Scheduling method and system based on typical day extraction and oriented to access of new energy field station containing energy storage

Abstract

The invention is suitable for the technical field of electric power system dispatching, and provides a dispatching method and system depending on typical day extraction and oriented to access of a new energy station containing energy storage, and the method comprises the steps: extracting in-station new energy operation characteristics and station output characteristics according to historical data and station configuration energy storage system parameters; constructing a new energy station operation model; constructing a preprocessing model of a slack integer variable based on the new energy station operation model, determining a pre-scheduling result of a system containing the new energy station according to the constructed preprocessing model of the slack integer variable, and extracting a system operation reference vector from the pre-scheduling result of the system; performing time clustering on the system operation reference vector by using a machine learning clustering algorithm to extract a typical day; the unit commitment model is determined based on the typical days, and the operation state and the power distribution scheme of each element of the system in each typical day and the whole time period are obtained after solving is carried out by utilizing an optimization solving algorithm, so that the efficiency and the comprehensiveness of system scheduling are effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power system dispatching, and in particular to a dispatching method and system based on typical day extraction for access to new energy stations containing energy storage. Background Art

[0002] With the widespread access of renewable energy stations, the fluctuations of the power system have become more complex and difficult to predict, especially the modeling and operation prediction of the power system under the access of renewable energy stations. The existing unit combination method is difficult to achieve rapid calculation of the power system containing renewable energy stations on a long time scale and the system operation characteristics are lost after the simplified method is adopted.

[0003] At present, some studies have achieved system dispatch by combining unit combination with clustering method. Patent CN118353102A "A method for unit combination of power system based on target robustness optimization" proposes to establish a unit combination model. The objective function of the unit combination model is to minimize the sum of fuel cost, startup cost and weighted load loss, where the fuel cost is expressed as a piecewise linearized consumption function. The target robustness optimization model with uncertainty in photovoltaic output limitation is considered, and the photovoltaic output random variable is introduced as the sum of the photovoltaic output expectation and the photovoltaic output prediction error term, forming a highly robust model solution for the impact of new energy sites on the long-term operation of the power system. Patent CN117318047A "Planning State Power System Operation Simulation Method and Device Considering Energy Storage Participating in the Market" proposes a planning state power system operation simulation method considering energy storage participating in the market. Different from the traditional power system planning simulation which only models the traditional power plant model, load model, transformer model, and line model, it completely considers the planned power topology in the power market environment for optimization simulation, and considers the new subject that will be incorporated into the power system on a large scale in the future, namely the energy storage system, and its participation in the optimization of the power market. However, the existing clustering and unit combination methods do not consider the new energy and energy storage in the new energy station, do not pay enough attention to the flexibility brought by the joint dispatch of traditional units and new energy stations, and fail to solve the problem of overly complex large-scale system unit combination in long time scales.

[0004] In view of this, a scheduling method and system that relies on typical day extraction for access to new energy sites containing energy storage is needed. Summary of the invention

[0005] The embodiments of the present application provide a scheduling method and system that relies on typical day extraction for access to new energy sites containing energy storage, which is used to solve the problem of overly complex group calculations of large-scale system units over long time scales.

[0006] A first aspect of an embodiment of the present application provides a scheduling method for access to a new energy station containing energy storage and relying on typical day extraction, comprising:

[0007] Based on historical data and station configuration energy storage system parameters, extract the operation characteristics of new energy in the station and the station output characteristics, and build a new energy station operation model;

[0008] Constructing a preprocessing model of relaxed integer variables based on the new energy station operation model, determining a system pre-dispatching result including the new energy station according to the constructed preprocessing model of relaxed integer variables, and extracting a system operation reference vector from the system pre-dispatching result;

[0009] Using a machine learning clustering algorithm to perform time clustering on the system operation reference vector to extract a typical day;

[0010] The unit commitment model is determined based on the typical day, and the operation status and power allocation plan of each component of the system are obtained after solving it by using the optimization solution algorithm for each typical day and in the whole time period.

