Smart microgrid energy management method and device considering user differential privacy protection

Abstract

A smart microgrid energy management method and device considering user differential privacy protection, the method comprising: considering the privacy protection preference level of the smart microgrid user, randomly generating a noise signal using the Laplace mechanism, and adding the noise signal to the initial power load data of the user's smart meter; the smart microgrid operator establishes a microgrid optimal power flow model with the goal of minimizing the power generation cost, and solves to obtain the optimal output power and node marginal price of the generator set; the Shapley value method is used to allocate the additional power generation cost of the smart microgrid to the user, and the user adjusts his privacy protection preference level according to the total electricity cost in the next time period, and the smart microgrid operator obtains the optimal energy management plan for the next time period according to the user's new privacy protection preference level. The present invention takes into account the privacy protection of user power consumption data in the smart microgrid energy management method, thereby obtaining a safer, more reasonable and flexible energy management plan.

Description

Technical Field

[0001] The present invention relates to the technical field of microgrid energy management, and in particular to an intelligent microgrid energy management method and device considering user differential privacy protection. Background Art

[0002] Smart microgrids, through the use of advanced Internet and information technology, can not only achieve energy self-sufficiency, but also improve energy efficiency and reduce environmental pollution by optimizing energy allocation and management. They are gradually becoming a hot topic in research and the focus of application. In order to achieve real-time monitoring and automatic response, smart microgrids usually need to install a large number of smart meters to collect high-precision user electricity consumption data and realize two-way interaction between users and microgrids. Differential privacy is a privacy protection technology that adds an appropriate amount of noise to the statistical results to ensure that modifying an individual record in the data set will not have a significant impact on the statistical results, thereby meeting the requirements of user privacy protection.

[0003] Existing smart microgrid energy management methods are usually based on the real electricity consumption data recorded by the user's smart meter, combined with the output characteristics of various distributed power generation equipment and the operation mode of energy storage equipment, with the goal of minimizing the comprehensive cost of microgrid operation, and using intelligent algorithms to solve, and obtain the operation plan of power generation and energy storage equipment and the user's electricity cost. The above-mentioned microgrid energy management method ignores the protection of a large amount of real electricity consumption data information of users. Attackers can analyze personal privacy information such as users' living habits and electricity consumption patterns from it, which poses a great threat to users' privacy protection and the safe operation of smart microgrids. Therefore, it is necessary to consider the privacy protection of users' electricity consumption data in microgrid energy management to obtain a safer and more reasonable energy management solution. Summary of the invention

[0004] The purpose of the present invention is to overcome the above-mentioned defects and problems existing in the prior art, and to provide a smart microgrid energy management method and device taking into account user differential privacy protection, so as to solve the problem that the existing smart microgrid energy management method ignores the privacy protection of microgrid user electricity consumption data.

[0005] To achieve the above objectives, the technical solution of the present invention is: a smart microgrid energy management method considering user differential privacy protection, comprising:

[0006] Considering the privacy protection preference level of smart microgrid users, a Laplace mechanism is used to randomly generate noise signals, and the noise signals are added to the initial power load data of the user's smart meter.

[0007] Based on the electricity load data with noisy signals, the smart microgrid operator takes the minimization of power generation cost as the goal, considers the node power balance constraints, line transmission constraints, and generator output power constraints, establishes the microgrid optimal power flow model, and solves the optimal output power of the generator and the node marginal price;

[0008] Calculate the additional power generation cost of the smart microgrid after considering differential privacy protection, and use the Shapley value method to allocate the additional power generation cost to users;

[0009] Based on the total cost including electricity cost and additional cost generated by differential privacy protection, users can adjust their privacy protection preference level in the next period, and the smart microgrid operator obtains the optimal energy management plan for the next period according to the user's new privacy protection preference level.

[0010] The privacy protection preference level of the smart microgrid user is considered, and the Laplace mechanism is used to randomly generate noise signals, including:

[0011] Smart microgrid users decide whether to accept differential privacy protection and choose their privacy protection preference level when accepting differential privacy protection;

[0012] Based on the privacy protection preference level ρ of user n n , ρ n ∈{0.01, 0.1, 0.5}, and ρ n =0.01 indicates a high privacy protection preference level, ρ n =0.1 indicates a medium privacy protection preference level, ρ n =0.5 indicates a low level of privacy protection preference;

[0013] From the Laplace distribution Randomly generate noise signal ε n .

