Multi-period multi-scenario scuc decoupling method, system, device and storage medium

Abstract

The application discloses a kind of multi-period multi-scenario SCUC decoupling method, system, equipment and storage medium, method includes: according to the uncertainty of hydropower, establish multi-period multi-scenario SCUC model;Obtain cascade hydropower parameters, establish original cascade hydropower system, and original cascade hydropower system is equivalent to hydropower single station system;Based on multi-period decoupling mechanism, divide multi-period multi-scenario SCUC model, establish SCUC sub-problem in different time periods;Based on multi-scenario decoupling mechanism, divide multi-period multi-scenario SCUC model, establish SCUC sub-problem in different scenes according to climbing coupling constraint;According to target cascade analysis algorithm, parallel computing is carried out, and SCUC sub-problem in different time periods and SCUC sub-problem in different scenes are solved. By considering multi-period and multi-scenario decoupling mechanism, decoupling and accelerated calculation of SCUC problem are realized by parallel computing, and the model solving time length is effectively reduced within acceptable confidence.

Description

Technical Field

[0001] This invention belongs to the field of new energy and energy-saving technology, and relates to a multi-time period and multi-scenario SCUC decoupling method, system, device and storage medium. Background Technology

[0002] Hydropower offers advantages such as flexible regulation and environmental friendliness, effectively alleviating the shortage of traditional energy supplies while reducing environmental pollution. However, hydropower generation is characterized by fluctuations and randomness. Coupled with the limitations of hydropower reservoir capacity, the computational burden of Security-Constrained Unit Commitment (SCUC) is significantly increased, making it impossible to complete the calculations and obtain the corresponding optimization results within the stipulated time. Therefore, how to accelerate the calculation of SCUC for hydropower units connected to the power system across multiple time periods and scenarios has become a hot topic in academia. Dividing the SCUC problem into smaller problems based on geographical regions is a feasible solution, but this solution does not consider time-period decoupling and scenario decoupling, resulting in a still long computation time. Summary of the Invention

[0003] The purpose of this invention is to address the problem that existing technologies do not consider how to decouple SCUC problems involving hydropower uncertainties across multiple time periods and scenarios to reduce solution time. This invention provides a method, system, device, and storage medium for decoupling SCUC problems across multiple time periods and scenarios.

[0004] To achieve the above objectives, the present invention employs the following technical solution:

[0005] A multi-time-period, multi-scenario SCUC decoupling method includes the following steps:

[0006] Based on the uncertainties of hydropower, a multi-time period and multi-scenario SCUC model is established;

[0007] The parameters of cascade hydropower are obtained from the multi-time period and multi-scenario SCUC model, the original cascade hydropower system is established, and the original cascade hydropower system is equivalent to a single hydropower station system.

[0008] Based on the multi-time period decoupling mechanism, the SCUC model is divided into multi-time period and multi-scenario, and SCUC sub-problems are established for different time periods;

[0009] Based on the multi-scenario decoupling mechanism, a multi-time period and multi-scenario SCUC model is divided, and SCUC sub-problems are established for different scenarios according to the climbing coupling constraints.

[0010] Parallel computation is performed using the target cascade analysis algorithm to solve SCUC subproblems at different time periods and in different scenarios.

[0011] A further improvement of the present invention is that:

[0012] The establishment of the multi-time-period, multi-scenario SCUC model is specifically represented as follows:

[0013] The objective function is to minimize the operating cost of the power system.

[0014]

[0015] Where, x n The variables in the SCUC model include thermal power unit output, hydropower unit output, hydropower station discharge, hydropower station overflow, and unit start-up / shutdown state variables; n is the random scenario number; N is the total number of random scenarios; π n Let Σπ represent the probability of a random scenario n, and let Σπ represent the probability of a random scenario n. n =1; t is the time period number; T is the total number of time periods; y is the thermal power unit number; Y is the total number of thermal power units; the subscript b indicates the baseline scenario; f n (p t,y,n ,z t,y,n ) represents the operating cost of the power system under random scenario n; f b (p t,y,n ,z t,y,n ) represents the power system operating cost under baseline scenario b; p t,y,n The output of thermal power unit y under random scenario n in time period t; z t,y,n This represents the start-up and shutdown status of thermal power unit y under random scenario n in time period t, where 1 represents start-up and 0 represents shutdown; p t,y,b The output of thermal power unit y under the baseline scenario b at time period t; z t,y,b The thermal power unit y represents the start-up and shutdown status of the unit in the baseline scenario b during time period t, where 1 represents start-up and 0 represents shutdown.

