Microgrid scheduling method and device, computer equipment, medium and program product

Abstract

The invention provides a micro-grid dispatching method. The micro-grid dispatching method comprises the following steps: acquiring micro-grid state real-time data of a micro-grid; determining a micro-grid state prediction data sequence of the micro-grid in the prediction time sequence by using a time sequence prediction model based on the micro-grid state real-time data; on the basis of the microgrid state prediction data sequence and the value set of the control variables, a preset differentiable utility function is optimized, a scheduling strategy is determined, and the scheduling strategy comprises an optimized value sequence of the control variables in the prediction time sequence; adjusting model parameters of the time sequence prediction model based on the differentiable utility function, the microgrid state prediction data sequence and the optimization value sequence of the control variables; and scheduling the micro-grid based on a scheduling strategy. The invention further relates to a micro-grid dispatching device applying the micro-grid dispatching method, and computer equipment, computer readable storage equipment and a computer program product which are used for implementing the steps of the micro-grid dispatching method.

Description

Technical Field

[0001] The present disclosure relates to the field of industrial control, and in particular, to a microgrid scheduling method, a microgrid scheduling device applying the method, and also to a computer device, a computer-readable storage device, and a computer program product for implementing each step of the above-mentioned microgrid scheduling method. Background Art

[0002] Microgrid is a small grid system composed of distributed energy, energy storage system and load, which can operate in grid-connected or off-grid mode. Microgrid dispatching is to coordinate the dispatching of various components in the microgrid to achieve stable, economical and reliable operation of the microgrid. Intelligent dispatching of microgrids needs to consider multiple state inputs including distributed energy systems (such as solar energy, wind energy, biomass energy, fuel cells, etc.), energy storage systems, real-time and predicted loads, grid status, and environmental and weather data to optimize energy distribution and improve energy efficiency.

[0003] In order to achieve the dispatch of microgrids, predictions are generally made first (such as load prediction), and then decisions are optimized based on the prediction results (such as microgrid dispatch). However, in the existing solutions in the field of microgrid dispatch, prediction and decision-making are two independent tasks, so that the solution often cannot fully consider the mutual influence between the two, resulting in suboptimal dispatch effects and energy utilization, unable to achieve accurate energy management, and unable to optimize the comprehensive utilization of photovoltaic power generation and energy storage in microgrids, and may even have an adverse impact on energy efficiency and grid stability. Summary of the invention

[0004] According to a first aspect of the present disclosure, a microgrid scheduling method is provided, which includes: acquiring real-time data of a microgrid state of a microgrid; determining a microgrid state prediction data sequence of the microgrid in a prediction time series using a time series prediction model based on the real-time data of the microgrid state; optimizing a preset differentiable utility function based on the microgrid state prediction data sequence and a set of values ​​of control variables to determine a scheduling strategy, wherein the scheduling strategy includes an optimized value sequence of the control variable in the prediction time series; adjusting model parameters of the time series prediction model based on the differentiable utility function, the microgrid state prediction data sequence and the optimized value sequence of the control variable; and scheduling the microgrid based on the scheduling strategy.

[0005] According to some exemplary embodiments, the preset differentiable utility function is optimized based on the microgrid state prediction data sequence and the value set of the control variable, and the scheduling strategy is determined, including: determining the minimum value of the differentiable utility function under preset constraints; and determining the value sequence of the control variable corresponding to the minimum value of the differentiable utility function as the optimized value sequence of the control variable in the prediction time series.

[0006] According to some exemplary embodiments, the differentiable utility function includes summing the maximum net power consumption preset in the forecast time series and the sum of the time-sharing charges; the control variables include the battery charging control variable and the battery discharging control variable at each moment in the forecast time series. The preset constraints include: the net power consumption at each moment in the forecast time series meets the preset power consumption demand of the microgrid and is less than the preset maximum net power consumption; the value of the battery charging control variable is greater than or equal to 0 and less than or equal to 1, and the value of the battery discharging control variable is greater than or equal to -1 and less than or equal to 0.

[0007] According to some exemplary embodiments, the time series prediction model includes a neural network prediction model pre-trained using existing microgrid status data; the method of determining the microgrid status prediction data sequence of the microgrid in the prediction time series based on the real-time data of the microgrid status using the time series prediction model includes: inputting the real-time data of the microgrid status into the neural network prediction model to generate the microgrid status prediction data sequence.

[0008] According to some exemplary embodiments, the adjusting of the model parameters of the time series prediction model based on the differentiable utility function, the microgrid state prediction data sequence and the optimized value sequence of the control variable includes: substituting the optimized value sequence and the microgrid state prediction data sequence into the differentiable utility function to generate a differentiable utility function corresponding to the optimized value sequence; determining the derivatives of the model parameters of the time series prediction model based on the differentiable utility function corresponding to the optimized value sequence; and adjusting the model parameters based on the derivatives of the model parameters.