[0014] The objective function of the microgrid optimal power flow model is:

[0015]

[0016] In the formula, is a node set; Ω i is the set of generators located at node i; P g，i is the active power output by the generator set g at node i; θ i is the voltage phase angle of node i; f g，i is the power generation cost function of the generator g located at node i; is the minimum power generation cost of the smart microgrid obtained based on the power load data with noise signals; Electricity load data with noisy signals for all users.

[0017] The node power balance constraint is:

[0018]

[0019]

[0020] Where P i is the active power of node i; is the active power demand of user at node i; P l，i is the active power loss of user at node i; Q i is the reactive power of node i; Q g，i is the reactive power output by the generator g at node i; Q d，i is the reactive power demand of the user at node i; Q l，i is the reactive power loss of node i;

[0021] The line transmission constraints are:

[0022]

[0023]

[0024]

[0025]

[0026] V min ≤V i ≤V max ;

[0027] Where P i，j and Q i，j are the active power flow and reactive power flow of the line connecting node i and node j respectively; V i and V j are the voltages of nodes i and j respectively; g i，j and b i，j are the conductance and susceptance of the line connecting node i and node j respectively; θ i，j is the phase difference between node i and node j; V nom is the rated voltage; is the maximum power flow of the line connecting node i and node j; and are the minimum and maximum active power flows of the line connecting node i and node j respectively; V min and V max are the minimum and maximum values ​​of the node voltage respectively;

[0028] The generator set output power constraint is:

[0029]

[0030]

[0031] In the formula, and are the minimum and maximum values ​​of the active power output by the generator set g located at the node i, respectively; is the power factor angle of generator set g located at node i.

[0032] The node marginal price is:

[0033] LMP i =λ i +μ i ;

[0034] Where, LMP i is the marginal price of node i, λ i is the energy price of the microgrid system, corresponding to the Lagrange multiplier of the node power balance constraint; μ i is the congestion price, corresponding to the Lagrange multiplier of the line transmission constraint.

[0035] The additional power generation cost of the smart microgrid after considering differential privacy protection is:

[0036]

[0037] In the formula, For the additional cost of power generation, is the set of users n; P d is the initial power load data of all users; c(P d ) is the minimum power generation cost of the smart microgrid obtained based on the initial power load data; is the minimum power generation cost of the smart microgrid obtained based on the power load data with noisy signals.

[0038] The method of allocating the additional power generation cost to users using the Shapley value method is:

[0039]

[0040] In the formula, Sh n is the cost allocated to user n; and S are a subset of all users excluding user n and the number of people in the set respectively; is the set of user n, and User collections and The increased power generation cost caused by the operation of smart microgrids.

[0041] Based on the total cost including the electricity cost and the additional cost generated by differential privacy protection, the user can adjust his privacy protection preference level in the next period, and the smart microgrid operator obtains the optimal energy management solution for the next period according to the user's new privacy protection preference level, including:

[0042] Calculate the total cost TC of the user in the current period n :

[0043] TC n =LMP n ×P d，n +Sh n ;

[0044] Where, LMP n is the marginal electricity price of the node where user n is located; P d，n The initial power load data recorded by the smart meter of user n; Sh n is the cost allocated to user n;

[0045] According to the total cost TC of the user in the current period n , user n updates his privacy protection preference level ρ n ;

[0046] The smart microgrid operator implements the Laplace noise mechanism and solves the optimal power flow model according to the updated privacy protection preference level to obtain the optimal energy management plan for the next period.

[0047] A smart microgrid energy management device considering user differential privacy protection, the device is applied to the above-mentioned method, the device comprising:

[0048] The power load data processing module is used to consider the privacy protection preference level of smart microgrid users, randomly generate noise signals using the Laplace mechanism, and add the noise signals to the initial power load data of the user's smart meter;

[0049] The microgrid optimal power flow model building module is used to establish the microgrid optimal power flow model based on the power load data with noise signals. The smart microgrid operator takes the minimization of power generation cost as the goal, considers the node power balance constraints, line transmission constraints, and generator output power constraints, and solves the optimal output power of the generator and the node marginal price.

