Load control method and system for multi-class power equipment

Abstract

The invention relates to the technical field of load control, and discloses a load control method and system for multi-class power equipment, and the method comprises the steps: obtaining a system topological relation of the operation control of the power equipment; constructing a load removal control strategy according to the system topological relation; taking a transformer substation of a system topological relation as an input load automatic coordination layer, taking a cut-off load control strategy as a hidden load automatic coordination layer, and taking power equipment as an output load automatic coordination layer to form a power grid automatic coordination control model; and learning and training the power grid automatic coordination control model through a deep learning algorithm to obtain a power grid load adjustment model capable of outputting a control instruction to adjust the operation state of the power equipment. According to the invention, adaptive load shedding control can be carried out through deep learning, the voltage stability edge of the system can be improved, and the risk of system collapse is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of load control, and in particular to a load control method and system for multiple types of power equipment. Background Art

[0002] With the rapid development of the power industry and the gradual opening of the power market, the grid structure of interconnected power grids has become increasingly complex, which has increased the probability of hidden system failures and cascading failures, and has caused frequent disconnection accidents. Especially for the receiving power grid, disconnection accidents will cause the system to lose important transmission channels or interconnection lines, resulting in large-capacity power shortages. If the system's emergency control measures are limited, system instability is likely to occur. In order to ensure the normal operation of the power system, it is necessary to effectively control and manage the power load.

[0003] In view of this, a load control method and system for multiple types of power equipment is needed. Summary of the invention

[0004] In view of the problem in the prior art that when a large capacity power shortage occurs in the power system, the system instability is caused by limited emergency control measures. The present invention provides a load control method and system for multiple types of power equipment, which can perform adaptive load shedding control through deep learning, improve the voltage stability margin of the system, and reduce the risk of system collapse. The specific technical solution is as follows:

[0005] A load control method for multiple types of power equipment, comprising:

[0006] Obtain the system topology relationship of power equipment operation control;

[0007] Constructing a load shedding control strategy according to the system topology relationship;

[0008] The substation in the system topology relationship is used as the input load automatic coordination layer, the load removal control strategy is used as the hidden load automatic coordination layer, and the power equipment is used as the output load automatic coordination layer to form a power grid automatic coordination control model;

[0009] The power grid automatic coordination control model is trained through a deep learning algorithm to obtain a power grid load regulation model capable of outputting control instructions to adjust the operating status of power equipment.

[0010] Preferably, constructing a load shedding control strategy according to the system topology relationship includes:

[0011] Obtain the total load reduction that needs to be adjusted under the system topology;

[0012] Obtain the voltage sensitivity of all buses under the system topology;

[0013] A load shedding control model is obtained according to the total load shedding amount and the voltage sensitivity of all buses.

[0014] Preferably, the obtaining of the total load reduction amount that needs to be adjusted under the system topology relationship includes:

[0015] Obtain the power deficit between the generated power and the load consumption under the system topology relationship;

[0016] Obtain the spinning reserve capacity under the system topology relationship;

[0017] Obtain the number of loads under the system topology, the initial active power of each load, the initial voltage value of each load, the voltage value of each load in the current state, and the voltage characteristic coefficient of each load;

[0018] The total load reduction amount that needs to be adjusted is calculated based on the power shortage, rotating reserve capacity, number of loads, initial active power of each load, initial voltage value of each load, voltage value of each load in the current state and voltage characteristic coefficient of each load.

[0019] Preferably, obtaining the power deficit between the generated power and the load consumption under the system topology relationship includes:

[0020] Obtain the number of generators, frequency change, inertia time constant of each generator and the equivalent inertia time constant of the system in the system topology relationship, and obtain the system inertia center frequency;

[0021] Obtain the rated power, unbalanced power and equivalent inertia time constant of the system topology relationship, and obtain the equivalent power balance equation of the system;

[0022] The power deficit is obtained based on the system inertia center frequency and the system equivalent power balance equation.

[0023] Preferably, the method for calculating the unbalanced power includes:

[0024] The mechanical power and the electrical power of the system are acquired, and the unbalanced power is obtained according to the changes of the mechanical power and the electrical power.