[0016] The constraints are:

[0017]

[0018]

[0019]

[0020] Among them, h n (x n ) / h b (x b This includes constraints related to power balance and reservoir capacity balance in cascade hydropower stations; g n (x n ) / g b (x b This includes inequality constraints such as output limits for thermal power units, output limits for hydropower units, capacity limits for cascade hydropower reservoirs, and ramping constraints for thermal power units. This refers to the uphill / downhill ramp limit for thermal power unit y.

[0021] The original cascade hydropower system model is specifically represented as follows:

[0022] The objective function is to maximize the benefits of the cascade hydropower system.

[0023]

[0024] Wherein, the superscript O represents the original cascade hydropower system; λ t I is the electricity price for time period t; i is the hydroelectric power station number; I o is the number of hydropower stations in the original cascade hydropower model; k is the linearized segment number of the hydropower station's output performance curve; K is the number of linearized segments of the hydropower station's output performance curve. It is the output performance coefficient of the k-th linearized segment of the i-th hydropower station; λ is the water output of hydropower station i in the k-th segment of time period t; F It is a forecast of future electricity prices; It is the reservoir capacity of hydropower station i during time period T; This is a binary parameter. It is 1 when hydropower station j is a downstream power station of hydropower station i, and 0 otherwise. It is the future predicted output performance coefficient of hydropower station j;

[0025] Storage capacity balance constraints:

[0026]

[0027] in, Let be the overflow discharge of hydropower station i during time period t; Let be the inflow rate of hydropower station i during time period t; Let i be the set of upstream hydropower stations;

[0028] Initial storage capacity constraints:

[0029]

[0030] in, It is the percentage of the initial reservoir capacity of hydropower station i to the total reservoir capacity; The maximum reservoir capacity of hydropower station i;

[0031] Water output limits:

[0032]

[0033] in, It is the minimum water output of hydropower station i in the k-th segment; It is the maximum water output of hydropower station i in the k-th segment;

[0034] Storage capacity constraints:

[0035]

[0036] in, It is the minimum reservoir capacity of hydropower station i;

[0037] Overflow flow limit constraints:

[0038]

[0039] in, It is the minimum overflow of hydropower station i; It is the maximum overflow of hydropower station i.

[0040] The original cascade hydropower system is equivalent to a single hydropower station system through a two-layer optimization model, specifically represented as follows:

[0041] Minimizing the revenue difference between the original cascade hydropower system and the single hydropower station system is taken as the objective function of the upper-level model:

[0042]

[0043] The constraints of the upper-level model are:

[0044] Hydropower single-station system output performance coefficient limit:

[0045]

[0046] Limitations on the future projected output performance coefficient of a single hydropower station system:

[0047]

[0048] The objective function of the lower-level model is:

[0049]

[0050] The constraints of the lower-level model are:

[0051]

[0052]

[0053]

[0054]

[0055]

[0056] The lower-level model is transformed into equivalent constraint conditions using KKT conditions and the Big M method, resulting in an equivalent single-level model.

[0057] Based on the initial hydropower energy of the original cascade hydropower system, the parameters of the single hydropower station system are calculated. The initial hydropower energy of the original cascade hydropower system is:

[0058]

[0059] Among them, E O This represents the initial hydropower energy of the original cascade hydropower system.

[0060] The output performance coefficient of the first linearized segment of the hydropower single-station system is:

[0061]

[0062] in, It is the output performance curve of the first linearized segment of the equivalent single-station system; r i The total inflow of hydropower station i;

[0063] The initial reservoir capacity of a single hydropower station system is:

[0064]

[0065] in, This represents the initial storage capacity of an equivalent single-station system.

[0066] The multi-time-period, multi-scenario SCUC model is divided based on a multi-time-period decoupling mechanism, and SCUC sub-problems for different time periods are established. The specific representations of the SCUC sub-problems for different time periods are as follows:

[0067] Suppose that the SCUC model for different scenarios is divided into three time periods, and the corresponding time periods are c. - c and c + The corresponding SCUC subproblems are SP. c- SP c and SP c+ ;

[0068] SCUC subproblem SP c- The corresponding time period is from 1 to t. c- +1, the objective function is:

[0069]

[0070] The constraints are:

[0071] h c- (x c- )=0&g c- (x c- )≤0,t={1,...,t c- +1}

[0072] SCUC subproblem SP c The corresponding time period is t c- +1 to t c +1, the objective function is:

[0073]

[0074] The constraints are:

[0075] h c (x c )=0&g c (x c )≤0,t={t c- +1,...,t c +1}

[0076] SCUC subproblem SP c+ The corresponding time period is t c From +1 to T, the objective function is:

[0077]

[0078] The constraints are:

[0079] h c+ (x c+ )=0&g c+ (x c+ )≤0,t={t c +1,...,t c+}

[0080] Where, x c- x c and x c+ These are subproblems SP c- SP c and SP c+ The variable group includes the output of thermal power units, the output of hydropower units, the discharge of hydropower stations, the overflow of hydropower stations, and the start-up and shutdown status variables of the units.