[0009] According to some exemplary embodiments, the microgrid real-time status information includes power consumption data, power generation data, load demand data, and stored power data of the microgrid.

[0010] According to some exemplary embodiments, the microgrid real-time status information also includes ambient temperature data

[0011] According to a second aspect of the present disclosure, a microgrid scheduling device is provided, which includes: a data collection module, a prediction module, a decision module, a parameter adjustment module and an execution module. The data collection module is configured to obtain real-time data of a microgrid state of a microgrid. The prediction module is configured to determine a microgrid state prediction data sequence in the microgrid using a time series prediction model based on the real-time data of the microgrid state. The decision module is configured to optimize a preset differentiable utility function based on the microgrid state prediction data sequence and a set of values ​​of control variables to determine a scheduling strategy, wherein the scheduling strategy includes an optimized value sequence of the control variable in the predicted time series. The parameter adjustment module is configured to adjust the model parameters of the time series prediction model based on the differentiable utility function, the microgrid state prediction data sequence and the optimized value sequence of the control variable. The execution module is configured to schedule the microgrid based on the scheduling strategy.

[0012] According to some exemplary embodiments, the time series prediction model in the prediction module includes a neural network prediction model pre-trained using existing microgrid status data, and the neural network prediction model is configured to: receive the real-time data of the microgrid status, and generate the microgrid status prediction data sequence based on the real-time data of the microgrid status.

[0013] According to some exemplary embodiments, the parameter adjustment module is further configured to: substitute the optimized value sequence and the microgrid state prediction data sequence into the differentiable utility function to generate a differentiable utility function corresponding to the optimized value sequence; determine the derivatives of the model parameters of the time series prediction model based on the differentiable utility function corresponding to the optimized value sequence; and adjust the model parameters based on the derivatives of the model parameters.

[0014] According to some exemplary embodiments, the differentiable utility function includes summing the maximum net power consumption and the total time-sharing charges preset in the predicted time series; the control variables include a battery charging control variable and a battery discharging control variable at each moment in the predicted time series; the decision module is also configured to: determine the minimum value of the differentiable utility function under preset constraints, and determine the value sequence of the control variable corresponding to the minimum value of the differentiable utility function as the optimized value sequence of the control variable in the predicted time series, wherein the preset constraints include: the net power consumption at each moment meets the power consumption demand of the microgrid and is less than the maximum net power consumption; the value of the battery charging control variable is greater than or equal to 0 and less than or equal to 1, and the value of the battery discharging control variable is greater than or equal to -1 and less than or equal to 0.

[0015] According to a third aspect of the present disclosure, a computer device is provided, comprising a memory, a processor, and computer instructions stored on the memory, wherein the processor executes the computer program to implement the steps of the microgrid scheduling method according to the first aspect of the present disclosure and its various exemplary embodiments.

[0016] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, on which computer instructions are stored, wherein when the computer instructions are executed by a processor, the steps of the microgrid scheduling method according to the first aspect of the present disclosure and its exemplary embodiments are implemented.

[0017] According to a fifth aspect of the present disclosure, a computer program product is provided, comprising computer instructions, wherein when the computer instructions are executed by a processor, the steps of the microgrid scheduling method according to the first aspect of the present disclosure and its exemplary embodiments are implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Hereinafter, various exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings; in the accompanying drawings:

[0019] Figure 1 An application scenario according to an exemplary embodiment of the present disclosure is schematically shown;

[0020] Figure 2 A microgrid scheduling method according to an exemplary embodiment of the present disclosure is schematically illustrated in the form of a flow chart;

[0021] Figure 3 According to an exemplary embodiment of the present disclosure, details of the microgrid scheduling method are further shown;

[0022] Figure 4 According to an exemplary embodiment of the present disclosure, details of the microgrid scheduling method are further shown;

[0023] Figure 5 The process of adjusting the model parameters of the time series prediction model in the microgrid dispatching method according to the present disclosure is schematically shown in the form of a block diagram;

[0024] Figure 6 A microgrid dispatching device according to an exemplary embodiment of the present disclosure is schematically shown in the form of a block diagram;

[0025] Figure 7 A computer device according to an exemplary embodiment of the present disclosure is schematically illustrated in the form of a block diagram.

[0026] It should be understood that the accompanying drawings are only schematic illustrations of exemplary embodiments of the present disclosure, and are not intended to limit the present disclosure, nor are they necessarily drawn to scale. In addition, in the accompanying drawings, identical or similar features are indicated by identical or similar reference numerals. DETAILED DESCRIPTION

[0027] Various exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings so that those skilled in the art can fully understand and implement the technical solutions according to the present disclosure.

