and task planning method 100 may include:

[0075] S110, defining a multi-UAV collaborative scheduling and task planning scenario for user privacy protection.

[0076] In the scenario, it includes a UAV system composed of multiple UAVs, multiple ground users, and a ground area accessible to multiple ground users and UAVs. The location information of the ground users is reported to the UAV system after being blurred by adding Gaussian noise. The ground users adjust the accuracy of the reported location information according to their own privacy protection intensity. The UAV system estimates the weights of the ground area based on the location information reported by the ground users and performs multi-UAV collaborative scheduling and task planning.

[0077] S120, defining the total UAV utility and the total ground user utility based on the scenario.

[0078] Among them, the total UAV utility consists of service utility and flight cost, and the total ground user utility consists of privacy protection utility and service quality utility.

[0079] S130, constructing an optimization objective for the UAV system based on the total UAV utility, constructing an optimization objective for the ground users based on the total ground user utility, regarding the UAV system and the ground users as opposing entities, each optimizing its own optimization objective, and constructing a game model corresponding to the scenario.

[0080] S140, solving the game model using the Nash equilibrium algorithm or the double auction algorithm.

[0081] For the convenience of further understanding, the above steps will be described in detail below in combination with specific embodiments:

[0082] (1) Scenario definition

[0083] There are a total of UAVs, ground users, and the reachable areas of ground users and UAVs.

[0084] Set of UAVs Set of ground users Set of ground areas

[0085] Discrete time instants (also known as discrete time steps) \(t = 1, 2, \ldots, T\), where \(T\) is the number of time instants.

[0086] The position of UAV \(i\) at time instant \(t\) where are the \(x\)-axis coordinate, \(y\)-axis coordinate, and \(z\)-axis coordinate of UAV \(i\) at time instant \(t\), respectively.

[0087] The actual position of each ground user \(j\) at time instant \(t\) where are the \(x\)-axis coordinate and \(y\)-axis coordinate of ground user \(j\) at time instant \(t\). To achieve privacy protection, ground user \(j\) does not provide the exact position to the UAV system, but reports the position information after it is blurred by adding Gaussian noise to the UAV system which satisfies a Gaussian distribution with as the mean and as the variance, denoted as: where is the decision variable for ground user \(j\) to adjust the privacy protection strength at time instant \(t\).

[0088] Each ground area has a fixed center point \(l\) k =(x k ,y k ), where \(x\) k ,y k are the \(x\)-axis coordinate and \(y\)-axis coordinate of the center point \(l\) k respectively. To describe the actual position distribution of ground users, the following prior assumption is made: If ground user \(j\) belongs to ground area \(k\) at time instant \(t\), then its actual position follows a Gaussian distribution, and there is where is the degree of blurring of the positions of ground users within ground area \(k\).

[0089] For each ground area \(k\), at time instant \(t\), it has a weight value The UAV system needs to estimate the weight value of the ground area based on the location information reported by ground users. First, at time t, the contribution of ground user j to the weight of ground area k is:

[0090]

[0091] By summing up the contributions of all ground users to the weight of ground area k, the total weight of ground area k at time t is obtained

[0092]

[0093] (2) Definitions of the total utility of UAVs and the total utility of ground users

[0094] (2.1) Total utility of UAVs

[0095] At time t, the total utility of UAV i to ground area k consists of the service utility and the flight cost :

[0096]

[0097] (2.1.1) Service utility

[0098] Define the selection variable to indicate whether UAV i is assigned to ground area k at time t:

[0099]

[0100] Here, it is restricted that each UAV can be assigned to at most one ground area at a certain moment.

[0101] Ideally, without considering the actual service demand of the ground area (positively correlated with the weight of the ground area), the service utility of the UAV to the ground area is constant. That is, for each additional UAV added to the same ground area k, the service utility it provides is independent of other UAVs already in ground area k. It can be defined that the service utility of UAV i to ground area k at time t in the ideal case is

[0102]

[0103] where ∈ is a positive real constant to avoid division by zero errors.