[0050] The power generation cost allocation module is used to calculate the additional power generation cost of the smart microgrid after considering differential privacy protection, and allocate the additional power generation cost to users using the Shapley value method;

[0051] The optimal energy management solution generation module is used to generate the optimal energy management solution for the next period based on the total cost including the electricity cost and the additional cost generated by differential privacy protection. Users can adjust their privacy protection preference level in the next period, and the smart microgrid operator obtains the optimal energy management solution for the next period according to the user's new privacy protection preference level.

[0052] A smart microgrid energy management device considering user differential privacy protection includes a memory and a processor;

[0053] The memory is used to store computer program code and transmit the computer program code to the processor;

[0054] The processor is used to execute the method according to the instructions in the computer program code.

[0055] Compared with the prior art, the present invention has the following beneficial effects:

[0056] The present invention provides an intelligent microgrid energy management method and device that considers user differential privacy protection. The method includes the user's privacy protection preference for personal electricity consumption data in the microgrid energy management model, and adopts the Shapley value method to achieve fair distribution of the additional cost after considering privacy protection. At the same time, the user is allowed to update his privacy protection preference level according to the total cost paid, thereby obtaining a safer, more reasonable and flexible microgrid energy management solution. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 It is a flow chart of a smart microgrid energy management method considering user differential privacy protection of the present invention.

[0058] Figure 2 It is a flowchart of user differential privacy protection provided by an embodiment of the present invention.

[0059] Figure 3 It is a structural block diagram of an intelligent microgrid energy management device that takes user differential privacy protection into consideration in the present invention.

[0060] Figure 4 It is a structural block diagram of a smart microgrid energy management device that takes user differential privacy protection into consideration in the present invention. DETAILED DESCRIPTION

[0061] The present invention is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0062] See also Figure 1 , a smart microgrid energy management method considering user differential privacy protection, comprising:

[0063] S1. Considering the privacy protection preference level of smart microgrid users, a Laplace mechanism is used to randomly generate noise signals, and the noise signals are added to the initial power load data of the user's smart meter;

[0064] S2. Based on the power load data with noise signals, the smart microgrid operator takes the minimization of power generation cost as the goal, considers the node power balance constraint, line transmission constraint, and generator output power constraint, establishes the microgrid optimal power flow model, and solves the optimal output power of the generator and the node marginal price;

[0065] S3. Calculate the additional power generation cost of the smart microgrid after considering differential privacy protection, and use the Shapley value method to allocate the additional power generation cost to users;

[0066] S4. Based on the total cost including electricity cost and additional cost generated by differential privacy protection, users can adjust their privacy protection preference level in the next period, and the smart microgrid operator obtains the optimal energy management plan for the next period according to the user's new privacy protection preference level.

[0067] Furthermore, the node set of the smart microgrid is The line set is The user collection is Per user Connected to different nodes, the initial power load data recorded by its smart meter is P d，n .

[0068] like Figure 2 As shown, first, smart microgrid users Decide whether to accept differential privacy protection and choose the privacy protection preference level ρ when accepting differential privacy protection n , where ρ n ∈{0.01, 0.1, 0.5}, and ρ n =0.01 indicates a high privacy protection preference level, ρ n =0.1 indicates a medium privacy protection preference level, ρ n = 0.5 indicates a low privacy protection preference level. Then, based on the privacy protection preference level ρ of user n n , from the Laplace distribution Randomly generate noise signal ε n , and add the noise signal to the user's initial power load data. After adding the noise signal, the power load data of user n is: In addition, remember and They are the initial power load data of all users and the power load data with noise signals.

[0069] Furthermore, the objective function of the microgrid optimal power flow model is:

[0070]

[0071] In the formula, is a node set; Ω i is the set of generators located at node i, P g，i is the active power output by the generator set g at node i; θ i is the voltage phase angle of node i; f g，i is the power generation cost function of the generator g located at node i; is the minimum power generation cost of the smart microgrid obtained based on the power load data with noise signals; Electricity load data with noisy signals for all users.