[0028] See also Figure 1 , which schematically illustrates an application scenario according to an embodiment of the present disclosure. Figure 1 As shown, in the application scenario 100, the grid architecture 110 is respectively connected to the distributed energy 120, the power storage device 130 and the load 140 to form a microgrid. The distributed energy 120 may include a wind power generation device 120a and a solar power generation device 120b. However, it should be understood that other types of distributed energy are also possible, such as biomass power generation devices. The power storage device 130 may include any suitable type of battery, and the load 140 may include a DC load and / or an AC load. Figure 1 The grid architecture 110 in the illustrated microgrid may also be connected to a main grid 150 so as to be used in parallel with the main grid 150 in some applications. Figure 1 The microgrid shown also includes a microgrid scheduling device 160, which is used to schedule the microgrid according to the state of the microgrid, including adjusting the power generation equipment (such as distributed energy 120), power supply equipment (such as power storage device 130) and power consumption (such as load 140) in the microgrid.

[0029] In some embodiments, the microgrid dispatching device 160 can be specifically implemented as a server, on which a computer program can be run to implement the function of dispatching the microgrid. It should be understood that the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that can provide basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, and middleware services.

[0030] See also Figure 2 And see also Figure 1 ,in, Figure 2 A microgrid scheduling method according to an exemplary embodiment of the present disclosure is schematically illustrated in the form of a flow chart. Figure 2 As shown, the microgrid scheduling method 300 may include steps 310, 320, 330, 340 and 350:

[0031] In step 310, real-time data of a microgrid status of the microgrid is obtained;

[0032] In step 320, a microgrid state prediction data sequence of the microgrid in a prediction time series is determined based on the real-time data of the microgrid state using a time series prediction model;

[0033] In step 330, based on the microgrid state prediction data sequence and the value set of the control variable, the preset differentiable utility function is optimized to determine the dispatch strategy, wherein the dispatch strategy includes the optimized value sequence of the control variable in the prediction time series;

[0034] At step 340, based on the differentiable utility function, the time series prediction model and the optimized value sequence of the control variable, the model parameters of the time series prediction model are adjusted; and

[0035] In step 350, the microgrid is scheduled based on the scheduling strategy.

[0036] The real-time data of the microgrid status acquired in step 310 reflects the current state of the microgrid, which may include, for example, power consumption data, power generation data, load demand data, and stored power data of the microgrid, etc. In some embodiments, the real-time data of the microgrid status may also include real-time data reflecting the environmental status, such as the ambient temperature.

[0037] After acquiring the real-time data of the microgrid status, in step 320, a time series prediction model is used to determine the microgrid status prediction data sequence of the microgrid in the prediction time series. The time series prediction model can be any suitable prediction model, as long as it can determine the prediction data about the status of the microgrid in the future period of time based on the acquired real-time data. In some embodiments, the time series prediction model may include a neural network prediction model that has been pre-trained using existing microgrid status data. As an example, the neural network prediction model may include a multi-layer perceptron (MLP) neural network structure, but it should be understood that any other suitable type of neural network structure is also possible. In addition, for the time series prediction model, such a data model can be used for description, that is, for the input sequence Z, it generates a corresponding output sequence Among them, the model parameter of the time series prediction model is θ, and the output sequence is It represents the predicted data of the state of the microgrid in the future.

[0038] After obtaining the predicted data of the state of the microgrid in the future, these predictions can be used in the decision-making problem of microgrid scheduling to generate the required scheduling strategy. Therefore, in step 330, based on the microgrid state prediction data sequence and the value set of the control variable, the preset differentiable utility function is optimized to determine the scheduling strategy. It should be understood that the differentiable utility function can be constructed according to actual needs, and the optimization target can also be set according to actual needs. For example, it can be set to minimize the sum of time-of-use electricity prices, or it can be set to maximize the power generation efficiency of distributed energy, or it can be set to meet specific electricity consumption requirements, etc. The present disclosure does not impose any restrictions on the specific construction of the differentiable utility function and the specific setting of the optimization target.

[0039] See also Figure 3 See also Figure 2 ,in, Figure 3 According to an exemplary embodiment of the present disclosure, the details of step 330 in the microgrid scheduling method 300 are further shown. Figure 3 As shown, step 330 in the microgrid scheduling method 300 may further include:

[0040] In step 331, under preset constraints, the minimum value of the differentiable utility function is determined; and

[0041] In step 332, the value sequence of the control variable corresponding to when the differentiable utility function takes the minimum value is determined as the optimized value sequence of the control variable in the predicted time series.