[0025] Preferably, the step of acquiring the voltage sensitivity of all buses under the system topology relationship includes:

[0026] Obtaining the bus voltage of all nodes in the system topology, and the admittance, power angle difference and phase angle difference between each node, and constructing the transmission equation of the active power and reactive power of the node;

[0027] Perform Jacobian matrix analysis on the transmission equations of active power and reactive power of the node to obtain the linear equations of active power and reactive power;

[0028] By setting a specific value of active power change, solving the linear equations of active power and reactive power, the incremental change of bus reactive power and the incremental change of bus voltage amplitude are obtained;

[0029] The voltage sensitivity of all buses is obtained according to the incremental change of bus reactive power and the incremental change of bus voltage amplitude.

[0030] Preferably, the load shedding control strategy obtained according to the total load shedding amount and the voltage sensitivity of all buses includes:

[0031] Step S101, obtaining voltage and frequency data of all load buses;

[0032] Step S102, judging whether the voltage and frequency of each load bus meet the threshold conditions, if so, instantaneously cutting off the load of the bus and then executing step 103, if not, directly executing step S103;

[0033] Step S103, calculating the load shedding amount allocated to each load bus according to the total load shedding amount and the voltage sensitivity of all buses;

[0034] Step S104: After the load shedding is completed, repeat steps S102 to S104.

[0035] Preferably, the power grid automatic coordination control model is trained by a deep learning algorithm to obtain a power grid load regulation model capable of outputting control instructions to adjust the operating state of power equipment, including:

[0036] Obtain load data in substations;

[0037] Obtaining the control operation data under the load shedding control strategy;

[0038] Performing time stamp alignment processing on the load data and the control operation data to obtain sample data;

[0039] The sample data is input into the deep learning model for learning and training to obtain a power grid load regulation model capable of outputting control instructions to adjust the operating status of power equipment.

[0040] A load control system for multiple types of electric power equipment, applied to the aforementioned load control method for multiple types of electric power equipment, comprises:

[0041] A topology relationship acquisition unit, used to acquire the system topology relationship of the power equipment operation control;

[0042] A load shedding construction unit, used for constructing a load shedding control strategy according to the system topology relationship;

[0043] A control model generation unit is used to form a power grid automatic coordination control model by taking the substation in the system topology relationship as the input load automatic coordination layer, the load removal control strategy as the hidden load automatic coordination layer, and the power equipment as the output load automatic coordination layer;

[0044] The model learning and training unit is used to learn and train the power grid automatic coordination control model through a deep learning algorithm to obtain a power grid load regulation model that has output control instructions to adjust the operating status of power equipment.

[0045] Compared with the prior art, the present invention has the following beneficial effects:

[0046] A load control method for multi-category power equipment of the present invention obtains the system topology relationship of the power equipment operation control; constructs a load shedding control strategy according to the system topology relationship; uses the substation of the system topology relationship as the input load automatic coordination layer, the load shedding control strategy as the hidden load automatic coordination layer, and the power equipment as the output load automatic coordination layer to form a power grid automatic coordination control model; and trains the power grid automatic coordination control model through a deep learning algorithm to obtain a power grid load regulation model with output control instructions to adjust the operating state of the power equipment. The present invention can perform adaptive load shedding control through deep learning, which can improve the voltage stability margin of the system and reduce the risk of system collapse. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for the specific embodiments or the description of the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn according to the actual scale.

[0048] Figure 1 The present invention is a flow chart of a load control method for multiple types of power equipment.

[0049] Figure 2 The present invention is a flow chart of an embodiment of a load shedding control strategy.

[0050] Figure 3 The figure is a flow chart of an embodiment of calculating the total load reduction amount of the present invention.

[0051] Figure 4 The flowchart of the embodiment of calculating the voltage sensitivity of all buses of the present invention is shown in FIG.

[0052] Figure 5 The flowchart of the load shedding control strategy of the present invention is shown in FIG.

[0053] Figure 6The figure is a flow chart of an embodiment of calculating power shortage of the present invention.

[0054] Figure 7 The present invention is a flowchart of an embodiment of constructing a power grid load regulation model.

[0055] Figure 8 This is a system topology diagram for the power equipment operation control of the present invention.

[0056] Fig. 9 The present invention is a load control system schematic diagram of multiple types of power equipment. DETAILED DESCRIPTION

[0057] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0058] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0059] It should also be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0060] It should be further understood that the term "and / or" used in the present description and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0061] See the following examples Figures 1 to 9 .