[0072] Furthermore, the node power balance constraint is:

[0073]

[0074]

[0075] Where P i is the active power of node i; is the active power demand of user at node i; P l，i is the active power loss of user at node i; Q i is the reactive power of node i; Q g，i is the reactive power output by the generator g at node i; Q d，i is the reactive power demand of the user at node i; Q l，i is the reactive power loss of node i.

[0076] In the microgrid, on the one hand, the phase difference θ between node i and node j is i，j =θ i -θ j Usually small, it can be approximated as θ i，j ≈0; on the other hand, the node voltage is close to the rated voltage V nom Therefore, the line power flow can be linearized as:

[0077]

[0078]

[0079] The line transmission constraints are:

[0080]

[0081]

[0082] V min ≤V j ≤V max ;

[0083] Where P i，j and Q i，j are the active power flow and reactive power flow of the line connecting node i and node j respectively; V i and V j are the voltages of nodes i and j respectively; g i，j and b i，j are the conductance and susceptance of the line connecting node i and node j respectively; θ i，j is the phase difference between node i and node j; V nom is the rated voltage; is the maximum power flow of the line connecting node i and node j; and are the minimum and maximum active power flows of the line connecting node i and node j respectively; V min and V max are the minimum and maximum values ​​of the node voltage respectively.

[0084] The node power loss can be calculated by the following formula:

[0085]

[0086] In the formula, R i，j and X i，j are the resistance and reactance of the line connecting node i and node j, respectively.

[0087] The generator set output power constraint is:

[0088]

[0089]

[0090] In the formula, and are the minimum and maximum values ​​of the active power output by the generator set g located at the node i, respectively; is the power factor angle of generator set g located at node i.

[0091] Furthermore, the node marginal price is:

[0092] LMP i =λ i +μ i ;

[0093] Where, LMP iis the marginal price of node i, λ i is the energy price of the microgrid system, corresponding to the Lagrange multiplier of the node power balance constraint; μ i is the congestion price, corresponding to the Lagrange multiplier of the line transmission constraint.

[0094] Furthermore, considering differential privacy protection, the additional power generation cost of the smart microgrid is:

[0095]

[0096] In the formula, is the additional power generation cost; P d is the initial power load data of all users; c(P d ) is the minimum power generation cost of the smart microgrid obtained based on the initial power load data; is the minimum power generation cost of the smart microgrid obtained based on the power load data with noisy signals.

[0097] Furthermore, the Shapley value method is used to fairly distribute the additional power generation cost among users, where the additional cost allocated to user n is:

[0098]

[0099] In the formula, Sh n is the cost allocated to user n; and S are a subset of all users excluding user n and the number of people in the set respectively; and User collections and The increased power generation cost caused by the operation of smart microgrids.

[0100] Furthermore, based on the total cost including the electricity cost and the additional cost generated by differential privacy protection, the user can adjust his privacy protection preference level in the next period, and the smart microgrid operator obtains the optimal energy management solution for the next period according to the user's new privacy protection preference level, including:

[0101] Calculate the total cost TC of the user in the current period n :

[0102] TC n =LMP n ×P d，n +Sh n ;

[0103] Where, LMP n is the marginal electricity price of the node where user n is located; P d，n The initial power load data recorded by the smart meter of user n; Shn is the cost allocated to user n;

[0104] According to the total cost TC of the user in the current period n , user n updates his privacy protection preference level ρ n ;

[0105] The smart microgrid operator implements the Laplace noise mechanism and solves the optimal power flow model according to the updated privacy protection preference level to obtain the optimal energy management plan for the next period.

[0106] See also Figure 3 The present invention also provides a smart microgrid energy management device considering user differential privacy protection, which is applied to the smart microgrid energy management method considering user differential privacy protection as described above, and the device comprises:

[0107] The power load data processing module is used to consider the privacy protection preference level of smart microgrid users, randomly generate noise signals using the Laplace mechanism, and add the noise signals to the initial power load data of the user's smart meter;

[0108] The microgrid optimal power flow model building module is used to establish the microgrid optimal power flow model based on the power load data with noise signals. The smart microgrid operator takes the minimization of power generation cost as the goal, considers the node power balance constraints, line transmission constraints, and generator output power constraints, and solves the optimal output power of the generator and the node marginal price.