[0042] Figure 3 The optimization shown for the preset differentiable utility function can be described as the following linear programming mathematical model:

[0043]

[0044] The following constraints are met:

[0045]

[0046] Among them, a represents the control variable, represents the microgrid state prediction data sequence output by the time series prediction model, represents the preset differentiable utility function, a * represents the optimal value sequence of the control variable a. Therefore, the above equations 1 to 3 essentially describe the differentiable utility function under the constraints expressed by equations 2 and 3. Optimize (e.g., perform linear programming) to determine the optimal value sequence a that minimizes the differentiable utility function * .

[0047] In one embodiment, for the decision-making problem of microgrid scheduling, the following linear programming mathematical model can be constructed:

[0048]

[0049] The following constraints are met:

[0050] P t+k ≥x t+k ·C+y t+k ·C+L t+k -G t+k , k=1,2....,T Formula 5

[0051] D(≥P t+k , k = 1, 2, ..., T Formula 6

[0052] P t+k ≥0, k1, 2, ..., T Formula 7

[0053] soc t+k =soc t+k-1 +x t+k ·η c +y t+k ·η d , k = 1, 2, ..., T Formula 8

[0054] 0≤soc t+k ≤1, k=1, 2, ..., T Formula 9

[0055] 0≤x t+k ≤1, k=1, 2, ..., T Formula 10

[0056] -1≤y t+k ≤0, k=1, 2...., T Formula 11

[0057] x t+k ∈X,y t+k ∈Y, k=1, 2...., T Formula 12

[0058] Equation 4 in the above formula is a differentiable utility function, p t+k represents the electricity price at time k, P t+k represents the net power consumption at time k, DC represents the preset maximum net power consumption, λ is a hyperparameter that can be set according to experience and actual needs, X represents the value set of the battery charging control variable as a control variable, and Y represents the value set of the battery discharging control variable as a control variable. Therefore, the differentiable utility function of formula 4 represents the sum of the preset maximum net power consumption and the total time-sharing cost in the predicted time series.

[0059] In formula 5, C represents the battery power, xt+k represents the value of the battery charging control variable at time k, y t+k represents the value of the battery discharge control variable at time k, L t+k represents the load demand at time k, G t+k represents the power generation of distributed energy at time k. Therefore, Equation 5 ensures that the net power consumption at each time k meets the power consumption demand of the microgrid.

[0060] Equation 6 stipulates that the preset maximum net power consumption must be greater than or equal to the net power consumption during the forecast period.

[0061] Equation 7 stipulates that the net power consumption at time k must be non-negative.

[0062] In formula 8, soc t+k Represents the battery power status at time k, parameter η c is a hyperparameter related to the battery charging control variable, and the parameter η d are hyperparameters related to the battery discharge control variables. Both hyperparameters can be set based on experience and actual needs. Therefore, Equation 8 describes the dynamic changes of the battery power state in the predicted time series.

[0063] Equation 9 specifies the battery state of charge soc t+k The value range of the battery charging control variable x is specified in formula 10. t+k The value range of the battery discharge control variable y is specified in formula 11. t+k The value range of .

[0064] Equation 12 represents the battery charging control variable x t+k and battery discharge control variable y t+k In the value sets X and Y of the control variable respectively.

[0065] Based on the above linear programming model, the differentiable utility function represented by Equation 4 is set to take the minimum value in the predicted time series, thereby determining the battery charging control variable x t+k and battery discharge control variable y t+k The optimized value sequence in the predicted time series can then determine a scheduling strategy based on the optimized value sequence to schedule the microgrid.

[0066] See also Figure 4 See also Figure 2 ,in, Figure 4 According to an exemplary embodiment of the present disclosure, the details of step 340 in the microgrid scheduling method 300 are further shown. Figure 4 As shown, step 340 in the microgrid scheduling method 300 may further include:

[0067] In step 341, the optimized value sequence and the microgrid state prediction data sequence are both substituted into the differentiable utility function to generate a differentiable utility function corresponding to the optimized value sequence;

[0068] At step 342, based on the differentiable utility function corresponding to the optimized value sequence, the derivatives of the model parameters of the time series prediction model are determined;

[0069] In step 343, the model parameters are adjusted based on the derivatives of the model parameters.