[0011] Furthermore, the operation characteristics of the new energy station and the output characteristics of the station are extracted based on the historical data and the parameters of the energy storage system configured at the station, and a new energy station operation model is constructed, including:

[0012] New energy output constraints:

[0013]

[0014] Where: P w,t is the output power of the wind turbine at time t, P w,t and are the upper and lower limits of the output power of the wind turbine at time t, P pv,t is the output power of the photovoltaic cell at time t, P pv,t and They are the upper and lower limits of the output power of the photovoltaic cell at time t respectively;

[0015] Energy storage state of charge constraints:

[0016]

[0017] Among them: Soc s,t―1 and Soc s,t are the charge states of the energy storage system at time t-1 and t-1 respectively, and are the charge and discharge efficiency, and are the amount of electricity charged and discharged by the energy storage system at time t;

[0018] Energy storage charging and discharging constraints:

[0019]

[0020] in: and They are the upper and lower limits of the charging and discharging power of the energy storage system respectively;

[0021] Station output constraints:

[0022]

[0023] Where: P station,t is the total output of the station at time t, W is the set of wind turbines in the station, ∑ w∈W P w,t is the total output power of all wind turbines in the station at time t, PV is the set of photovoltaic cells in the station, ∑ pv∈PV P pv,t is the total output power of all photovoltaic cells in the station at time t, S is the set of energy storage systems in the station, is the net output power of all energy storage systems in the station at time t;

[0024] Station climbing constraints:

[0025] P station,t ―P station,t―1 ≤RU station

[0026] P station,t―1 ―P station,t ≤RD station

[0027] Where: P station,t―1 is the total output of the station at time t-1, RU station is the climbing rate limit of the station, RD station It is the climbing and descending rate limit of the station.

[0028] Furthermore, the preprocessing model of the relaxed integer variables is constructed based on the new energy station operation model, and the system pre-dispatching result containing the new energy station is determined according to the constructed preprocessing model of the relaxed integer variables, and the system operation reference vector is extracted from the system pre-dispatching result, including:

[0029] Objective function of the preconditioning model with relaxed integer variables:

[0030]

[0031] Where: T is the total number of time periods, G is the set of traditional units, U g,t ,P g,t They represent the startup state, offline state and power generation of the traditional unit g in the system in time period t, They respectively represent the startup cost, fixed power generation cost and variable power generation cost of the traditional unit g in the system.

[0032] Furthermore, the preprocessing model of the relaxed integer variables is constructed based on the new energy station operation model, and the system pre-dispatching result containing the new energy station is determined according to the constructed preprocessing model of the relaxed integer variables, and the system operation reference vector is extracted from the system pre-dispatching result, including:

[0033] The constraints of the preprocessing model of relaxed integer variables include traditional unit combination constraints, power balance constraints and new energy station operation constraints, and their expressions are as follows:

[0034] Traditional unit combination constraints:

[0035]

[0036] in: is the number of startups of the traditional unit g in a scheduling cycle, is the maximum number of starts allowed for unit g;

[0037] Power balance constraints:

[0038]

[0039] Among them: RS is the set of new energy stations, D is the load set, P d,t is the active power demand of the load at time t.

[0040] Furthermore, the using of a machine learning clustering algorithm to perform time clustering on the system operation reference vector to extract a typical day includes:

[0041] Classifying each natural day according to the similarity of the system operation reference vector in the time dimension, and determining a typical day for each category of operation representation;

[0042] Based on the preset arrangement rules, typical days are used to construct the operation scenarios for the entire time period.

[0043] Furthermore, the classifying of each natural day according to the similarity of the system operation reference vector in the time dimension and determining the typical day of each category of operation representation includes:

[0044]

[0045] Where: x and y are the two system operation reference vectors, n is the dimension of the system operation reference vector, and d(x,y) is the Euclidean distance between the two system operation reference vectors.