[0062] The present application provides a load control method for multiple types of power equipment, including:

[0063] Step S01, obtaining a system topology relationship for operation control of power equipment;

[0064] like Figure 8As shown, the connection mode and relationship between each device in the entire power system are obtained, and the connection mode from the power station to the substation and from the substation to each type of power equipment is simplified into a system topology relationship for power equipment operation control.

[0065] Step S02: constructing a load shedding control strategy according to the system topology relationship;

[0066] The main purpose of the strategy is to maintain the stable operation of the power grid by cutting off part of the load when the power grid is overloaded or in an emergency. The formulation of the strategy needs to take into account a variety of factors, such as load distribution, capacity limitations of equipment, and stability margin of the power grid.

[0067] Step S03, the substation in the system topology relationship is used as the input load automatic coordination layer, the load removal control strategy is used as the hidden load automatic coordination layer, and the power equipment is used as the output load automatic coordination layer to form a power grid automatic coordination control model;

[0068] The substations in the system topology are used as the input load automatic coordination layer, the load removal control strategy is used as the hidden load automatic coordination layer, and the power equipment is used as the output load automatic coordination layer to form a power grid automatic coordination control model. The core function of this model is to automatically adjust the operating status of the power equipment according to the real-time operating status of the power grid to achieve balanced load distribution and stable operation of the power grid.

[0069] Step S04: training the power grid automatic coordination control model through a deep learning algorithm to obtain a power grid load regulation model capable of outputting control instructions to adjust the operating status of power equipment.

[0070] Through training, the model will learn to output corresponding control instructions to adjust the operating status of power equipment based on the real-time load conditions of the power grid, the status of the equipment, and the load removal control strategy. Finally, a power grid load regulation model with the ability to output control instructions to adjust the operating status of power equipment is obtained.

[0071] Specifically, in a preferred implementation of the present application, the load shedding control strategy constructed according to the system topology relationship includes:

[0072] Step S21: Obtain the total load reduction amount P that needs to be adjusted under the system topology relationship shed ;

[0073] Specifically, the total load reduction amount P that needs to be adjusted under the system topology relationship is obtained. shed include:

[0074] Step S210: Obtain the power deficit P between the power generation and load consumption under the system topology relationship. def ;

[0075] Step S211: Obtain the spinning reserve capacity P under the system topology relationship SR ;

[0076] Step S212: Obtain the number of loads m and the initial active power P of each load under the system topology relationship. L0,i , the initial voltage value U of each load 0,i , the voltage value U of each load in the current state i and the voltage characteristic coefficient α of each load i ;

[0077] Step S213: according to the power shortage P def , Spinning reserve capacity P SR , the number of loads m, the initial active power P of each load L0,i , the initial voltage value U of each load 0,i , the voltage value U of each load in the current state i and the voltage characteristic coefficient α of each load i , calculate the total load reduction P that needs to be adjusted shed .

[0078]

[0079] Total load shedding refers to the total power demand that needs to be reduced by shedding part of the load when the power grid is overloaded or in an emergency. The purpose of obtaining total load shedding is to ensure that the load shedding control strategy can effectively alleviate the overload situation of the power grid while maintaining the stable operation of the power grid.

[0080] Step S22: Obtain the voltage sensitivity dV of all buses under the system topology relationship i / dQ i ;

[0081] Specifically, the voltage sensitivity dV of all buses under the system topology relationship is obtained. i / dQ i include:

[0082] Step S220: Obtain the bus voltages of all nodes in the system topology, and the admittance, power angle difference, and phase angle difference between each node, and construct the transmission equations of the active power and reactive power of the nodes; the expressions are as follows:

[0083]

[0084] Where V i and V j Represents the bus voltage of node i and node j respectively, G ij represents the admittance of nodes i and j, B ijrepresents the power angle difference between node i and node j, θ ij Represents the phase angle difference between node i and node j.

[0085] Step S221, performing Jacobian matrix analysis on the transmission equations of active power and reactive power of the node to obtain linear equations of active power and reactive power;

[0086]

[0087] In the formula, J Pθ represents the matrix elements composed of the partial derivatives of active power P with respect to bus voltage angle θ, J PV represents the matrix elements composed of the partial derivatives of active power P with respect to bus voltage amplitude V, J Qθ represents the matrix elements composed of the partial derivatives of reactive power Q with respect to bus voltage angle θ, J QV Represents the matrix elements composed of the partial derivatives of the reactive power Q with respect to the bus voltage amplitude V.