[0070] See also Figure 5 See also Figure 4 ,in, Figure 4 The process of adjusting the model parameters of the time series prediction model in the microgrid dispatching method according to the present disclosure is schematically shown in the form of a block diagram. Figure 5 As shown, in process 500, for the input sequence Z, it passes through the time series prediction model f in the prediction process 510 θ (where the model parameter is θ) to generate the corresponding microgrid state prediction data sequence (Right now ), microgrid state prediction data series Subsequently, it can be used to generate a dispatch strategy in the decision process 520, wherein the linear programming mathematical model represented by equations 1 to 3 is used to determine the optimized value sequence a* representing the control variable a; the optimized value sequence a* can be used to adjust the model parameter θ of the time series prediction model in the parameter adjustment process 530, wherein the optimized value sequence a* and the microgrid state prediction data sequence is substituted into the differentiable utility function J to generate a differentiable utility function corresponding to the optimized value sequence Based on the differentiable utility function corresponding to the optimal value sequence Determine the derivative of the model parameter θ of the time series forecasting model Based on the derivative of the model parameter, the model parameter θ is adjusted (for example, the model parameter θ at the next moment may be: Among them, the parameter γ is a hyperparameter, which can be set according to experience and actual needs). In the above process, the derivative of the model parameter θ of the time series prediction model is It can be calculated using the chain rule as follows:

[0071]

[0072] Where J is a differentiable utility function, a* represents the optimal value sequence of the control variable a, represents the microgrid state prediction data sequence, and θ is the model parameter of the time series prediction model.

[0073] Therefore, according to the microgrid dispatching method disclosed in the present invention, a combination of prediction model and differentiable optimization technology is adopted to realize an end-to-end optimization process, in which the time series prediction model is responsible for predicting power generation and load demand, and the model parameters of the time series prediction model are adjusted and optimized according to the final utility function feedback to ensure that the optimal balance between cost efficiency, environmental protection and system safety is achieved in a variable operating environment. Through the differentiable utility function, the parameters of the time series prediction model are optimized and adjusted, and the accuracy of the prediction in the decision-making system can be significantly improved. Accurate prediction enables the microgrid to more effectively foresee future power demand and power generation, so as to make more reasonable scheduling decisions, which can directly affect the system to effectively manage peak and valley power, reduce energy waste, and optimize resource allocation. In addition, accurate prediction and effective resource management not only help to reduce energy waste, but also increase the utilization rate of renewable energy (such as photovoltaic power generation), and support the green development of microgrids. By optimizing the use of renewable energy, microgrids can reduce dependence on fossil fuels, reduce carbon emissions, and promote environmental sustainable utilization and development.

[0074] See also Figure 6 , which schematically illustrates a microgrid dispatching device according to an exemplary embodiment of the present disclosure in the form of a block diagram. Figure 6 As shown, the microgrid dispatching device 700 may include: a data collection module 710, a prediction module 720, a decision module 730, a parameter adjustment module 740 and an execution module 750. Specifically, the data collection module 710 may be configured to: obtain the real-time data of the microgrid state of the microgrid; the prediction module 720 may be configured to: determine the microgrid state prediction data sequence in the microgrid using the time series prediction model based on the real-time data of the microgrid state; the decision module 730 may be configured to: optimize the preset differentiable utility function based on the microgrid state prediction data sequence and the value set of the control variable, and determine the dispatching strategy, wherein the dispatching strategy includes the optimized value sequence of the control variable in the predicted time series; the parameter adjustment module 740 may be configured to: adjust the model parameters of the time series prediction model based on the differentiable utility function, the microgrid state prediction data sequence and the optimized value sequence of the control variable; the execution module 750 may be configured to: dispatch the microgrid based on the dispatching strategy. The microgrid scheduling device 700 may apply the microgrid scheduling method 300 and the steps in its various exemplary embodiments described in detail above.

[0075] Therefore, the microgrid dispatching device 700 of the exemplary embodiment of the present invention adopts a combination of prediction model and differentiable optimization technology to realize an end-to-end optimization process, in which the time series prediction model is responsible for predicting power generation and load demand, and adjusting and optimizing the model parameters of the time series prediction model according to the final utility function feedback can ensure the optimal balance between cost efficiency, environmental protection and system safety in a changing operating environment.