[0104] In actual situations, there is an upper limit to the demand for services in the ground area. When the demand is satisfied, the service utility provided by the UAVs will decline, and it is necessary to model the service utility attenuation effect caused by the unfairness of resource allocation. First, define that at time t, the number of UAVs allocated to ground area k is

[0105]

[0106] Here, the concept of Location Quotient is introduced, which measures the relationship between the resource allocation situation in a certain ground area and its actual demand. Its calculation formula is: That is to say, the Location Quotient of ground area k can be calculated as follows:

[0107]

[0108] If it indicates that the allocated resources in ground area k exceed its demand, and the service utility of the UAVs shows a decreasing trend. Therefore, the service utility of UAV i in ground area k is:

[0109]

[0110] (2.1.2) Flight cost

[0111] The flight cost of UAV i expands to:

[0112]

[0113] Among them, the flight cost is the virtual flight energy consumption required for UAV i to fly at a fixed altitude from its current position to above the center point of the area k it is allocated to at the current speed . η i is a conversion parameter related to the flight power of UAV i, reflecting the characteristics of the UAV (such as weight, air resistance, etc.). is the flight speed of UAV i at time t. ν is the flight power exponent, usually a positive value greater than 1. For example, ν = 2 means that the energy consumption is proportional to the square of the speed.

[0114] (2.2) Total utility of ground users

[0115] At time t, the total utility of ground user j consists of the privacy protection utility and the service quality utility

[0116]

[0117] (2.2.1) Privacy protection utility

[0118] The privacy information that ground user j hopes to protect is its actual location l j , and it hopes that the drone system can infer its actual location as little as possible from the location it reports . That is, it is necessary to minimize the mutual information The calculation formula is:

[0119]

[0120] It can be seen that and is the joint probability density, indicating that the actual location of ground user j is l j , and the reported location is The probability of, p(l j ) is the marginal probability density function of l j , indicating that the actual location of ground user j is l j The probability of, is The marginal probability density function of, indicating that the actual location of ground user j is The probability of; substituting the distributions that l j and respectively follow into the calculation of the KL divergence, the mutual information can be calculated. Taking the negative of it is the privacy protection utility

[0121]

[0122] (2.2.1) Quality of service utility

[0123] The quality of service utility of ground user j Expanded as:

[0124]

[0125] The positive correlation function f related to the quality of service utility can be defined as a variant of the sigmoid function:

[0126]

[0127] When the drone ratio increases, the quality of service improves; however, too many drones gathering in the same area may lead to unfair resource allocation. Therefore, a variant of the sigmoid function can be used to limit the upper limit of the quality of service obtained by ground users.

[0128] Furthermore, it can be obtained that:

[0129]

[0130] Among them, β is the maximum value of the service quality utility, representing the maximum service quality utility that ground users can obtain. γ is the sensitivity coefficient, used to control the steepness of the service quality utility function, and θ is the median point of the service quality utility function. When the value of the service quality utility function is half of the maximum service quality utility, that is

[0131] (3) Game model construction

[0132] From the perspective of game theory, an optimization objective for the UAV system is constructed based on the total UAV utility, and an optimization objective for ground users is constructed based on the total ground user utility. The UAV system and ground users are regarded as opposing entities, each optimizing its own optimization objective to construct a corresponding game model.

[0133] (3.1) Optimization objective of the UAV system

[0134] At time t, the optimization objective of the UAV system is:

[0135]

[0136] (3.2) Optimization objective of ground users

[0137] At time t, the optimization objective of ground users is:

[0138]

[0139] Among them, is the minimum value of the decision variable for ground user j to adjust the privacy protection intensity, is the maximum value of the decision variable for ground user j to adjust the privacy protection intensity.

[0140] (4) Solving the game model

[0141] (4.1) Using the Nash equilibrium algorithm to solve the game model

[0142] Step 1: Optimization of the UAV system side (fixing the user strategy)

[0143] For each UAV i, calculate the total UAV utility of all feasible allocations and select the task allocation strategy that can maximize the total UAV utility.

[0144] Step 2: Optimization of the ground user side (fixing the UAV strategy)

[0145] For each ground user j, optimize within the constraint range Solve through the gradient descent algorithm or other algorithms to maximize the total utility of ground users.

[0146] Step 3: Check convergence

[0147] Calculate the change in the total utility of the current strategy combination. If the change value is less than the preset convergence threshold or the number of iterations is greater than the preset iteration number threshold, stop.

[0148] (4.2) Solve the game model using the double auction algorithm

[0149] Step 1: Initialize

[0150] Each drone i calculates the initial bid B i,k (t) for all ground areas k, reflecting its service-providing ability and cost:

[0151]

[0152] Each ground user j calculates the initial willingness to pay A j (t) based on the privacy protection strength and quality of service:

[0153]

[0154] Step 2: Drone side bids

[0155] Each drone i updates its bid B i,k (t) for all ground areas k to reflect its service utility and flight cost. A higher bid indicates that the drone provides more competitive services in that ground area.

