A park microgrid optimization control method based on real-time state judgment

Abstract

The present invention discloses a park microgrid optimization control method based on real-time state judgment, which relates to the field of microgrid control technology. The method includes: constructing a prediction algorithm library of commonly used algorithms, determining the optimal prediction algorithm for predicting photovoltaic power generation and park power consumption, determining the photovoltaic power generation power prediction value and the park power consumption prediction value in the current cycle unit according to a first fixed period; constructing an optimization scheduling model corresponding to the current cycle unit based on the park photovoltaic power generation and power consumption prediction values ​​in each cycle of the current cycle unit, and determining the minimum cost scheduling plan corresponding to the daily scheduling plan in combination with the scheduling cost and constraint conditions; judging the operating state of the park microgrid according to the real-time data of the voltage at the park microgrid grid connection point according to the second fixed period, and determining the optimization control plan according to the operating state. The present invention can significantly improve the operating economy and safety of the microgrid under a wide range of working conditions.

Description

Technical Field

[0001] The present invention relates to the field of microgrid control technology, and in particular to a campus microgrid optimization control method based on real-time status judgment. Background Art

[0002] The widespread adoption of distributed photovoltaic, wind, and other renewable energy sources on the user side has introduced a series of issues, such as volatility and uncertainty, into user-side microgrids, severely impacting their operational economics and safety. Current research in microgrid control focuses on leveraging user-side energy storage for joint optimization and control, mitigating the impact of uncertainty from renewable energy sources like wind and solar, and improving system economics.

[0003] However, current optimization control methods are usually only designed for a certain type of operating state, and it is difficult to adjust the optimization control algorithm according to the different operating states of the user-side microgrid, and thus it is difficult to achieve optimal operation of the global operating conditions. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to address the deficiencies of the existing technology and specifically provide a campus microgrid optimization control method based on real-time status judgment, which is as follows:

[0005] 1) In the first aspect, the present invention provides a method for optimizing and controlling a campus microgrid based on real-time status judgment. The specific technical solution is as follows:

[0006] Construct a prediction algorithm library of commonly used algorithms, and use one day as a cycle unit. Determine, in the prediction algorithm library, based on the previous cycle unit, the optimal prediction algorithm for predicting the photovoltaic power generation power and the park power consumption in the current cycle unit, and determine the photovoltaic power generation power prediction value and the park power consumption prediction value in each cycle of the current cycle unit according to the first fixed period;

[0007] Based on the predicted values ​​of photovoltaic power generation and park power consumption in each cycle of the current cycle unit, an optimization scheduling model corresponding to the current cycle unit is constructed, and the minimum cost scheduling plan corresponding to the daily scheduling plan is determined in combination with the scheduling cost and constraints, where the scheduling cost is determined by the predicted values ​​of photovoltaic power generation and park power consumption in each cycle of the current cycle unit;

[0008] The daily scheduling plan is executed, and according to the second fixed period, the operating status of the park microgrid is judged according to the real-time data of the voltage at the park microgrid grid connection point, and the optimal control plan is determined according to the operating status.

[0009] The beneficial effects of the park microgrid optimization control method based on real-time status judgment provided by the present invention are as follows:

[0010] Collecting real-time data on the voltage at the microgrid's grid connection point, judging the microgrid's current operating status every second fixed period, and selecting different optimization control schemes based on the status judgment results can significantly improve the microgrid's operating economy and safety under a wide range of working conditions.

[0011] Based on the above solution, the present invention can also be improved as follows.

[0012] Furthermore, the process of determining the optimal prediction algorithm for predicting the photovoltaic power generation and the park power consumption in the current cycle unit is specifically as follows:

[0013] Call all commonly used algorithms in the prediction algorithm library, and in the previous cycle unit, determine multiple first photovoltaic power generation power prediction values ​​and multiple first park electricity consumption prediction values ​​obtained by calculating and processing different commonly used algorithms in each first fixed period, determine the photovoltaic prediction accuracy based on the multiple first photovoltaic power generation power prediction values ​​under any commonly used algorithm, and determine the electricity consumption prediction accuracy based on the multiple first park electricity consumption prediction values ​​under any commonly used algorithm, and use the commonly used algorithm corresponding to the maximum value of all photovoltaic prediction accuracies as the optimal prediction algorithm for predicting photovoltaic power in the current cycle unit, and use the commonly used algorithm corresponding to the maximum value of all electricity consumption prediction accuracies as the optimal prediction algorithm for predicting park electricity consumption in the current cycle unit.