[0076] In some embodiments, the time series prediction model in the prediction module 720 may include a neural network prediction model pre-trained using existing microgrid state data, and the neural network prediction model is configured to: receive the real-time data of the microgrid state, and generate the microgrid state prediction data sequence based on the real-time data of the microgrid state. In some embodiments, the differentiable utility function includes summing the maximum net power consumption and the total time-sharing cost preset in the prediction time series (such as the utility function shown in the previous formula 4), and the control variables include the battery charging control variable and the battery discharging control variable at each moment in the prediction time series. Therefore, the decision module 730 can also be configured to: determine the minimum value of the differentiable utility function under preset constraints, and determine the value sequence of the control variable corresponding to the minimum value of the differentiable utility function as the optimized value sequence of the control variable in the predicted time series, wherein the preset constraints include: the net power consumption at each moment meets the power consumption demand of the microgrid and is less than the maximum net power consumption; the value of the battery charging control variable is greater than or equal to 0 and less than or equal to 1, and the value of the battery discharging control variable is greater than or equal to -1 and less than or equal to 0. In addition, in some embodiments, the parameter adjustment module 740 can also be configured to: substitute the optimized value sequence and the microgrid state prediction data sequence into the differentiable utility function to generate a differentiable utility function corresponding to the optimized value sequence; determine the derivatives of the model parameters of the time series prediction model based on the differentiable utility function corresponding to the optimized value sequence; and adjust the model parameters based on the derivatives of the model parameters.

[0077] It should be understood that Figure 6The various modules shown in the microgrid scheduling method 300 described above and the operations of the corresponding steps in the method of each exemplary embodiment thereof are respectively related to the operations of the corresponding steps in the method, and thus will not be repeated here. In addition, each module described in the present disclosure can be implemented in hardware or in hardware in combination with software and / or firmware. For example, these modules can be implemented as computer executable code / instructions, which can be configured to be executed in one or more processors and stored in a computer-readable storage medium. Alternatively, these modules can be implemented as hardware logic / circuits. As a non-limiting example, one or more of these modules can be implemented in a system on chip (SoC). The SoC may include an integrated circuit chip (which includes a processor (e.g., a central processing unit, a microcontroller, a microprocessor, a digital signal processor, etc.), a memory, one or more communication interfaces, and / or one or more components in other circuits), and may optionally execute the received program code and / or include embedded firmware to perform functions.

[0078] See also Figure 7 , which schematically shows the structure of a computer device according to an exemplary embodiment of the present disclosure. Figure 7 As shown, the computer device 900 can be used in various exemplary embodiments described in the present disclosure, and can implement the microgrid scheduling method 300 described in the present disclosure and the steps in the methods of various exemplary embodiments thereof.

[0079] The computer device 900 may include at least one processor 902, memory 904, communication interface(s) 906, a display device 908, other input / output (I / O) devices 910, and one or more mass storage devices 912 that can communicate with each other, such as via a system bus 914 or other appropriate connection.

[0080] The processor 902 may be a single processing unit or multiple processing units, all of which may include a single or multiple computing units or multiple cores. The processor 902 may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuits, and / or any device that manipulates signals based on operating instructions. Among other capabilities, the processor 902 may be configured to obtain and execute computer-readable instructions stored in the memory 904, mass storage device 912, or other computer-readable storage media, such as program codes of an operating system 916, program codes of an application program 918, program codes of other programs 920, and the like.

[0081] The memory 904 and the mass storage device 912 are examples of computer-readable storage media for storing instructions that can be executed by the processor 902 to implement the various functions described above. For example, the memory 904 can generally include both volatile memory and non-volatile memory (e.g., RAM, ROM, etc.). In addition, the mass storage device 912 can generally include a hard drive, a solid-state drive, a removable medium, including external and removable drives, a memory card, a flash memory, a floppy disk, an optical disk (e.g., CD, DVD), a storage array, a network attached storage, a storage area network, etc. The memory 904 and the mass storage device 912 can all be collectively referred to herein as computer-readable memory or computer-readable storage media, and can be a non-transitory medium capable of storing computer-readable, processor-executable program instructions as computer-executable code, which can be executed by the processor 902 as a specific machine configured to implement the operations and functions described in the exemplary embodiments of the present disclosure.

[0082] A plurality of program modules may be stored on the mass storage device 912. These program modules may include an operating system 916, one or more application programs 918, other programs 920, and program data 922, and they may be executed by the processor 902. Examples of such applications or program modules may include, for example, computer program logic (e.g., computer executable code or instructions) for implementing the following components / functions, namely: data collection module 710, prediction module 720, decision module 730, parameter adjustment module 740, and execution module 750.

[0083] Although in Figure 7904 of the computer device 900, but the above modules or parts thereof can be implemented using any form of computer-readable storage media accessible by the computer device 900. As used herein, "computer-readable storage media" includes at least two types of computer-readable storage media, namely computer storage media and communication media. Computer storage media include volatile and non-volatile, removable and non-removable media implemented by any method or technology for storing information, such as computer-readable instructions, data structures, program modules or other data. Computer storage media include but are not limited to RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD), or other optical storage devices, magnetic cassettes, tapes, disk storage devices or other magnetic storage devices, or any other non-transmission media that can be used to store information for access by a computing device. In contrast, communication media can specifically implement computer-readable instructions, data structures, program modules or other data in modulated data signals such as carrier waves or other transmission mechanisms. The computer storage media defined in the present disclosure do not include communication media.