[0081] The multi-scenario decoupling mechanism-based SCUC model is divided into multi-time-period, multi-scenario sub-problems. Specifically, a penalty term and a consistency constraint are added to the objective functions of the random and baseline scenarios of the hydropower single-station system. This ensures that, within each time period, the same thermal power unit in different random scenarios satisfies the climbing constraint as well as the corresponding thermal power unit in the baseline scenario. The climbing constraint is expressed as:

[0082]

[0083] The output of the baseline scenario in the random scenario meets the output limit of the thermal power unit, specifically as follows:

[0084]

[0085] The consistency constraints added to the random scenario and the baseline scenario are specifically expressed as follows:

[0086]

[0087]

[0088] in, This represents the maximum uphill / downhill gradient of thermal power unit y.

[0089] When the target cascade analysis algorithm performs parallel computation, a coordinator is introduced to coordinate and optimize the SCUC subproblems, and each subproblem is solved in parallel until the convergence condition is met; the initial value of the target cascade analysis is obtained through a supervised BP neural network.

[0090] A multi-time, multi-scenario SCUC decoupling system includes the following modules:

[0091] The model building module is used to build a multi-time period and multi-scenario SCUC model based on the uncertainty of hydropower.

[0092] The system equivalent module is used to obtain cascade hydropower parameters from a multi-time period and multi-scenario SCUC model, establish the original cascade hydropower system, and convert the original cascade hydropower system into a single hydropower station system.

[0093] The first decoupling module is used to divide the multi-time period and multi-scenario SCUC model based on the multi-time period decoupling mechanism and establish SCUC sub-problems for different time periods.

[0094] The second decoupling module is used to divide the SCUC model into multiple time periods and multiple scenarios based on the multi-scenario decoupling mechanism, and to establish SCUC sub-problems for different scenarios according to the climbing coupling constraints.

[0095] The data analysis and processing module is used to perform parallel computation based on the target cascaded analysis algorithm to solve the SCUC subproblems at different time periods and in different scenarios.

[0096] An apparatus includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, performs the steps of the method as described in any of the preceding items.

[0097] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method as described in any of the preceding claims.

[0098] Compared with the prior art, the present invention has the following beneficial effects:

[0099] This invention proposes a multi-time-period, multi-scenario SCUC decoupling method. Based on the uncertainties of hydropower, a multi-time-period, multi-scenario SCUC model is established to obtain an equivalent single-station hydropower system. By considering the multi-time-period and multi-scenario decoupling mechanism, multi-time-period sub-problems and multi-scenario sub-problems are obtained. Parallel computing is used to achieve decoupling and accelerated computation of the SCUC problem, ensuring that the solution time of the multi-time-period, multi-scenario SCUC model for hydropower units connected to the power system is effectively reduced within an acceptable confidence level.

[0100] Furthermore, a data initialization method is established through a supervised BP neural network, ignoring consistency constraints to solve each subproblem in parallel and obtain the corresponding results. The results close to the optimal solution are used as the initial values ​​for the target cascade analysis, which accelerates the convergence speed of the parallel computation of subproblems. Attached Figure Description

[0101] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0102] Figure 1 This is a flowchart of the multi-time-period, multi-scenario safety constraint unit combination decoupling method of the present invention;

[0103] Figure 2 This is a schematic diagram of the multi-time-period, multi-scenario safety constraint unit combination decoupling system module of the present invention;

[0104] Figure 3 This is a linearized curve of the power output performance of the hydropower station used in this invention.