[0014] Furthermore, the dispatching cost includes: life loss cost, the cost of purchasing electricity from the power grid for the park, and the operating cost of the distributed photovoltaic system in the park.

[0015] Furthermore, the constraints include: power balance constraints, energy storage battery charge and discharge constraints, energy storage battery SOC constraints, and tie line power constraints.

[0016] Furthermore, the specific process of judging the operating status of the park microgrid based on the real-time data of the voltage at the park microgrid grid connection point is as follows:

[0017] when or When , it is determined that the operating state of the park microgrid is the first operating state;

[0018] when Furthermore, when the photovoltaic prediction accuracy and the power consumption prediction accuracy in the current cycle unit meet the first preset condition, the operation state of the park microgrid is determined to be the second operation state;

[0019] when Furthermore, when the photovoltaic prediction accuracy and the power consumption prediction accuracy in the current cycle unit meet the second preset condition, it is determined that the operation state of the park microgrid is the third operation state;

[0020] Among them, U is the real-time data of voltage, and U0 is the reference value of voltage.

[0021] Furthermore, the optimized control scheme is determined according to the operating state as follows:

[0022] When the operating state is the first operating state, the optimization control scheme is specifically a constant voltage combined control scheme;

[0023] When the operating state is the second operating state, the optimization control scheme is specifically an MPPT maximum power tracking control scheme, and the energy storage battery is controlled based on the day-ahead optimization scheduling curve of the energy storage battery;

[0024] When the operating state is the third operating state, the optimization control scheme is specifically an MPPT maximum power tracking control scheme, and the energy storage battery is controlled based on the improved energy storage battery day-ahead optimization scheduling curve.

[0025] 2) In a second aspect, the present invention further provides a campus microgrid optimization control system based on real-time status judgment, the specific technical solution of which is as follows:

[0026] The construction module is used to: construct a prediction algorithm library of commonly used algorithms, and use one day as a cycle unit, determine the optimal prediction algorithm for predicting the photovoltaic power generation power and the park power consumption in the current cycle unit based on the previous cycle unit in the prediction algorithm library, and determine the photovoltaic power generation power prediction value and the park power consumption prediction value in each cycle of the current cycle unit according to the first fixed period;

[0027] The calculation module is used to: construct an optimization scheduling model corresponding to the current cycle unit based on the predicted values ​​of photovoltaic power generation and park power consumption in each cycle of the current cycle unit, and determine the minimum cost scheduling plan corresponding to the daily scheduling plan in combination with the scheduling cost and constraints, where the scheduling cost is determined by the predicted values ​​of photovoltaic power generation and park power consumption in each cycle of the current cycle unit;

[0028] The control module is used to: execute the daily scheduling plan, and according to the second fixed period, judge the operating status of the park microgrid based on the real-time data of the voltage of the park microgrid grid connection point, and determine the optimal control plan based on the operating status.

[0029] 3) In a third aspect, the present invention further provides an electronic device, comprising a processor, wherein the processor is coupled to a memory, wherein at least one computer program is stored in the memory, and the at least one computer program is loaded and executed by the processor so that the electronic device implements any of the above methods.

[0030] 4) In a fourth aspect, the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores at least one computer program, and the at least one computer program is loaded and executed by a processor to enable a computer to implement any of the above methods.

[0031] It should be noted that the beneficial effects achieved by the technical solutions of the second to fourth aspects of the present invention and the corresponding possible implementation methods can be found in the above-mentioned technical effects of the first aspect and its corresponding possible implementation methods, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Other features, objects and advantages of the present invention will become more apparent upon reading the detailed description of non-limiting embodiments made with reference to the following drawings:

[0033] Figure 1 This is a flow chart of a method for optimizing and controlling a campus microgrid based on real-time status judgment according to an embodiment of the present invention;

[0034] Figure 2 A schematic structural diagram of a campus microgrid according to a campus microgrid optimization control method based on real-time status judgment according to an embodiment of the present invention;

[0035] Figure 3 This is a second flow chart of a campus microgrid optimization control method based on real-time status judgment according to an embodiment of the present invention;

[0036] Figure 4 This is a structural framework diagram of an electronic device. DETAILED DESCRIPTION

[0037] To make the objectives, technical solutions and advantages of the present invention more clear, the embodiments of the present invention will be described in further detail below with reference to the accompanying drawings.