[0156] Step 3: Ground user side feedback:

[0157] Each ground user j updates the willingness to pay A i,k (t) based on the bid B j (t) of drone i and its own privacy protection strength. If A j (t) is higher than a certain drone bid, then the ground user is willing to pay for the service; otherwise, the ground user adjusts the privacy protection strength to change the willingness to pay.

[0158] Step 4: Matching strategy

[0159] For each ground area k, collect the bids B i,k (t) of each drone i and the willingness to pay A j (t) of each ground user j, and calculate the allocation strategy that maximizes the total utility of the drones

[0160] Step 5: Check convergence

[0161] Calculate the total utility change of the current strategy combination. If the change value is less than the preset convergence threshold or the number of iterations is greater than the preset iteration number threshold, stop.

[0162] In summary, according to the embodiments of the present invention, at least the following technical effects are achieved:

[0163] Based on the game theory framework, the present invention innovatively constructs a non - cooperative game model between the UAV system and ground users. In this model, the UAV system and ground users are respectively modeled as game players with opposing interest demands: the UAV system aims to maximize service utility and minimize flight cost, while ground users make decisions based on maximizing service quality utility and privacy protection utility. To solve this game model, the present invention proposes to use the Nash equilibrium algorithm or the double - auction algorithm to calculate the equilibrium solution, achieving the interest balance of both game parties. This method not only effectively solves the contradiction between ground user privacy protection and service quality requirements, but also realizes the cooperative scheduling and task optimization of multiple UAV systems, significantly improving the task execution efficiency and the overall system performance, providing reliable theoretical support and technical guarantee for the practical application of UAV systems in complex environments.

[0164] It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to the present invention.

[0165] The above is the introduction of the method embodiments. The following further illustrates the solution of the present invention through device embodiments.

[0166] Figure 2 The following is a structural diagram of a multi - UAV cooperative scheduling and task planning device provided for the embodiments of the present invention. As Figure 2 shown, the multi - UAV cooperative scheduling and task planning device 200 may include:

[0167] Define module 210, which is used to define a multi-UAV cooperative scheduling and task planning scenario for user privacy protection; in this scenario, it includes a UAV system composed of multiple UAVs, multiple ground users, a ground area accessible by multiple ground users and UAVs, and the location information of ground users is reported to the UAV system after being blurred by adding Gaussian noise. Ground users adjust the accuracy of the reported location information according to their own privacy protection intensity. The UAV system estimates the weights of the ground area based on the location information reported by ground users, and conducts multi-UAV cooperative scheduling and task planning.

[0168] Define module 210 is also used to define the total UAV utility and the total ground user utility based on the scenario; among them, the total UAV utility consists of service utility and flight cost, and the total ground user utility consists of privacy protection utility and quality of service utility.

[0169] Build module 220, which is used to build an optimization target for the UAV system based on the total UAV utility, build an optimization target for ground users based on the total ground user utility, regard the UAV system and ground users as mutually opposing entities, optimize their own optimization targets respectively, and build a game model corresponding to the scenario.

[0170] Solve module 230, which is used to solve the game model by using the Nash equilibrium algorithm or the double auction algorithm.

[0171] It can be understood that Figure 2 Each module / unit in the multi-UAV cooperative scheduling and task planning device 200 shown has the function of realizing Figure 1 Each step in the multi-UAV cooperative scheduling and task planning method 100 shown, and can achieve its corresponding technical effects. For the sake of brevity, it will not be elaborated here.

[0172] Figure 3 It is a structural diagram of an exemplary electronic device capable of implementing the embodiments of the present invention. The electronic device 300 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device 300 can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown in the present invention, their connections and relationships, and their functions are only examples and are not intended to limit the implementation of the present invention described and / or claimed in the present invention.