[0088] Step S222, by setting a specific value of active power change, solving the linear equation of active power and reactive power, and obtaining the relationship between the incremental change of bus reactive power and the incremental change of bus voltage amplitude;

[0089] Since the stability of system voltage is affected by both active power and reactive power, it is assumed that the active power is kept constant at each operating point and the incremental relationship between the two is considered. Let active power P = 0, and we get:

[0090]

[0091] At the same time, we get:

[0092]

[0093] Among them, J R is made by The resulting matrix, J R The coefficient matrix represents the relationship between reactive power and bus voltage amplitude increment when active power P=0.

[0094] Step S223: Obtain the voltage sensitivity of all buses according to the relationship between the incremental change of bus reactive power and the incremental change of bus voltage amplitude.

[0095]

[0096] The voltage of each busbar dV i / dQ i It indicates the slope of the curve at a given operating point. When the voltage sensitivity is positive, it means that the system is running stably, and the smaller the voltage sensitivity, the more stable the system.

[0097] Voltage sensitivity refers to the degree to which the bus voltage in the power grid responds to load changes. It is crucial to consider voltage sensitivity in the formulation of load shedding control strategies. By obtaining the voltage sensitivity of all buses, the impact of shedding different loads on the voltage stability of the power grid can be evaluated, and a more reasonable load shedding control strategy can be formulated.

[0098] Step S23: according to the total load reduction amount P shed And the voltage sensitivity of all buses dV i / dQ i The load shedding control strategy is obtained.

[0099] Specifically, according to the total load reduction amount P shed And the voltage sensitivity of all buses dV i / dQ i The load shedding control strategies include:

[0100] Step S101: Obtain the voltage V of all load buses i and frequency data f i ;

[0101] Step S102: Determine the voltage V of each load bus i and frequency f i Does it meet V i <0.8pu and f i <47.5H Z If the threshold condition is met, the load of the bus is instantly cut off and step 103 is executed. If not met, step S103 is directly executed;

[0102] Step S103: according to the total load reduction amount P shed And the voltage sensitivity of all buses dV i / dQ i Calculate the load shedding amount allocated to each load bus;

[0103]

[0104] Step S104: After the load shedding is completed, repeat steps S102 to S104.

[0105] In this embodiment, a centralized adaptive load shedding algorithm based on wide area information is proposed, the main goal is to ensure voltage stability while taking into account the restoration of system frequency stability when formulating load shedding strategies in emergency situations. The system interference amplitude is determined according to the disturbance situation and the interference degree is classified, and then the load shedding location and the load shedding amount of the corresponding bus are determined according to the voltage sensitivity, so as to quickly cut off the overload and restore the stability of the system.

[0106] Specifically, the power deficit P between the generated power and the load consumption under the system topology relationship is obtained. def include:

[0107] Step S201: Obtain the number of generators n and the frequency change Δf of each generator in the system topology relationship. i and the inertia time constant H of each generator i , we get the system inertia center frequency Δf COI ;

[0108]

[0109] In the formula, H eq is the equivalent inertia time constant of the system,

[0110] Step S202: Obtain the rated power f of the system topology relationship N , unbalanced power ΔP and system equivalent inertia time constant H eq , we get the equivalent power balance equation of the system; the expression is:

[0111]

[0112] Where, ΔP = ΔP M -ΔP L , ΔP M is the mechanical power, ΔP L is the electrical power, (ΔP M -ΔP L ) represents the change of mechanical power and electrical power.

[0113] Step S203: according to the system inertia center frequency Δf COI The power balance equation equivalent to the system gives the power deficit P def .

[0114]

[0115] In the formula, S eq Represents the sum of the available powers of all generators.

[0116] In this embodiment, by obtaining the system inertia center frequency and power shortage, the stability of the system under load changes or faults can be evaluated, and the system crash can be well prevented; a load shedding control strategy can be formulated; and accurate power shortage information is calculated to provide an important basis for formulating a load shedding control strategy. In addition, understanding the inertia time constant and rated power of each generator in the system is helpful to optimize the system resource configuration. By reasonably allocating the power generation and load demand, the overall operating efficiency and reliability of the system can be improved.