[0038] like Figure 1 As shown, a campus microgrid optimization control method based on real-time status judgment according to an embodiment of the present invention includes the following steps:

[0039] Step 1: Build a prediction algorithm library of commonly used algorithms, and use one day as a cycle unit. Based on the previous cycle unit, determine the optimal prediction algorithm for predicting the photovoltaic power generation power and the park power consumption in the current cycle unit in the prediction algorithm library, and determine the predicted value of the photovoltaic power generation power and the predicted value of the park power consumption in each cycle of the current cycle unit according to the first fixed period.

[0040] Step 2: Based on the predicted values ​​of photovoltaic power generation and park power consumption in each cycle of the current cycle unit, an optimization scheduling model corresponding to the current cycle unit is constructed, and the minimum cost scheduling plan corresponding to the daily scheduling plan is determined in combination with the scheduling cost and constraints, where the scheduling cost is determined by the predicted values ​​of photovoltaic power generation and park power consumption in each cycle of the current cycle unit;

[0041] Step 3: execute the daily scheduling plan, and according to the second fixed period, judge the operating status of the park microgrid based on the real-time data of the voltage at the park microgrid grid connection point, and determine the optimal control plan based on the operating status.

[0042] The beneficial effects of the park microgrid optimization control method based on real-time status judgment provided by the present invention are as follows:

[0043] Collecting real-time data on the voltage at the microgrid's grid connection point, judging the microgrid's current operating status every second fixed period, and selecting different optimization control schemes based on the status judgment results can significantly improve the microgrid's operating economy and safety under a wide range of working conditions.

[0044] Commonly used algorithms include: Transformer, LSTM, CNN, GRU, and BP algorithms.

[0045] The process of determining the optimal prediction algorithm for predicting the photovoltaic power generation and the park power consumption in the current cycle unit may include the following schemes:

[0046] The first method is to calculate the photovoltaic prediction accuracy R PV,j And the power consumption prediction accuracy R Load,j The specific calculation formula is:

[0047]

[0048] Wherein, n is the number of accuracy test samples (i.e., the number of parts into which a cycle unit is divided according to the first fixed period); and are the predicted values ​​of photovoltaic output and power consumption obtained by the jth algorithm at time i; j = 1, 2, 3, 4, 5 represent Transformer, LSTM, CNN, GRU, and BP algorithms respectively; y PV,i and y Load,i are the actual measured values ​​of photovoltaic output and power consumption at the i-th moment; Ca PV,i is the photovoltaic startup capacity at the i-th moment.

[0049] Select R PV,j and R Load,j The algorithm with the largest value predicts the photovoltaic power generation and park power consumption on the second day.

[0050] The second method is to call all commonly used algorithms in the prediction algorithm library, and in the previous cycle unit, determine multiple first photovoltaic power generation power prediction values ​​and multiple first park electricity consumption prediction values ​​obtained by calculating and processing different commonly used algorithms in each first fixed period, determine the target photovoltaic power generation power prediction value with the largest value among the multiple first photovoltaic power generation power prediction values, determine the target park electricity consumption prediction value with the largest value among the multiple first park electricity consumption prediction values, and determine the first commonly used algorithm corresponding to the target photovoltaic power generation power prediction value and the second commonly used algorithm corresponding to the target park electricity consumption prediction value, and use the first commonly used algorithm as the optimal prediction algorithm for predicting the photovoltaic power generation power prediction value in the corresponding fixed period in the current cycle unit, and use the second commonly used algorithm as the optimal prediction algorithm for predicting the park electricity consumption prediction value in the corresponding fixed period in the current cycle unit.

[0051] The specific process of determining the predicted value of photovoltaic power generation and the predicted value of park power consumption in each cycle of the current cycle unit according to the first fixed cycle is as follows:

[0052] The prediction model for photovoltaic power generation and park power consumption on the second day is as follows:

[0053]

[0054] Where, to are the predicted values ​​of photovoltaic power generation at 96 consecutive points on the second day; y PV,t-95 to y PV,t The actual measured value of photovoltaic power generation on the first day; x t+1 to x t+96 are the predicted characteristic values ​​of the weather on the second day; f PV,j (·) is R PV,j The algorithm with the largest value. to are the predicted values ​​of the park's power consumption at 96 consecutive points on the second day; y Load,similar is the historical load data similar to the forecast day; f Load,j (·) is R Load,j The algorithm with the largest value.