[0109] The power generation cost allocation module is used to calculate the additional power generation cost of the smart microgrid after considering differential privacy protection, and allocate the additional power generation cost to users using the Shapley value method;

[0110] The optimal energy management solution generation module is used to generate the optimal energy management solution for the next period based on the total cost including the electricity cost and the additional cost generated by differential privacy protection. Users can adjust their privacy protection preference level in the next period, and the smart microgrid operator obtains the optimal energy management solution for the next period according to the user's new privacy protection preference level.

[0111] See also Figure 4 ,The present invention also provides a smart microgrid energy management device considering user differential privacy protection, including a memory and a processor;

[0112] The memory is used to store computer program code and transmit the computer program code to the processor;

[0113] The processor is used to execute the above-mentioned smart microgrid energy management method considering user differential privacy protection according to the instructions in the computer program code.

[0114] The present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the smart microgrid energy management method considering user differential privacy protection is implemented.

[0115] Generally speaking, the computer instructions for implementing the method of the present invention may be carried in any combination of one or more computer-readable storage media. Non-transitory computer-readable storage media may include any computer-readable media except for the signal itself that is temporarily propagating.

[0116] The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EKROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, device, or device.

[0117] Computer program code for performing the operation of the present invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages, in particular, Python suitable for neural network computing and platform frameworks based on TensorFlow, PyTorch, etc. can be used. The program code can be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer or to an external computer (for example, using an Internet service provider to connect via the Internet) through any type of network, including a local area network (LAN) or a wide area network (WAN).

[0118] The above-mentioned devices and non-temporary computer-readable storage media can be found in the specific description of a smart microgrid energy management method considering user differential privacy protection and its beneficial effects, which will not be repeated here.

[0119] Although the embodiments of the present invention have been shown and described above, it should be understood that the above embodiments are exemplary and should not be construed as limitations on the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A smart microgrid energy management method considering user differential privacy protection, characterized in that: include: Considering the privacy protection preference level of smart microgrid users, a Laplace mechanism is used to randomly generate noise signals, and the noise signals are added to the initial power load data of the user's smart meter. Based on the electricity load data with noisy signals, the smart microgrid operator takes the minimization of power generation cost as the goal, considers the node power balance constraints, line transmission constraints, and generator output power constraints, establishes the microgrid optimal power flow model, and solves the optimal output power of the generator and the node marginal price; The objective function of the microgrid optimal power flow model is: In the formula, is a node set; Ω i is the set of generators located at node i; P g，i is the active power output by the generator set g located at node i; θ i is the voltage phase angle of node i; f g，i is the power generation cost function of the generator g located at node i; is the minimum power generation cost of the smart microgrid obtained based on the power load data with noise signals; Power load data with noisy signals for all users; Calculate the additional power generation cost of the smart microgrid after considering differential privacy protection, and use the Shapley value method to allocate the additional power generation cost to users; The additional power generation cost of the smart microgrid after considering differential privacy protection is: In the formula, For the additional cost of power generation, is the set of users n; P d is the initial power load data of all users; c(P d ) is the minimum power generation cost of the smart microgrid obtained based on the initial power load data; is the minimum power generation cost of the smart microgrid obtained based on the power load data with noise signals; The method of allocating the additional power generation cost to users using the Shapley value method is: In the formula, Sh n is the cost allocated to user n; and S are a subset of all users excluding user n and the number of people in the subset respectively; is the set of users n, and User collections and The increased power generation cost of smart microgrid operation; Based on the total cost including electricity cost and additional cost generated by differential privacy protection, users can adjust their privacy protection preference level in the next period, and the smart microgrid operator obtains the optimal energy management plan for the next period according to the user's new privacy protection preference level.

2. According to claim 1, a smart microgrid energy management method considering user differential privacy protection is characterized in that: The privacy protection preference level of the smart microgrid user is considered, and the noise signal is randomly generated by using the Laplace mechanism, including: Smart microgrid users decide whether to accept differential privacy protection and choose their privacy protection preference level when accepting differential privacy protection; Based on the privacy protection preference level ρ of user n n , ρ n ∈{0.01, 0.1, 0.5}, and ρ n =0.01 indicates a high privacy protection preference level, ρ n =0.1 indicates a medium privacy protection preference level, ρ n =0.5 indicates a low level of privacy protection preference; From the Laplace distribution Randomly generate noise signal ε n .