[0105] Figure 4 (a) is the original hydropower system topology diagram, and (b) is the equivalent hydropower single-station system topology diagram;

[0106] Figure 5 This is a schematic diagram of the time-period decoupling proposed in this invention;

[0107] Figure 6 This is a schematic diagram of the S-BPNN used in this invention;

[0108] Figure 7Here is a flowchart of the ATC algorithm proposed in this invention;

[0109] Figure 8 The equivalent single-station system reservoir capacity change curve obtained using the traditional centralized algorithm;

[0110] Figure 9 The equivalent single-station system reservoir capacity change curve is obtained using a parallel solution algorithm. Detailed Implementation

[0111] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0112] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0113] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0114] In the description of the embodiments of the present invention, it should be noted that if terms such as "upper," "lower," "horizontal," or "inner" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship commonly used when the product of the invention is in use, they are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention. Furthermore, terms such as "first" and "second" are only used to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0115] Furthermore, the use of the term "horizontal" does not imply that the component must be absolutely horizontal, but rather that it can be slightly tilted. For example, "horizontal" simply means that its direction is more horizontal than "vertical," and does not mean that the structure must be completely horizontal, but can be slightly tilted.

[0116] In the description of the embodiments of the present invention, it should also be noted that, unless otherwise explicitly specified and limited, the terms "set," "install," "connect," and "link" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in the present invention according to the specific circumstances.

[0117] The present invention will now be described in further detail with reference to the accompanying drawings:

[0118] See Figure 1 The flowchart below illustrates a multi-time-period, multi-scenario safety constraint unit combination decoupling method according to the present invention, which specifically includes the following steps:

[0119] S1. Based on the uncertainty of hydropower, a multi-time period and multi-scenario SCUC model is established.

[0120] Considering the uncertainties of hydropower, a multi-time period and multi-scenario SCUC model is established.

[0121] The objective function for minimizing the operating cost of the power system is:

[0122]

[0123] Where, x n The variables in the SCUC model include thermal power unit output, hydropower unit output, hydropower station discharge, hydropower station overflow, and unit start-up and shutdown state variables; n is the random scenario number; N is the total number of random scenarios; π n Let Σπ represent the probability of a random scenario n, and let Σπ represent the probability of a random scenario n. n =1; t is the time period number; T is the total number of time periods; y is the thermal power unit number; Y is the total number of thermal power units; the subscript b indicates the baseline scenario; f n (p t,y,n ,z t,y,n ) represents the operating cost of the power system under random scenario n; f b (p t,y,n ,z t,y,n ) represents the power system operating cost under baseline scenario b; p t,y,n The output of thermal power unit y under random scenario n in time period t; z t,y,n This represents the start-up and shutdown status of thermal power unit y under random scenario n in time period t, where 1 represents start-up and 0 represents shutdown; p t,y,b The output of thermal power unit y under the baseline scenario b at time period t; z t,y,bThe start-up and shutdown status of thermal power unit y in the baseline scenario b during time period t is represented by 1, where 1 represents start-up and 0 represents shutdown.

[0124] Its constraints are:

[0125]

[0126]

[0127]

[0128] Among them, h n (x n ) / h b (x b This includes constraints such as power balance and reservoir capacity balance of cascade hydropower stations; g n (x n ) / g b (x b This includes inequality constraints such as output limits for thermal power units, output limits for hydropower units, capacity limits for cascade hydropower reservoirs, and ramping constraints for thermal power units. This refers to the uphill / downhill ramp limit for thermal power unit y.

[0129] S2 obtains cascade hydropower parameters from a multi-time period and multi-scenario SCUC model, establishes the original cascade hydropower system, and converts the original cascade hydropower system into a single hydropower station system.

[0130] Considering the cascade hydropower parameters included in the SCUC model, a two-level optimization modeling method is used to determine the parameters of the equivalent single-station hydropower system. An original cascade hydropower system model is established, which is influenced by the following factors: the topology between the cascade hydropower stations, the power output performance curves of the hydropower stations, random inflow, reservoir capacity constraints, initial reservoir capacity values, and reservoir overflow. (See also...) Figure 3 This was achieved by linearizing the power output performance curve of the hydropower station. (See also...) Figure 4 The original hydropower system is equivalent to a single-station system through a two-layer optimization modeling method.

[0131] The objective function of the cascade hydropower revenue maximization model is:

[0132]

[0133] Wherein, the superscript O represents the original cascade hydropower system; λ t I is the electricity price for time period t; i is the hydroelectric power station number; I o is the number of hydropower stations in the original cascade hydropower model; k is the linearized segment number of the hydropower station's output performance curve; K is the number of linearized segments of the hydropower station's output performance curve. It is the output performance coefficient of the k-th linearized segment of the i-th hydropower station; λ is the water output of hydropower station i in the k-th segment of time period t; F It is a forecast of future electricity prices; It is the reservoir capacity of hydropower station i during time period T; This is a binary parameter. It is 1 when hydropower station j is a downstream power station of hydropower station i, and 0 otherwise. It is the future predicted output performance coefficient of hydropower station j.