[0055] The specific process of determining the minimum cost corresponding to the daily scheduling plan based on the scheduling cost is as follows:

[0056] min f=C ES +C Grid +C DG

[0057] in, The life loss cost of the energy storage battery during one charge and discharge cycle, Ccapital_ES is the initial investment cost of the energy storage battery, DOD is the depth of charge and discharge of the energy storage, and g(·) is the correlation function corresponding to DOD; is the cost of purchasing electricity from the power grid for the park, k grid,i is the time-of-use electricity price, P grid,i is the power purchased by the park from the grid the day before, Δt is the strategy execution period, and n is the optimization scheduling execution period; is the operating cost of the park’s distributed power supply (photovoltaic), k OM-PV is the operation and maintenance cost per unit power of photovoltaic cells, is the predicted value of photovoltaic power generation at the i-th moment.

[0058] The specific process of constructing the constraints corresponding to the current cycle unit is:

[0059] Power balance constraints:

[0060] Energy storage battery charging and discharging constraints: P ES,min ≤P ES,i ≤P ES,max

[0061] Energy storage battery SOC constraints: SOC min ≤SOC i ≤SOC max

[0062] Tie line power constraint: P grid,i ≤P grid,max

[0063] Among them, P ES,i is the current charging and discharging power of the energy storage battery, P ES,i >0 means charging, P ES,i <0 means discharge; is the predicted value of the park's power consumption at the i-th moment; P ES,min and P ES,max are the maximum charge and discharge power of the energy storage battery; P grid,max In order to consider the transformer capacity limitation, the maximum power purchase power limit is allowed; SOC i+1 and SOC i are the SOC values ​​of the energy storage battery at time i+1 and time i respectively; η ES E is the charging and discharging efficiency of the energy storage battery; ES,0 is the design capacity of the energy storage battery; SOC min and SOC max They are the upper and lower limits of the SOC allowed for the energy storage battery.

[0064] The specific process of judging the operating status of the park microgrid based on the real-time data of the voltage at the park microgrid grid connection point and determining the optimal control scheme based on the operating status is as follows:

[0065] State 1: Satisfied or At this time, the voltage at the park grid connection point exceeds the upper limit or the voltage exceeds the lower limit;

[0066] State 2: Satisfied And max{R PV,j ,R Load,j >85%. At this point, the grid-connected voltage in the park is normal, and the photovoltaic power generation and power consumption forecasts are highly accurate.

[0067] State three, satisfied And max{R PV,j ,R Load,j}≤85%. At this time, the voltage at the park's grid connection point is normal, but the accuracy of the photovoltaic power generation and park power consumption predictions is low.

[0068] If it is state 1, photovoltaic and energy storage adopt a constant voltage joint control method to eliminate the voltage limit problem at the park grid connection point.

[0069] If it is state 2, the photovoltaic power plant adopts the MPPT maximum power tracking control method, and the energy storage battery adopts the energy storage battery day-ahead optimization scheduling curve for control.

[0070] If it is state three, the photovoltaic power adopts the MPPT maximum power tracking control method, and carries out the energy storage day optimization scheduling calculation based on the energy storage battery day optimization scheduling curve. The energy storage battery uses the result of the day optimization scheduling calculation for control. The energy storage day optimization scheduling model is:

[0071]

[0072] Among them, P grid,i P is the power purchased by the park from the power grid in the past few days; in-grid,i P is the power purchased by the park from the grid during the day; ES,i is the current charging and discharging power of the energy storage battery; P in-ES,i k is the daily charging and discharging power of the energy storage battery; grid,i and k ES,i They are electricity purchase cost and energy storage dispatching and operating cost respectively.

[0073] The constraints of the intraday optimization scheduling model are similar to those of the day-ahead optimization scheduling model.

[0074] Furthermore, the process of determining the optimal prediction algorithm for predicting the photovoltaic power generation and the park power consumption in the current cycle unit is specifically as follows:

[0075] Call all commonly used algorithms in the prediction algorithm library, and in the previous cycle unit, determine multiple first photovoltaic power generation power prediction values ​​and multiple first park electricity consumption prediction values ​​obtained by calculating and processing different commonly used algorithms in each first fixed period, determine the photovoltaic prediction accuracy based on the multiple first photovoltaic power generation power prediction values ​​under any commonly used algorithm, and determine the electricity consumption prediction accuracy based on the multiple first park electricity consumption prediction values ​​under any commonly used algorithm, and use the commonly used algorithm corresponding to the maximum value of all photovoltaic prediction accuracies as the optimal prediction algorithm for predicting photovoltaic power in the current cycle unit, and use the commonly used algorithm corresponding to the maximum value of all electricity consumption prediction accuracies as the optimal prediction algorithm for predicting park electricity consumption in the current cycle unit.