[0046] Furthermore, the unit commitment model is determined based on the typical day, and the operation status and power allocation scheme of each component of the system in each typical day and in the whole time period are obtained by solving the model using the optimization solution algorithm, including:

[0047] The objective function of the unit commitment model is:

[0048]

[0049] Where: RP is the total number of typical days obtained by time clustering, λ rp is the number of natural days corresponding to the typical day rp;

[0050] Constraints of the unit commitment model:

[0051]

[0052] Among them: RU g and RD g is the climbing and descending capacity constraint of unit g, t1 and t2 are the end and beginning moments of adjacent typical time periods, respectively. and are the powers at time t1 and t2 respectively.

[0053] A second aspect of the embodiment of the present application provides a scheduling system that relies on typical day extraction for access to new energy sites including energy storage, including:

[0054] The new energy station operation model building unit is used to extract the new energy operation characteristics and station output characteristics in the station according to historical data and station configuration energy storage system parameters, and build a new energy station operation model;

[0055] A system operation reference vector extraction unit is used to construct a preprocessing model of a relaxed integer variable based on the new energy station operation model, determine a system pre-dispatching result containing the new energy station according to the constructed pre-processing model of the relaxed integer variable, and extract a system operation reference vector from the system pre-dispatching result;

[0056] A typical day extraction unit, used for performing time clustering on the system operation reference vector using a machine learning clustering algorithm to extract a typical day;

[0057] The scheduling scheme determination unit is used to determine the unit combination model based on the typical day, and obtain the operating status and power allocation scheme of each component of the system on each typical day and in the entire time period after solving it using the optimization solution algorithm.

[0058] A third aspect of the embodiments of the present application provides a computer device, including:

[0059] memories, transceivers, processors, and bus systems;

[0060] Wherein, the memory is used to store programs;

[0061] The processor is used to execute the program in the memory, including executing the scheduling method relying on typical day extraction for access of new energy stations with energy storage as described in any one of the above;

[0062] The bus system is used to connect the memory and the processor so that the memory and the processor can communicate with each other.

[0063] A fourth aspect of an embodiment of the present application provides a readable storage medium, including instructions, which, when executed on a computer, enables the computer to execute the steps of the scheduling method relying on typical day extraction for access to new energy stations containing energy storage as described in any of the above items.

[0064] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0065] The present invention extracts the operating characteristics of new energy sources in the station and the output characteristics of the station according to historical data and station configuration energy storage system parameters, and constructs an operating model for a new energy station; constructs a preprocessing model of relaxed integer variables, obtains system pre-dispatching results containing new energy stations, and establishes a system operation reference vector; uses a machine learning algorithm to perform time clustering to extract typical days, arranges typical days according to the extraction results, and reconstructs the full-time operation scenario; constructs a time clustering unit combination model based on typical days, and completes the full-time operation simulation of the power system containing new energy stations. The present invention realizes the operation simulation of the full time scale, and its final optimization result retains the complete constraints on the unit and the flexible description of the new energy station. At the same time, the time clustering method adopted by the invention accelerates the problem solving speed while keeping the system operation characteristics and timing fully reflected.

[0066] Other advantages, objectives, and features of the present invention will be set forth in part in the following description, and in part will be apparent to those skilled in the art based on an examination of the following or may be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 The present invention is a flowchart of an embodiment of a scheduling method for accessing new energy stations containing energy storage and relying on typical day extraction. DETAILED DESCRIPTION

[0068] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0069] In this embodiment, the scheduling method based on typical day extraction for access to new energy stations with energy storage solves the problem of overly complex group calculation of large-scale system units over a long time scale. The implementation method in this embodiment can be implemented in the system, on the server, or on the terminal, without specific limitation.