[0084] The computer device 900 may also include one or more communication interfaces 906 for exchanging data with other devices, such as through a network, direct connection, etc. The communication interface 906 may facilitate communication within a variety of network and protocol types, including wired networks (e.g., LAN, cable, etc.) and wireless networks (e.g., WLAN, cellular, satellite, etc.), the Internet, etc. The communication interface 906 may also provide for communication with external storage devices (not shown), such as in a storage array, network attached storage, storage area network, etc.

[0085] In some examples, the computer device 900 may also include a display device 908 such as a display for displaying information and images. Other I / O devices 910 may be devices that receive various inputs from a target object and provide various outputs to the target object, including but not limited to a touch input device, a gesture input device, a camera, a keyboard, a remote control, a mouse, a printer, an audio input / output device, and the like.

[0086] The present disclosure also relates to a computer-readable storage medium, which is configured to store computer-executable instructions, which are configured to, when executed on a processor, cause the processor to perform the microgrid scheduling method described in each exemplary embodiment of the present disclosure. It should be understood that the computer-readable storage medium should be any suitable storage medium, including but not limited to RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD), or other optical storage device, magnetic cassette, tape, disk storage device or other magnetic storage device, or semiconductor medium (such as a solid state drive), or any other non-transmission medium that can be used to store information for access by a computing device. The present disclosure does not impose any restrictions on computer-readable storage media.

[0087] In addition, the present disclosure also relates to a computer program product, which includes computer executable instructions, and the computer executable instructions are configured to, when executed on a processor, cause the processor to execute the microgrid scheduling method according to each exemplary embodiment of the present disclosure.

[0088] When implemented using software, the microgrid dispatching method according to the present disclosure can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to each exemplary embodiment of the present disclosure is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) mode.

[0089] The terms used in this disclosure are only used to describe the embodiments in the present disclosure and are not intended to limit the present disclosure. As used in this disclosure, the singular forms "one", "an" and "the" are intended to also include plural forms, unless the context clearly indicates otherwise. It is also to be understood that the terms "include" and "comprise" when used in this disclosure refer to the presence of the features described, but do not exclude the presence of one, one or more other features or add one or more other features. As used in this disclosure, the term "and / or" includes any and all combinations of one or more of the associated listed items. It will be understood that although the terms "first", "second", "third", etc. can be used to describe various features in the present disclosure, these features should not be limited by these terms. These terms are only used to distinguish one feature from another feature.

[0090] Unless otherwise defined, all terms (including technical and scientific terms) used in this disclosure have the same meaning as commonly understood by those of ordinary skill in the art to which this disclosure belongs. It is also understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the relevant art and / or the context of this specification, and will not be interpreted in an idealized or overly formal sense unless explicitly defined in this disclosure.

[0091] In the description of this specification, the description of the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present disclosure. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradicting each other and without violating technical principles, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, or may omit some technical features from the different embodiments or examples described in this specification, and the embodiments or examples obtained based on such combination, combination or omission are also considered to fall within the scope of the present disclosure.

[0092] The method described in the present disclosure includes one or more steps or actions. These method steps and / or actions do not have to be performed in the order described in the present disclosure, but can be performed in a different order, for example, they can be performed simultaneously or in a reverse order, as long as they do not conflict with the principle of the technical solution described in the present disclosure. In addition, according to actual needs, the steps or actions in the method described in the present disclosure can be replaced with different steps or actions, or can also include additional steps or actions.

[0093] Although the present disclosure has been described in detail in conjunction with some exemplary embodiments, it is not to be limited to the specific forms described in the present disclosure. Rather, the scope of the present disclosure is limited only by the appended claims.

Claims

1. A microgrid dispatching method, characterized in that: include: Obtain real-time data of microgrid status of microgrid; Determine a microgrid state prediction data sequence of the microgrid in a prediction time sequence based on the real-time data of the microgrid state using a time series prediction model; Based on the microgrid state prediction data sequence and the value set of the control variable, the preset differentiable utility function is optimized to determine the dispatch strategy, wherein the dispatch strategy includes the optimized value sequence of the control variable in the prediction time series; Adjusting the model parameters of the time series prediction model based on the differentiable utility function, the microgrid state prediction data sequence and the optimized value sequence of the control variable; The microgrid is scheduled based on the scheduling strategy.

2. The microgrid dispatching method according to claim 1, characterized in that: The step of optimizing a preset differentiable utility function based on the microgrid state prediction data sequence and the value set of the control variable to determine the scheduling strategy includes: Under preset constraints, determining the minimum value of the differentiable utility function; The value sequence of the control variable corresponding to when the differentiable utility function takes a minimum value is determined as the optimized value sequence of the control variable in the predicted time series.