[0076] Furthermore, the dispatching cost includes: life loss cost, the cost of purchasing electricity from the power grid for the park, and the operating cost of the distributed photovoltaic system in the park.

[0077] Furthermore, the constraints include: power balance constraints, energy storage battery charge and discharge constraints, energy storage battery SOC constraints, and tie line power constraints.

[0078] Furthermore, the specific process of judging the operating status of the park microgrid based on the real-time data of the voltage at the park microgrid grid connection point is as follows:

[0079] when or When , it is determined that the operating state of the park microgrid is the first operating state;

[0080] when Furthermore, when the photovoltaic prediction accuracy and the power consumption prediction accuracy in the current cycle unit meet the first preset condition, the operation state of the park microgrid is determined to be the second operation state;

[0081] when Furthermore, when the photovoltaic prediction accuracy and the power consumption prediction accuracy in the current cycle unit meet the second preset condition, it is determined that the operating state of the park microgrid is the third operating state;

[0082] Among them, U is the real-time data of voltage, and U0 is the reference value of voltage.

[0083] Furthermore, the optimized control scheme is determined according to the operating state as follows:

[0084] When the operating state is the first operating state, the optimization control scheme is specifically a constant voltage combined control scheme;

[0085] When the operating state is the second operating state, the optimization control scheme is specifically an MPPT maximum power tracking control scheme, and the energy storage battery is controlled based on the day-ahead optimization scheduling curve of the energy storage battery;

[0086] When the operating state is the third operating state, the optimization control scheme is specifically an MPPT maximum power tracking control scheme, and the energy storage battery is controlled based on the improved energy storage battery day-ahead optimization scheduling curve.

[0087] Example 1, as Figure 2 as well as Figure 3 As shown:

[0088] S1: Build a prediction algorithm library that includes commonly used algorithms such as Transformer, LSTM, CNN, GRU, and BP. At 24:00 on the same day, select the optimal prediction algorithm based on the accuracy of each algorithm for that day's predictions. For 96 points in total, predict the microgrid's photovoltaic power generation and park power consumption from 00:15 to 24:00 the following day, with a 15-minute interval.

[0089] S2: At 24:00 on the same day, considering the life loss cost of energy storage battery charging and discharging, a microgrid day-ahead optimization scheduling model is established. The scheduling curve of the energy storage battery from 01:00 to 24:00 on the second day is calculated using a quantum genetic algorithm, with a total of 24 points;

[0090] S3: On the second day, real-time voltage data at the microgrid connection point is collected. The current operating status of the microgrid is determined every hour. Different optimization control schemes are selected based on the status determination results.

[0091] It should be further explained that the photovoltaic prediction accuracy R PV,j And the power consumption prediction accuracy R Load,j The calculation method and the process of predicting the photovoltaic power generation power of the microgrid and the power consumption of the park from 00:15 to 24:00 on the second day have been explained above and will not be repeated here.

[0092] Furthermore, the objective function of the microgrid day-ahead optimization scheduling in step S2 is:

[0093] min f=C ES +C Grid +C DG

[0094] in, The life loss cost of the energy storage battery during one charge and discharge cycle, C capital_ES is the initial investment cost of the energy storage battery, DOD is the depth of charge and discharge of the energy storage, and g(·) is the correlation function corresponding to DOD; is the cost of purchasing electricity from the power grid for the park, kgrid,i is the time-of-use electricity price, P grid,i is the power purchased by the park from the grid the day before, Δt is the strategy execution period, and n1 is the optimization scheduling execution period; is the operating cost of the park’s distributed power supply (photovoltaic), k OM-PV is the operation and maintenance cost per unit power of photovoltaic cells, is the predicted value of photovoltaic power generation at the i-th moment.

[0095] The constraints have been described above and will not be repeated here.

[0096] The improved balance optimizer algorithm in step S2 is:

[0097] Set the control parameters of the balance optimizer algorithm, including the initial population size Varnum, the maximum number of iterations Max_iter, the global search weight b1, the local search weight b2, the controlled volume v, and the generation rate GP to construct the balance pool:

[0098] C eq,pool ={C eq,1 C eq,2 C eq,3 C eq,4 C eq,5}

[0099] Among them, C eq,pool is the balancing tank; C eq,1 、C eq,2 、C eq,3 、C eq,4 are the four solutions with the best fitness at the current moment; C eq,5 is the average of these four solutions.