[0070] Embodiment 1

[0071] See also Figure 1 In the present invention, an embodiment of a scheduling method based on typical day extraction for access to a new energy station with energy storage comprises the following steps:

[0072] S11. Based on historical data and station configuration energy storage system parameters, extract the operation characteristics of new energy in the station and the output characteristics of the station, and build a new energy station operation model;

[0073] In this embodiment, the historical data and station-configured energy storage system parameters include: new energy output historical data, station-configured energy storage capacity, station-configured energy storage maximum charge and discharge power, station-configured energy storage charge and discharge efficiency, station-configured energy storage cycle period or more. Including as follows:

[0074] New energy output constraints:

[0075]

[0076] Where: P w，t is the output power of the wind turbine at time t, P w，t and are the upper and lower limits of the output power of the wind turbine at time t, P pv，t is the output power of the photovoltaic cell at time t, P pv，t and They are the upper and lower limits of the output power of the photovoltaic cell at time t respectively;

[0077] Energy storage state of charge constraints:

[0078]

[0079] Among them: Soc s，t is the state of charge of the energy storage system at time t, and are the charge and discharge efficiency, and are the amount of electricity charged and discharged by the energy storage system at time t;

[0080] Energy storage charging and discharging constraints:

[0081]

[0082] in: and They are the upper and lower limits of the charging and discharging power of the energy storage system respectively;

[0083] Station output constraints:

[0084]

[0085] Where: P station，t is the total output of the station at time t, W is the set of wind turbines in the station, ∑ w∈W P w，t is the total output power of all wind turbines in the station at time t, PV is the set of photovoltaic cells in the station, ∑ pv∈PV P pv，t is the total output power of all photovoltaic cells in the station at time t, S is the set of energy storage systems in the station, is the net output power of all energy storage systems in the station at time t;

[0086] Station climbing constraints:

[0087] P station，t -P station，t-1 ≤RU station

[0088] P station，t-1 -P station，t ≤RD station

[0089] Where: P station，t-1 is the total output of the station at time t-1, RU station is the climbing rate limit of the station, RD station It is the climbing and descending rate limit of the station.

[0090] S12. Constructing a preprocessing model of relaxed integer variables based on the operation model of the new energy station, determining the system pre-dispatching result including the new energy station according to the constructed preprocessing model of relaxed integer variables, and extracting the system operation reference vector from the system pre-dispatching result;

[0091] In this embodiment, the objective function of the preprocessing model of the relaxed integer variable is to minimize the system operation cost, and the expression of the objective function is as follows:

[0092] Objective function of the preconditioning model with relaxed integer variables:

[0093]

[0094] Where: T is the total number of time periods, G is the set of traditional units, U g，t , P g，tThey represent the startup state, offline state and power generation of the traditional unit g in the system in time period t, They respectively represent the startup cost, fixed power generation cost and variable power generation cost of the traditional unit g in the system.

[0095] Specifically, the constraints of the preprocessing model of the relaxed integer variables include: one or more of the traditional unit combination constraints, power balance constraints, and new energy station operation constraints. They include the following:

[0096] Traditional unit combination constraints:

[0097]

[0098] in: is the number of startups of the traditional unit g in a scheduling cycle, is the maximum number of starts allowed for unit g;

[0099] Power balance constraints:

[0100]

[0101] Among them: RS is the set of new energy stations, D is the load set, P d，t is the active power demand of the load at time t.

[0102] In addition, the system operation reference vector includes one or more of the output of traditional units and the output of new energy stations in the system, which can be expressed as OP nd :

[0103]

[0104] in, is the output vector of the traditional unit g on natural day nd, which is composed of the output at each moment; It is the output vector of the new energy station in the natural day, which is composed of the output at each moment.