[0173] As Figure 3As shown, the electronic device 300 may include a computing unit 301, which may perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 302 or a computer program loaded from a storage unit 308 into a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 may also be stored. The computing unit 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0174] Multiple components in the electronic device 300 are connected to the I / O interface 305, including: an input unit 306, such as a keyboard, a mouse, etc.; an output unit 307, such as various types of displays, speakers, etc.; a storage unit 308, such as a magnetic disk, an optical disc, etc.; and a communication unit 309, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 309 allows the electronic device 300 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0175] The computing unit 301 may be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 301 include but are not limited to a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 301 executes the various methods and processes described above, such as method 100. For example, in some embodiments, method 100 may be implemented as a computer program product, including a computer program, which is tangibly contained in a computer-readable medium, such as the storage unit 308. In some embodiments, part or all of the computer program may be loaded and / or installed onto the electronic device 300 via the ROM 302 and / or the communication unit 309. When the computer program is loaded into the RAM 303 and executed by the computing unit 301, one or more steps of method 100 described above may be executed. Alternatively, in other embodiments, the computing unit 301 may be configured to execute method 100 in any other appropriate manner (e.g., by means of firmware).

[0176] The various embodiments described above in the present invention can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special or general programmable processor, and can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0177] The program code for implementing the methods of the present invention can be written in any combination of one or more programming languages. These program codes can be provided to the processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing devices, such that when the program codes are executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The program codes can be executed entirely on the machine, partially on the machine, executed partially on the machine as an independent software package and partially on a remote machine, or executed entirely on a remote machine or server.

[0178] In the context of the present invention, a computer-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of computer-readable storage media would include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0179] It should be noted that the present invention also provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to execute method 100 and achieve the corresponding technical effects achieved by the method of the embodiments of the present invention. For the sake of brevity of description, it will not be elaborated herein.

[0180] In addition, the present invention also provides a computer program product, which includes a computer program that, when executed by a processor, implements method 100.

[0181] It should be understood that various forms of the processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in the present invention can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in the present invention can be achieved. The present invention is not limited herein.

[0182] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A multi-UAV collaborative scheduling and task planning method for user privacy protection, characterized in that The method includes: Defining a multi-UAV collaborative scheduling and task planning scenario for user privacy protection; in this scenario, it includes a UAV system composed of multiple UAVs, multiple ground users, the ground area accessible to multiple ground users and UAVs, the location information of the ground users is reported to the UAV system after being blurred by adding Gaussian noise, the ground users adjust the accuracy of the reported location information according to their own privacy protection strength, and the UAV system estimates the weights of the ground area based on the location information reported by the ground users and conducts multi-UAV collaborative scheduling and task planning; Defining the total UAV utility and the total ground user utility based on the scenario; among them, the total UAV utility consists of service utility and flight cost, and the total ground user utility consists of privacy protection utility and quality of service utility; Constructing an optimization objective for the UAV system based on the total UAV utility, constructing an optimization objective for the ground users based on the total ground user utility, regarding the UAV system and the ground users as opposing entities, each optimizing its own optimization objective, and constructing a game model corresponding to the scenario; Using the Nash equilibrium algorithm or the double auction algorithm to solve the game model.

2. The method according to claim 1, wherein In the described scenario, there are a total of unmanned aerial vehicles, ground users, ground users and areas reachable by the unmanned aerial vehicles; Drone set Ground user set Ground area set Discrete time t = 1, 2, …, T, where T is the number of time instants; The position of UAV i at time t wherein, are respectively the x-axis coordinate, y-axis coordinate, and z-axis coordinate of UAV i at time t; The actual position of each ground user j at time t wherein, are respectively the x-axis coordinate and y-axis coordinate of ground user j at time t, and ground user j reports to the UAV system the position information after blurring it by adding Gaussian noise which satisfies a Gaussian distribution with as the mean value and as the variance, denoted as: is the decision variable for ground user j to adjust the privacy protection intensity at time t; Each ground area has a fixed center point l k =(x k , y k ), where x k , y k are the x-axis coordinate and y-axis coordinate of the center point l k respectively. To describe the actual position distribution of ground users, the following prior assumptions are made: If ground user j belongs to ground area k at time t, then its actual position follows a Gaussian distribution, and there is where is the degree of fuzziness quantifying the positions of ground users within ground area k; For each ground area k, at time t, it has a weight value The UAV system needs to estimate the weight value of the ground area based on the location information reported by the ground user. First, at time t, the contribution of ground user j to the weight of ground area k Sum up the contributions of all ground users to the weight of ground area k to obtain the total weight of ground area k at time t 3. The method according to claim 2, wherein At time t, the total utility of UAV i is composed of the service utility and the flight cost as follows: The total utility of ground user j at time t consists of the privacy protection utility and the quality of service utility as follows:

4. The method according to claim 3, wherein Service utility of the UAV i (t) is derived as follows: Define the optional variable Indicate whether the UAV i is assigned to the ground area k at time t: Ideally, without considering the actual service demand of the ground area, the service utility of the UAV for the ground area is constant. That is, for every additional UAV added to the same ground area k, the service utility it provides is independent of the other UAVs already in the ground area k. Thus, the service utility of UAV i for the ground area k at time t is defined as Where ∈ is a positive real constant to avoid division by zero errors; In the actual situation, there is an upper limit to the demand for services in the ground area. When the demand is met, the service utility provided by the drones will decline. It is necessary to model the service utility attenuation effect caused by the unfairness of resource allocation. First, define that at time t, the number of drones allocated to the ground area k is Calculate the location quotient of ground area k If it indicates that the allocated resources in ground area k exceed its demand, and the service utility of the UAV shows a decreasing trend. Therefore, the service utility of UAV i in ground area k is as follows: The flight cost of drone i Expanded as: Among them, η i is a conversion parameter related to the flight power of UAV i, is the flight speed of UAV i at time t, and ν is the flight power exponent.

5. The method according to claim 4, wherein Privacy protection utility of ground user j Expanded as: Quality of service utility of ground user j Expanded as: Among them, β is the maximum value of the service quality utility, representing the maximum service quality utility that ground users can obtain. γ is the sensitivity coefficient, used to control the steepness of the service quality utility function. θ is the median point of the service quality utility function. When the value of the service quality utility function is half of the maximum service quality utility, that is 6. The method according to claim 5, wherein At time t, the optimization objective of the UAV system is: At time t, the optimization objective of the ground users is: wherein, is the minimum value of the decision variable for ground user j to adjust the privacy protection strength, is the maximum value of the decision variable for ground user j to adjust the privacy protection strength.

7. The method according to claim 6, wherein Using the Nash equilibrium algorithm to solve the game model includes: For each drone i, calculate the total utility of all feasible assignments of drones, and select the task assignment strategy that maximizes the total utility of the drones; For each ground user j, optimize within the constraints Solve using the gradient descent algorithm for the optimal value to maximize the total utility of ground users; Calculating the change in the total utility of the current strategy combination, and stopping if the change value is less than the preset convergence threshold or the number of iterations is greater than the preset iteration number threshold.

8. The method according to claim 6, wherein Using the double auction algorithm to solve the game model includes: Each drone i calculates an initial bid B i,k (t) for all ground areas k Each ground user j calculates the initial willingness to pay A j (t): Each drone i updates its bid B i,k (t) for all ground areas k to reflect its service utility and flight cost. A higher bid indicates that the drone offers more competitive services in that ground area; Each ground user j updates its willingness to pay A i,k (t) based on the offer B j (t) of the UAV i and its own privacy protection strength. If A j (t) is higher than a certain UAV offer, then the ground user is willing to pay for the service; otherwise, the ground user adjusts its privacy protection strength to change its willingness to pay; For each ground area k, collect the bids B i,k (t) of each drone i and the willingness to pay A j (t) of each ground user j, and calculate the allocation strategy that maximizes the total utility of the drones Calculating the change in the total utility of the current strategy combination, and stopping if the change value is less than the preset convergence threshold or the number of iterations is greater than the preset iteration number threshold.

9. A multi-UAV collaborative scheduling and task planning device for user privacy protection, characterized in that, The device includes: A definition module for defining a multi-UAV collaborative scheduling and task planning scenario for user privacy protection; in this scenario, it includes a UAV system composed of multiple UAVs, multiple ground users, the ground area accessible to multiple ground users and UAVs, the location information of the ground users is reported to the UAV system after being blurred by adding Gaussian noise, the ground users adjust the accuracy of the reported location information according to their own privacy protection strength, and the UAV system estimates the weights of the ground area based on the location information reported by the ground users and conducts multi-UAV collaborative scheduling and task planning; The definition module is also used for defining the total UAV utility and the total ground user utility based on the scenario; among them, the total UAV utility consists of service utility and flight cost, and the total ground user utility consists of privacy protection utility and quality of service utility; A construction module for constructing an optimization objective for the UAV system based on the total UAV utility, constructing an optimization objective for the ground users based on the total ground user utility, regarding the UAV system and the ground users as opposing entities, each optimizing its own optimization objective, and constructing a game model corresponding to the scenario; A solution module for using the Nash equilibrium algorithm or the double auction algorithm to solve the game model.

10. An electronic device, characterized in that, The electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method according to any one of claims 1-8.

Images