[0117] Specifically, the power grid automatic coordination control model is trained by a deep learning algorithm to obtain a power grid load regulation model capable of outputting control instructions to adjust the operating state of power equipment, including:

[0118] Step S41, obtaining load data in the substation;

[0119] Obtain real-time or historical load data in the substation. Load data usually includes key parameters such as current, voltage, and power factor, which reflect the load status of the power grid at different time points. These data are crucial for subsequent training models, and the data provide direct evidence of power grid load changes.

[0120] Step S42, obtaining control operation data under the load shedding control strategy;

[0121] It is necessary to collect the control and operation data of the power grid under the load shedding control strategy. The load shedding control strategy is usually a measure to deal with power grid overload or emergency situations, and to maintain the stable operation of the power grid by shedding part of the load. The control and operation data may include information such as the amount, time, and location of the load shedding, as well as the operating status data of the power grid after the load shedding.

[0122] Step S43, performing timestamp alignment processing on the load data and the control operation data to obtain sample data;

[0123] Since load data and control operation data may come from different data sources or have different sampling frequencies, they need to be timestamped to ensure that each pair of load data and control operation data corresponds to the same time point, thus forming a complete sample data set.

[0124] Step S44: input the sample data into the deep learning model for learning and training, and obtain a power grid load regulation model capable of outputting control instructions to adjust the operating status of power equipment.

[0125] Through training, the model will learn to predict future load changes based on load data and control operation data, and output corresponding control instructions to adjust the operating status of power equipment, obtaining a grid load regulation model that can respond to grid load changes in real time and output effective control instructions.

[0126] In this embodiment, the power grid automatic coordination control model is trained through a deep learning algorithm, aiming to build a power grid load regulation model that can intelligently adjust the operating status of power equipment to cope with load changes, improve the stability and reliability of the power grid, and optimize the allocation of power resources.

[0127] A load control method for multi-category power equipment of the present invention obtains the system topology relationship of the power equipment operation control; constructs a load shedding control strategy according to the system topology relationship; uses the substation of the system topology relationship as the input load automatic coordination layer, the load shedding control strategy as the hidden load automatic coordination layer, and the power equipment as the output load automatic coordination layer to form a power grid automatic coordination control model; and trains the power grid automatic coordination control model through a deep learning algorithm to obtain a power grid load regulation model with output control instructions to adjust the operating state of the power equipment. The present invention can perform adaptive load shedding control through deep learning, which can improve the voltage stability margin of the system and reduce the risk of system collapse.

[0128] The embodiment of the present application also provides a load control system for multiple types of electric power equipment, which is applied to the aforementioned load control method for multiple types of electric power equipment, including:

[0129] A topology relationship acquisition unit, used to acquire the system topology relationship of the power equipment operation control;

[0130] A load shedding construction unit, used for constructing a load shedding control strategy according to the system topology relationship;

[0131] A control model generation unit is used to form a power grid automatic coordination control model by taking the substation in the system topology relationship as the input load automatic coordination layer, the load removal control strategy as the hidden load automatic coordination layer, and the power equipment as the output load automatic coordination layer;

[0132] The model learning and training unit is used to learn and train the power grid automatic coordination control model through a deep learning algorithm to obtain a power grid load regulation model that has output control instructions to adjust the operating status of power equipment.

[0133] The functional explanation of the song circle in this embodiment is the same as the explanation in an embodiment of a load control method for multi-category power equipment, and the technical effect is the same, so it will not be repeated here.

[0134] Those of ordinary skill in the art will appreciate that the units of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition of each example has been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0135] In the embodiments provided by the present invention, it should be understood that the division of units is only a logical function division, and there may be other division methods in actual implementation, for example, multiple units can be combined into one unit, one unit can be split into multiple units, or some features can be ignored, etc.

[0136] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0137] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-0nlyMemory), random access memory (RAM, RandomAccessMemory), mobile hard disk, magnetic disk or optical disk, etc., which can store program code.

[0138] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. A load control method for multiple types of power equipment, characterized in that: include: Obtain the system topology relationship of power equipment operation control; Constructing a load shedding control strategy according to the system topology relationship; The substation in the system topology relationship is used as the input load automatic coordination layer, the load removal control strategy is used as the hidden load automatic coordination layer, and the power equipment is used as the output load automatic coordination layer to form a power grid automatic coordination control model; The power grid automatic coordination control model is trained through a deep learning algorithm to obtain a power grid load regulation model capable of outputting control instructions to adjust the operating status of power equipment.