[0100] Set the exponential term coefficient F and production rate G:

[0101] F=b1sign(r-0.5)[e -λt -1]

[0102]

[0103] G=G CP (C eq -λC)F

[0104]

[0105] Where b1 is the global search coefficient; sign is the sign function; r is a random value between [0, 1]; e is a natural constant; λ is the flow rate per unit volume; Iter is the current iteration number; Max_iter is the maximum iteration number; b2 is the local search coefficient. Gcp is the production rate control parameter; r1 and r2 are random values ​​between [0, 1]; GP is the generation probability; and C is the sample concentration at the current iteration number.

[0106] Update individual concentration C new :

[0107]

[0108] Among them, C eq is the concentration in the controlled volume at equilibrium, derived from the equilibrium tank C eq,pool Randomly selected data from C new is the concentration of the currently updated example. In the next iteration, let C = C new .

[0109] The operating status in step S3 is defined as follows:

[0110] State 1: Satisfied or At this time, the voltage at the park grid connection point exceeds the upper limit or the voltage exceeds the lower limit;

[0111] State 2: Satisfied And max{R PV,j ,R Load,j >85%. At this point, the grid connection point voltage in the park is normal, and the photovoltaic power generation and park power consumption forecasts are highly accurate.

[0112] State three, satisfied And max{R PV,j ,R Load,j}≤85%. At this time, the voltage at the park's grid connection point is normal, but the accuracy of the photovoltaic power generation and park power consumption predictions is low;

[0113] The selection of different optimization control schemes according to the state judgment results in step S3 is defined as follows:

[0114] S301: If it is state 1, photovoltaic and energy storage adopt a constant voltage joint control method to eliminate the voltage limit problem at the park grid connection point.

[0115] S302: If it is state 2, the photovoltaic power plant adopts the MPPT maximum power tracking control method, and the energy storage battery adopts the energy storage battery day-ahead optimization scheduling curve calculated in S2 for control.

[0116] S303: If it is state 3, the photovoltaic adopts the MPPT maximum power tracking control method, and performs the energy storage day optimization scheduling calculation based on the energy storage battery day optimization scheduling curve. The energy storage battery uses the result of the day optimization scheduling calculation for control. The energy storage day optimization scheduling model is:

[0117]

[0118] Among them, P grid,i P is the power purchased by the park from the power grid in the past few days; in-grid,i P is the power purchased by the park from the grid during the day; ES,i P is the current charging and discharging power of the energy storage battery; in-ES,i k is the daily charging and discharging power of the energy storage battery; grid,i and k ES,i They are electricity purchase cost and energy storage dispatching and operating cost respectively.

[0119] The constraints of the intraday optimization scheduling model are similar to those of the day-ahead optimization scheduling model.

[0120] In the above embodiments, although the steps are numbered S1, S2, etc., these are only specific embodiments given by the present invention. Those skilled in the art may adjust the execution order of S1, S2, etc. according to actual conditions, which is also within the scope of protection of the present invention. It can be understood that in some embodiments, some or all of the above embodiments may be included.

[0121] The present invention also provides a park microgrid optimization control system based on real-time status judgment, and the specific technical solution is as follows:

[0122] The construction module is used to: construct a prediction algorithm library of commonly used algorithms, and use one day as a cycle unit, determine the optimal prediction algorithm for predicting the photovoltaic power generation power and the park power consumption in the current cycle unit based on the previous cycle unit in the prediction algorithm library, and determine the photovoltaic power generation power prediction value and the park power consumption prediction value in each cycle of the current cycle unit according to the first fixed period;

[0123] The calculation module is used to: construct an optimization scheduling model corresponding to the current cycle unit based on the predicted values ​​of photovoltaic power generation and park power consumption in each cycle of the current cycle unit, and determine the minimum cost scheduling plan corresponding to the daily scheduling plan in combination with the scheduling cost and constraints, where the scheduling cost is determined by the predicted values ​​of photovoltaic power generation and park power consumption in each cycle of the current cycle unit;

[0124] The control module is used to: execute the daily scheduling plan, and according to the second fixed period, judge the operating status of the park microgrid based on the real-time data of the voltage of the park microgrid grid connection point, and determine the optimal control plan based on the operating status.