[0105] S13. Use machine learning clustering algorithm to perform time clustering on system operation reference vectors to extract typical days;

[0106] In this embodiment, step S13 includes the following:

[0107] 1. Classify each natural day according to the similarity of the system operation reference vector in the time dimension, and determine the typical day of each category of operation representation;

[0108] The system operation reference vector data includes key information such as traditional unit output, new energy station output, etc. that can reflect the system operation status, and each vector corresponds to a natural day, that is, each natural day is represented by its specific system operation reference vector. For each pair of system operation reference vectors (corresponding to different natural days), the Euclidean distance formula is used to measure the similarity between them.

[0109]

[0110] Wherein: x and y are the two system operation reference vectors respectively, n is the dimension of the system operation reference vector, and d(x, y) is the Euclidean distance between the two system operation reference vectors.

[0111] Based on the above calculation, the distance value between the system operation reference vectors corresponding to any two natural days can be calculated. The smaller the distance, the more similar the system operation characteristics of the two natural days. According to the calculated Euclidean distance, the system operation reference vectors are clustered, and the natural days corresponding to vectors with similar distances are classified into the same category. The natural days in each category have a high similarity in system operation characteristics, which means that they have similar unit output, new energy station output and other operating conditions. In each clustering category, the natural day that best represents the operating characteristics of this category is selected as the typical day.

[0112] 2. Use typical days to construct the operation scenario for the entire time period based on preset arrangement rules.

[0113] Mark the category of the system operation reference vector corresponding to each original natural day to clarify which category it belongs to in the previous clustering process. The day closest to the geometric mean vector of each category is used as the operation reference vector of the corresponding typical day. By calculating the distance between the system operation reference vector of each natural day and the geometric mean vector of each category, the natural day with the closest distance is found, and its corresponding system operation reference vector is used as the operation reference vector of the typical day, further clarifying the specific characteristics of the typical day in terms of system operation. According to the category to which the natural day belongs, the original natural day is replaced with the corresponding typical day to obtain the reconstructed full-time operation scene. For example, if natural days nd1, nd2 and nd3 are respectively classified as typical day rp1, typical day rp3 and typical day rp2, then in the reconstructed operation scene, the original continuous natural days nd1, nd2 and nd3 will be replaced by the sequence of typical day rp1, typical day rp3 and typical day rp2, thereby constructing a full-time operation scene based on typical days, which is representative and can reflect the changes in the overall operation characteristics of the system.

[0114] S14. Determine the unit combination model based on the typical day, and use the optimization solution algorithm to solve it to obtain the operating status and power allocation plan of each component of the system on each typical day and in the entire time period.

[0115] The objective function of the full-time operation simulation model of the power system including new energy stations is to minimize the full-time operation cost, which is expressed as follows:

[0116]

[0117] Where: RP is the total number of typical days obtained by time clustering, λ rp is the number of natural days corresponding to the typical day rp

[0118] The constraints of the full-time operation simulation model of the power system including new energy stations include: one or more of the following: unit intra-day constraints, power balance constraints, new energy station output constraints, unit daytime constraints, and system grid constraints.

[0119] Constraints of the unit commitment model:

[0120]

[0121] Among them: RU g and RD g is the climbing and descending capacity constraint of unit g, t1 and t2 are the end and beginning moments of adjacent typical time periods, respectively. and are the powers at time t1 and t2 respectively.

[0122] The above-mentioned embodiments improve the operating characteristics and adjustment capabilities of new energy stations in the system by constraining the operating mode of traditional units at high time resolution on all time scales, thereby effectively improving the efficiency and comprehensiveness of system scheduling.

[0123] Embodiment 2

[0124] An embodiment of a typical day extraction-dependent dispatching system for access to a new energy station including energy storage in the present invention comprises the following steps:

[0125] The new energy station operation model building unit is used to extract the new energy operation characteristics and station output characteristics in the station according to historical data and station configuration energy storage system parameters, and build a new energy station operation model;

[0126] A system operation reference vector extraction unit is used to construct a preprocessing model of a relaxed integer variable based on the new energy station operation model, determine a system pre-dispatching result containing the new energy station according to the constructed pre-processing model of the relaxed integer variable, and extract a system operation reference vector from the system pre-dispatching result;

[0127] A typical day extraction unit, used for performing time clustering on the system operation reference vectors using a machine learning clustering algorithm to extract typical days;

[0128] The dispatching scheme determination unit is used to determine the unit combination model based on the typical day, and obtain the operating status and power allocation scheme of each component of the system on each typical day and in the entire time period after solving it using the optimization solution algorithm.