2. A load control method for multiple types of power equipment according to claim 1, characterized in that: The constructing of a load shedding control strategy according to the system topology relationship comprises: Obtain the total load reduction that needs to be adjusted under the system topology; Obtain the voltage sensitivity of all buses under the system topology; A load shedding control model is obtained according to the total load shedding amount and the voltage sensitivity of all buses.

3. A load control method for multiple types of power equipment according to claim 2, characterized in that: The total load reduction amount that needs to be adjusted under the system topology relationship is obtained, including: Obtain the power deficit between the generated power and the load consumption under the system topology relationship; Obtain the spinning reserve capacity under the system topology relationship; Obtain the number of loads under the system topology, the initial active power of each load, the initial voltage value of each load, the voltage value of each load in the current state, and the voltage characteristic coefficient of each load; The total load reduction amount that needs to be adjusted is calculated based on the power shortage, rotating reserve capacity, number of loads, initial active power of each load, initial voltage value of each load, voltage value of each load in the current state and voltage characteristic coefficient of each load.

4. A load control method for multiple types of power equipment according to claim 3, characterized in that: The obtaining of the power deficit between the generated power and the load consumption under the system topology relationship includes: Obtain the number of generators, frequency change, inertia time constant of each generator and the equivalent inertia time constant of the system in the system topology relationship, and obtain the system inertia center frequency; Obtain the rated power, unbalanced power and equivalent inertia time constant of the system topology relationship, and obtain the equivalent power balance equation of the system; The power deficit is obtained based on the system inertia center frequency and the system equivalent power balance equation.

5. A load control method for multiple types of power equipment according to claim 4, characterized in that: The method for calculating the unbalanced power includes: The mechanical power and the electrical power of the system are acquired, and the unbalanced power is obtained according to the changes of the mechanical power and the electrical power.

6. A load control method for multiple types of power equipment according to claim 5, characterized in that: The method of obtaining the voltage sensitivity of all buses under the system topology relationship includes: Obtaining the bus voltage of all nodes in the system topology, and the admittance, power angle difference and phase angle difference between each node, and constructing the transmission equation of the active power and reactive power of the node; Perform Jacobian matrix analysis on the transmission equations of active power and reactive power of the node to obtain the linear equations of active power and reactive power; By setting a specific value of active power change, solving the linear equations of active power and reactive power, the incremental change of bus reactive power and the incremental change of bus voltage amplitude are obtained; The voltage sensitivity of all buses is obtained according to the incremental change of bus reactive power and the incremental change of bus voltage amplitude.

7. A load control method for multiple types of power equipment according to claim 6, characterized in that: The load shedding control strategy obtained according to the total load shedding amount and the voltage sensitivity of all buses includes: Step S101, obtaining voltage and frequency data of all load buses; Step S102, judging whether the voltage and frequency of each load bus meet the threshold conditions, if so, instantaneously cutting off the load of the bus and then executing step 103, if not, directly executing step S103; Step S103, calculating the load shedding amount allocated to each load bus according to the total load shedding amount and the voltage sensitivity of all buses; Step S104: After the load shedding is completed, repeat steps S102 to S104.

8. A load control method for multiple types of power equipment according to claim 1, characterized in that: The power grid automatic coordination control model is trained by a deep learning algorithm to obtain a power grid load regulation model capable of outputting control instructions to adjust the operating state of power equipment, including: Obtain load data in substations; Obtaining the control operation data under the load shedding control strategy; Performing time stamp alignment processing on the load data and the control operation data to obtain sample data; The sample data is input into the deep learning model for learning and training to obtain a power grid load regulation model capable of outputting control instructions to adjust the operating status of power equipment.

9. A load control system for multiple types of power equipment, characterized in that: A load control method for multi-category power equipment applied to any one of claims 1 to 8, comprising: A topology relationship acquisition unit, used to acquire the system topology relationship of the power equipment operation control; A load shedding construction unit, used to construct a load shedding control strategy according to the system topology relationship; A control model generation unit is used to form a power grid automatic coordination control model by taking the substation in the system topology relationship as the input load automatic coordination layer, the load removal control strategy as the hidden load automatic coordination layer, and the power equipment as the output load automatic coordination layer; The model learning and training unit is used to learn and train the power grid automatic coordination control model through a deep learning algorithm to obtain a power grid load regulation model that has output control instructions to adjust the operating status of power equipment.

Images