[0125] It should be noted that the beneficial effects of the campus microgrid optimization control system based on real-time status judgment provided by the above embodiment are the same as the beneficial effects of the above-mentioned campus microgrid optimization control method based on real-time status judgment, which will not be repeated here. In addition, when the system provided by the above embodiment realizes its functions, it only uses the division of the above-mentioned functional modules as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the system can be divided into different functional modules according to actual conditions to complete all or part of the functions described above. In addition, the system and method embodiments provided by the above embodiment belong to the same concept. The specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0126] like Figure 4 As shown, an electronic device 300 according to an embodiment of the present invention includes a processor 320, which is coupled to a memory 310. The memory 310 stores at least one computer program 330. The at least one computer program 330 is loaded and executed by the processor 320 to enable the electronic device 300 to implement any of the above methods. Specifically:

[0127] The electronic device 300 may have relatively large differences due to different configurations or performances, and may include one or more processors 320 (Central Processing Units, CPUs) and one or more memories 310, wherein the one or more memories 310 store at least one computer program 330, and the at least one computer program 330 is loaded and executed by the one or more processors 320 to enable the electronic device 300 to implement a campus microgrid optimization control method based on real-time status judgment provided in the above embodiment. Of course, the electronic device 300 may also have components such as a wired or wireless network interface, a keyboard, and an input and output interface for input and output. The electronic device 300 may also include other components for implementing device functions, which will not be described in detail here.

[0128] A computer-readable storage medium according to an embodiment of the present invention stores at least one computer program, and the at least one computer program is loaded and executed by a processor to enable a computer to implement any of the above methods.

[0129] Alternatively, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, or the like.

[0130] In an exemplary embodiment, a computer program product or computer program is also provided, the computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the electronic device to perform any of the above methods.

[0131] It should be noted that the terms "first," "second," and the like in the specification and claims of this application are used to distinguish similar objects and to define a specific order or precedence. Where appropriate, the order used for similar objects may be interchanged, such that the embodiments of the present application described herein can be implemented in an order other than the order shown or described.

[0132] Those skilled in the art will appreciate that the present invention may be implemented as a system, method, or computer program product. Therefore, the present disclosure may be implemented in the following forms: entirely in hardware, entirely in software (including firmware, resident software, microcode, etc.), or in a combination of hardware and software, generally referred to herein as a "circuit," "module," or "system." Furthermore, in some embodiments, the present invention may be implemented in the form of a computer program product embodied in one or more computer-readable media containing computer-readable program code.

[0133] Any combination of one or more computer-readable media can be used. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or component, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media 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 (EPROM 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 this document, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device or device.

[0134] Although the embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and are not to be construed as limitations on the present invention. A person skilled in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A park microgrid optimization control method based on real-time status judgment, characterized in that: include: Construct a prediction algorithm library of commonly used algorithms, and use one day as a cycle unit. Determine, in the prediction algorithm library, based on the previous cycle unit, the optimal prediction algorithm for predicting the photovoltaic power generation power and the park power consumption in the current cycle unit, and determine the photovoltaic power generation power prediction value and the park power consumption prediction value in each cycle of the current cycle unit according to the first fixed period; Based on the predicted values ​​of photovoltaic power generation and park power consumption in each cycle of the current cycle unit, an optimization scheduling model corresponding to the current cycle unit is constructed, and the minimum cost scheduling plan corresponding to the daily scheduling plan is determined in combination with the scheduling cost and constraints, where the scheduling cost is determined by the predicted values ​​of photovoltaic power generation and park power consumption in each cycle of the current cycle unit; Executing the daily scheduling plan, and judging the operating status of the park microgrid according to the real-time data of the voltage at the park microgrid connection point according to the second fixed period, and determining the optimal control plan according to the operating status; The specific process of judging the operating status of the park microgrid based on the real-time data of the voltage at the park microgrid grid connection point is as follows: when or When , it is determined that the operating state of the park microgrid is the first operating state; when Furthermore, when the photovoltaic prediction accuracy and the power consumption prediction accuracy in the current cycle unit meet the first preset condition, the operation state of the park microgrid is determined to be the second operation state; when Furthermore, when the photovoltaic prediction accuracy and the power consumption prediction accuracy in the current cycle unit meet the second preset condition, it is determined that the operation state of the park microgrid is the third operation state; Among them, U is the real-time data of voltage, and U0 is the reference value of voltage; The optimized control scheme is determined according to the operating state as follows: When the operating state is the first operating state, the optimization control scheme is specifically a constant voltage combined control scheme; When the operating state is the second operating state, the optimization control scheme is specifically an MPPT maximum power tracking control scheme, and the energy storage battery is controlled based on the day-ahead optimization scheduling curve of the energy storage battery; When the operating state is the third operating state, the optimization control scheme is specifically an MPPT maximum power tracking control scheme, and the energy storage battery is controlled based on the improved energy storage battery day-ahead optimization scheduling curve.