[0129] For the specific definition of the system, please refer to the definition of the method above, which will not be repeated here. Each module in the above system can be implemented in whole or in part by software, hardware and a combination thereof. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0130] Embodiment 3

[0131] The present invention provides a computer device, comprising a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor. When the processor executes the computer-readable instructions, the steps of the above method are implemented.

[0132] 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.

[0133] 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, such as multiple units can be combined into one unit, one unit can be split into multiple units, or some features can be ignored. In addition, each functional unit in each embodiment of the present invention can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units.

[0134] 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.

[0135] It can be understood 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 above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above 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 scheduling method based on typical day extraction for access to new energy stations with energy storage, characterized in that: include: Based on historical data and station configuration energy storage system parameters, extract the operation characteristics of new energy in the station and the station output characteristics, and build a new energy station operation model; Constructing a preprocessing model of relaxed integer variables based on the new energy station operation model, determining a system pre-dispatching result including the new energy station according to the constructed preprocessing model of relaxed integer variables, and extracting a system operation reference vector from the system pre-dispatching result; Using a machine learning clustering algorithm to perform time clustering on the system operation reference vector to extract a typical day; The unit commitment model is determined based on the typical day, and the operation status and power allocation plan of each component of the system are obtained after solving it by using the optimization solution algorithm for each typical day and in the whole time period.

2. The scheduling method based on typical day extraction for access to new energy stations with energy storage according to claim 1 is characterized in that: The method of extracting the operation characteristics of new energy in the station and the output characteristics of the station based on historical data and station configuration energy storage system parameters, and building a new energy station operation model includes: New energy output constraints: Where: P w,t is the output power of the wind turbine at time t, P w,t and are the upper and lower limits of the output power of the wind turbine at time t, P pv,t is the output power of the photovoltaic cell at time t, P pv , t and They are the upper and lower limits of the output power of the photovoltaic cell at time t respectively; Energy storage state of charge constraints: Among them: Soc s,t―1 and Soc s,t are the charge states of the energy storage system at time t-1 and t-1 respectively, and are the charge and discharge efficiency, and are the amount of electricity charged and discharged by the energy storage system at time t; Energy storage charging and discharging constraints: in: and They are the upper and lower limits of the charging and discharging power of the energy storage system respectively; Station output constraints: Where: P station,t is the total output of the station at time t, W is the set of wind turbines in the station, ∑ w∈W P w,t is the total output power of all wind turbines in the station at time t, PV is the set of photovoltaic cells in the station, ∑ pv∈PV P pv,t is the total output power of all photovoltaic cells in the station at time t, S is the set of energy storage systems in the station, is the net output power of all energy storage systems in the station at time t; Station climbing constraints: P station,t ―P station,t―1 ≤RU station P station,t―1 ―P station,t ≤RD station Where: P station,t―1 is the total output of the station at time t-1, RD station is the climbing rate limit of the station, RD station It is the climbing and descending rate limit of the station.

3. The scheduling method based on typical day extraction for access to new energy stations with energy storage according to claim 1 is characterized in that: The method comprises: constructing a preprocessing model of a relaxed integer variable based on the new energy station operation model, determining a system pre-dispatching result including the new energy station according to the constructed preprocessing model of the relaxed integer variable, and extracting a system operation reference vector from the system pre-dispatching result, including: Objective function of the preconditioning model with relaxed integer variables: Where: T is the total number of time periods, G is the set of traditional units, U g,t ,P g,t They represent the startup state, offline state and power generation of the traditional unit g in the system in time period t, They respectively represent the startup cost, fixed power generation cost and variable power generation cost of the traditional unit g in the system.