3. The microgrid dispatching method according to claim 2, characterized in that: The differentiable utility function includes summing the maximum net power consumption and the total time-sharing cost preset in the predicted time series; The control variables include a battery charging control variable and a battery discharging control variable at each moment in the prediction time series; The preset constraints include: The net power consumption at each moment in the predicted time series meets the preset power consumption demand of the microgrid and is less than the preset maximum net power consumption; The value of the battery charging control variable is greater than or equal to 0 and less than or equal to 1, and the value of the battery discharging control variable is greater than or equal to -1 and less than or equal to 0.

4. The microgrid dispatching method according to claim 1, characterized in that: The time series prediction model includes a neural network prediction model pre-trained using existing microgrid status data; The method of determining the microgrid state prediction data sequence of the microgrid in the prediction time series based on the microgrid state real-time data using a time series prediction model includes: inputting the microgrid state real-time data into the neural network prediction model to generate the microgrid state prediction data sequence.

5. The microgrid dispatching method according to claim 1, characterized in that: The adjusting of the model parameters of the time series prediction model based on the differentiable utility function, the microgrid state prediction data sequence and the optimized value sequence of the control variable comprises: Substituting the optimized value sequence and the microgrid state prediction data sequence into the differentiable utility function to generate a differentiable utility function corresponding to the optimized value sequence; Determining derivatives of model parameters of the time series prediction model based on a differentiable utility function corresponding to the optimized value sequence; Based on the derivatives of the model parameters, the model parameters are adjusted.

6. The microgrid dispatching method according to claim 1, characterized in that: The microgrid real-time status information includes power consumption data, power generation data, load demand data and stored power data of the microgrid.

7. The microgrid dispatching method according to claim 6, characterized in that: The microgrid real-time status information also includes ambient temperature data.

8. A microgrid dispatching device, characterized in that: include: A data collection module is configured to: obtain real-time data of a microgrid status of the microgrid; A prediction module is configured to: determine a microgrid state prediction data sequence in the microgrid using a time series prediction model based on the microgrid state real-time data; A decision module, configured to: optimize a preset differentiable utility function based on the microgrid state prediction data sequence and a set of control variable values, and determine a dispatch strategy, wherein the dispatch strategy includes an optimized value sequence of the control variable in the prediction time series; A parameter adjustment module, configured to: adjust the model parameters of the time series prediction model based on the differentiable utility function, the microgrid state prediction data sequence and the optimized value sequence of the control variable; An execution module is configured to: schedule the microgrid based on the scheduling strategy.

9. The microgrid dispatching device according to claim 8, characterized in that: The time series prediction model in the prediction module includes a neural network prediction model pre-trained using existing microgrid status data, and the neural network prediction model is configured to: receive the real-time data of the microgrid status, and generate the microgrid status prediction data sequence based on the real-time data of the microgrid status.

10. The microgrid dispatching device according to claim 8, characterized in that: The parameter adjustment module is also configured to: Substituting the optimized value sequence and the microgrid state prediction data sequence into the differentiable utility function to generate a differentiable utility function corresponding to the optimized value sequence; Determining derivatives of model parameters of the time series prediction model based on a differentiable utility function corresponding to the optimized value sequence; Based on the derivatives of the model parameters, the model parameters are adjusted.

11. The microgrid dispatching device according to claim 8, characterized in that: The differentiable utility function includes summing the maximum net power consumption and the total time-sharing cost preset in the predicted time series; The control variables include a battery charging control variable and a battery discharging control variable at each moment in the prediction time series; The decision module is also configured to: determine the minimum value of the differentiable utility function under preset constraints, and determine the value sequence of the control variable corresponding to the minimum value of the differentiable utility function as the optimized value sequence of the control variable in the predicted time series, wherein the preset constraints include: the net power consumption at each moment meets the power consumption demand of the microgrid and is less than the maximum net power consumption; the value of the battery charging control variable is greater than or equal to 0 and less than or equal to 1, and the value of the battery discharging control variable is greater than or equal to -1 and less than or equal to 0.

12. A computer device comprising a memory, a processor and computer instructions stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the microgrid scheduling method according to any one of claims 1 to 7.

13. A computer-readable storage medium having computer instructions stored thereon, characterized in that: When the computer instructions are executed by the processor, the steps of the microgrid scheduling method according to any one of claims 1 to 7 are implemented.

14. A computer program product comprising computer instructions, characterized in that When the computer instructions are executed by the processor, the steps of the microgrid scheduling method according to any one of claims 1 to 7 are implemented.

Images