2. A campus microgrid optimization control method based on real-time status judgment according to claim 1, characterized in that: The process of determining the optimal prediction algorithm for predicting the photovoltaic power generation and the park power consumption in the current cycle unit also includes: Call all commonly used algorithms in the prediction algorithm library, and in the previous cycle unit, determine multiple first photovoltaic power generation power prediction values ​​and multiple first park electricity consumption prediction values ​​obtained by calculating and processing different commonly used algorithms in each first fixed period, determine the photovoltaic prediction accuracy based on the multiple first photovoltaic power generation power prediction values ​​under any commonly used algorithm, and determine the electricity consumption prediction accuracy based on the multiple first park electricity consumption prediction values ​​under any commonly used algorithm, and use the commonly used algorithm corresponding to the maximum value of all photovoltaic prediction accuracies as the optimal prediction algorithm for predicting photovoltaic power in the current cycle unit, and use the commonly used algorithm corresponding to the maximum value of all electricity consumption prediction accuracies as the optimal prediction algorithm for predicting park electricity consumption in the current cycle unit.

3. The method for optimizing and controlling a campus microgrid based on real-time status judgment according to claim 1, characterized in that: The dispatching costs include: life loss costs, the cost of purchasing electricity from the power grid for the park, and the operating costs of the park's distributed photovoltaics.

4. The method for optimizing and controlling a campus microgrid based on real-time status judgment according to claim 1, characterized in that: The constraints include: power balance constraints, energy storage battery charge and discharge constraints, energy storage battery SOC constraints, and tie line power constraints.

5. A campus microgrid optimization control system based on real-time status judgment, adopting the campus microgrid optimization control method based on real-time status judgment according to claim 1, characterized in that: include: The construction module is used to: construct a prediction algorithm library of commonly used algorithms, and use one day as a cycle unit, determine the optimal prediction algorithm for predicting the photovoltaic power generation power and the park power consumption in the current cycle unit based on the previous cycle unit in the prediction algorithm library, and determine the photovoltaic power generation power prediction value and the park power consumption prediction value in each cycle of the current cycle unit according to the first fixed period; The calculation module is used to: construct an optimization scheduling model corresponding to the current cycle unit based on the predicted values ​​of photovoltaic power generation and park power consumption in each cycle of the current cycle unit, and determine the minimum cost scheduling plan corresponding to the daily scheduling plan in combination with the scheduling cost and constraints, where the scheduling cost is determined by the predicted values ​​of photovoltaic power generation and park power consumption in each cycle of the current cycle unit; The control module is used to: execute the daily scheduling plan, and according to the second fixed period, judge the operating status of the park microgrid based on the real-time data of the voltage of the park microgrid grid connection point, and determine the optimal control plan based on the operating status.

6. A campus microgrid optimization control system based on real-time status judgment according to claim 5, characterized in that: The process of determining the optimal prediction algorithm for predicting the photovoltaic power generation and the park power consumption in the current cycle unit also includes: Call all commonly used algorithms in the prediction algorithm library, and in the previous cycle unit, determine multiple first photovoltaic power generation power prediction values ​​and multiple first park electricity consumption prediction values ​​obtained by calculating and processing different commonly used algorithms in each first fixed period, determine the photovoltaic prediction accuracy based on the multiple first photovoltaic power generation power prediction values ​​under any commonly used algorithm, and determine the electricity consumption prediction accuracy based on the multiple first park electricity consumption prediction values ​​under any commonly used algorithm, and use the commonly used algorithm corresponding to the maximum value of all photovoltaic prediction accuracies as the optimal prediction algorithm for predicting photovoltaic power in the current cycle unit, and use the commonly used algorithm corresponding to the maximum value of all electricity consumption prediction accuracies as the optimal prediction algorithm for predicting park electricity consumption in the current cycle unit.

7. An electronic device, characterized in that: The electronic device includes a processor coupled to a memory, wherein the memory stores at least one computer program, and the at least one computer program is loaded and executed by the processor so that the electronic device implements the method according to any one of claims 1 to 4.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores at least one computer program, which is loaded and executed by a processor to enable a computer to implement the method according to any one of claims 1 to 4.

Images