3. According to claim 1, a smart microgrid energy management method considering user differential privacy protection is characterized in that: The node power balance constraint is: Where P i is the active power of node i; is the active power demand of user at node i; P l，i is the active power loss of user at node i; Q i is the reactive power of node i; Q g，i is the reactive power output by the generator set g at node i; Q d，i is the reactive power demand of the user at node i; Q l，i is the reactive power loss of node i; The line transmission constraints are: P i，j 2 +Q i，j 2 ≤(S i，j max ) 2 ; P i，j min ≤P i，j≤ P i，j max ; In min ≤V i ≤V max ; Where P i，j and Q i，j are the active power flow and reactive power flow of the line connecting node i and node j respectively; V i and V j are the voltages of nodes i and j respectively; g i，j and b i，j are the conductance and susceptance of the line connecting node i and node j respectively; θ i，j is the phase difference between node i and node j; V nom is the rated voltage; S i，j max is the maximum power flow of the line connecting node i and node j; P i，j min and P i，j max are the minimum and maximum active power flows of the line connecting node i and node j respectively; V min and V max are the minimum and maximum values ​​of the node voltage respectively; The generator set output power constraint is: P g，i min ≤P g，i ≤P g，i max ; Where P g，i min and P g，i max are the minimum and maximum values ​​of the active power output by the generator set g located at the node i, respectively; is the power factor angle of generator set g located at node i.

4. The smart microgrid energy management method considering user differential privacy protection according to claim 1 is characterized in that: The node marginal price is: LMP i =λ i +m i ; Where, LMP i is the marginal price of node i, λ i is the energy price of the microgrid system, corresponding to the Lagrange multiplier of the node power balance constraint; μ i is the congestion price, corresponding to the Lagrange multiplier of the line transmission constraint.

5. The smart microgrid energy management method considering user differential privacy protection according to claim 1 is characterized in that: Based on the total cost including the electricity cost and the additional cost generated by differential privacy protection, the user can adjust his privacy protection preference level in the next period, and the smart microgrid operator obtains the optimal energy management solution for the next period according to the user's new privacy protection preference level, including: Calculate the total cost TC of the user in the current period n : TC n =LMP n ×P d，n +Sh n ; Where, LMP n is the marginal electricity price of the node where user n is located; P d，n The initial power load data recorded by the smart meter of user n; Sh n is the cost allocated to user n; According to the total cost TC of the user in the current period n , user n updates his privacy protection preference level ρ n ; The smart microgrid operator implements the Laplace noise mechanism and solves the optimal power flow model according to the updated privacy protection preference level to obtain the optimal energy management plan for the next period.

6. A smart microgrid energy management device considering user differential privacy protection, characterized in that: The device is applied to the method described in any one of claims 1 to 5, and the device comprises: The power load data processing module is used to consider the privacy protection preference level of smart microgrid users, randomly generate noise signals using the Laplace mechanism, and add the noise signals to the initial power load data of the user's smart meter; The microgrid optimal power flow model building module is used to establish the microgrid optimal power flow model based on the power load data with noise signals. The smart microgrid operator takes the minimization of power generation cost as the goal, considers the node power balance constraints, line transmission constraints, and generator output power constraints, and solves the optimal output power of the generator and the node marginal price. The power generation cost allocation module is used to calculate the additional power generation cost of the smart microgrid after considering differential privacy protection, and allocate the additional power generation cost to users using the Shapley value method; The optimal energy management solution generation module is used to generate the optimal energy management solution for the next period based on the total cost including the electricity cost and the additional cost generated by differential privacy protection. Users can adjust their privacy protection preference level in the next period, and the smart microgrid operator obtains the optimal energy management solution for the next period according to the user's new privacy protection preference level.

7. A smart microgrid energy management device considering user differential privacy protection, characterized in that: including memory and processor; The memory is used to store computer program code and transmit the computer program code to the processor; The processor is configured to execute the method according to any one of claims 1 to 5 according to instructions in the computer program code.

Images