4. The scheduling method based on typical day extraction for access to new energy stations with energy storage according to claim 3 is characterized in that: The method comprises: constructing a preprocessing model of a relaxed integer variable based on the new energy station operation model, determining a system pre-dispatching result including the new energy station according to the constructed preprocessing model of the relaxed integer variable, and extracting a system operation reference vector from the system pre-dispatching result, including: The constraints of the preprocessing model of relaxed integer variables include traditional unit combination constraints, power balance constraints and new energy station operation constraints, and their expressions are as follows: Traditional unit combination constraints: in: is the number of startups of the traditional unit g in a scheduling cycle, is the maximum number of starts allowed for unit g; Power balance constraints: Among them: RS is the set of new energy stations, D is the load set, P d,t is the active power demand of the load at time t.

5. The scheduling method based on typical day extraction for access to new energy stations with energy storage according to claim 1 is characterized in that: The method of using a machine learning clustering algorithm to perform time clustering on the system operation reference vector to extract a typical day includes: Classifying each natural day according to the similarity of the system operation reference vector in the time dimension, and determining a typical day for each category of operation representation; Based on the preset arrangement rules, typical days are used to construct the operation scenarios for the entire time period.

6. The scheduling method based on typical day extraction for access to new energy stations with energy storage according to claim 5 is characterized in that: The classifying each natural day according to the similarity of the system operation reference vector in the time dimension and determining the typical day of each category of operation representation includes: Where: x and y are the two system operation reference vectors, n is the dimension of the system operation reference vector, and d(x,y) is the Euclidean distance between the two system operation reference vectors.

7. The scheduling method based on typical day extraction for access to new energy stations with energy storage according to claim 1 is characterized in that: The unit commitment model is determined based on the typical day, and the operation status and power allocation scheme of each component of the system in each typical day and in the whole time period are obtained by solving the model using the optimization solution algorithm, including: The objective function of the unit commitment model is: Where: RP is the total number of typical days obtained by time clustering, λ rp is the number of natural days corresponding to the typical day rp; Constraints of the unit commitment model: Among them: RU g and RD g is the climbing and descending capacity constraint of unit g, t1 and t2 are the end and beginning moments of adjacent typical time periods, respectively. and are the powers at time t1 and t2 respectively.

8. A dispatching system based on typical day extraction for access to new energy stations with energy storage, characterized in that: include: The new energy station operation model building unit is used to extract the new energy operation characteristics and station output characteristics in the station according to historical data and station configuration energy storage system parameters, and build a new energy station operation model; A system operation reference vector extraction unit is used to construct a preprocessing model of a relaxed integer variable based on the new energy station operation model, determine a system pre-dispatching result containing the new energy station according to the constructed pre-processing model of the relaxed integer variable, and extract a system operation reference vector from the system pre-dispatching result; A typical day extraction unit, used for performing time clustering on the system operation reference vector using a machine learning clustering algorithm to extract a typical day; The scheduling scheme determination unit is used to determine the unit combination model based on the typical day, and obtain the operating status and power allocation scheme of each component of the system on each typical day and in the entire time period after solving it using the optimization solution algorithm.

9. A computer device, characterized in that: include: memories, transceivers, processors, and bus systems; Wherein, the memory is used to store programs; The processor is used to execute the program in the memory, including executing the scheduling method for access to new energy stations containing energy storage and relying on typical day extraction according to any one of claims 1 to 7; The bus system is used to connect the memory and the processor so that the memory and the processor can communicate with each other.

10. A readable storage medium, characterized in that: It includes instructions, which, when running on a computer, enable the computer to execute the steps of the scheduling method relying on typical day extraction for access to new energy stations containing energy storage as described in any one of claims 1 to 7.

Images