[0134] Storage capacity balance constraints:

[0135]

[0136] in, Let be the overflow discharge of hydropower station i during time period t; Let be the inflow rate of hydropower station i during time period t; Let i be the set of upstream hydropower stations.

[0137] Initial storage capacity constraints:

[0138]

[0139] in, It is the percentage of the initial reservoir capacity of hydropower station i to the total reservoir capacity; Let be the maximum reservoir capacity of hydropower station i.

[0140] Water output limits:

[0141]

[0142] in It is the minimum water output of hydropower station i in the k-th segment; It is the maximum water output of hydropower station i in the k-th segment.

[0143] Storage capacity constraints:

[0144]

[0145] in, It is the minimum reservoir capacity of hydropower station i.

[0146] Overflow flow limit constraints:

[0147]

[0148] in, It is the minimum overflow of hydropower station i; It is the maximum overflow of hydropower station i.

[0149] A two-level optimization model is established to obtain the parameters of the equivalent single-station model. The objective is to minimize the revenue difference between the original cascade hydropower system and the equivalent single-station system; the objective function is:

[0150]

[0151] The superscript E indicates an equivalent single-station system.

[0152] The constraints of the upper-level model are as follows.

[0153] Equivalent single-station system hydropower station output performance coefficient limit:

[0154]

[0155] Equivalent single-station system hydropower station future projected output performance coefficient limit:

[0156]

[0157] The objective function of the lower-level model is:

[0158]

[0159] The constraints are:

[0160]

[0161]

[0162]

[0163]

[0164]

[0165] The lower-level model is transformed into an equivalent constraint condition using the Karush-Kuhn-Tucker (KKT) conditions and the Big M method to obtain an equivalent single-level model. The equivalent constraint conditions of the lower-level model are as follows:

[0166]

[0167]

[0168]

[0169]

[0170]

[0171]

[0172]

[0173]

[0174]

[0175]

[0176]

[0177]

[0178]

[0179]

[0180]

[0181]

[0182]

[0183]

[0184]

[0185]

[0186] in, and They are Lagrange multipliers; and These are Boolean variables; M3 to M8 are sufficiently large numbers.

[0187] To expedite the calculation of the equivalent single-level model, some parameters of the equivalent single-station system are calculated using the initial hydropower energy of the original cascade hydropower system. The initial hydropower energy calculation formula for the original cascade hydropower system is as follows:

[0188]

[0189] Among them, E O This represents the initial hydropower energy of the original cascade hydropower system.

[0190] The output performance coefficient of the first linearized segment of the equivalent single-station system is:

[0191]

[0192] in, It is the output performance curve of the first linearized segment of the equivalent single-station system; r iLet i be the total inflow of hydropower station i.

[0193] The initial storage capacity of the equivalent single-station system is:

[0194]

[0195] in, This represents the initial storage capacity of an equivalent single-station system.

[0196] S3, based on the multi-time period decoupling mechanism, divides the SCUC model into multi-time period and multi-scenario, and establishes SCUC sub-problems for different time periods.

[0197] A multi-period decoupling mechanism is used to establish SCUC sub-problems divided according to time periods, enabling time-period decoupling. SCUC models for different scenarios are divided into different time periods, and corresponding SCUC sub-problems are modeled for each time period. To ensure the feasibility of SCUC solutions, penalty terms are added to the objective functions of the sub-problems, and consistency constraints are added to the sub-models. See [link / reference] Figure 5 Without loss of generality, we assume that the SCUC model for different scenarios is divided into 3 time periods, denoted as c. - c and c + The corresponding SCUC subproblems are denoted as SP. c- SP c and SP c+ Subproblem SP c- The corresponding time period is from 1 to t. c- +1, its objective function is:

[0198]

[0199] Where, x c- It is a subproblem SP c- The variable groups include thermal power unit output, hydropower unit output, hydropower station discharge, hydropower station overflow, and unit start-up and shutdown status variables.

[0200] The constraints are:

[0201] h c- (x c- )=0&g c- (x c- )≤0,t={1,...,t c- +1}

[0202] Subproblem SP c The corresponding time period is t c- +1 to t c +1, its objective function is:

[0203]

[0204] The constraints are:

[0205] h c (x c )=0&g c (x c )≤0,t={t c- +1,...,t c +1}

[0206] Subproblem SP c+ The corresponding time period is t c From +1 to T, the objective function is:

[0207]

[0208] The constraints are:

[0209] h c+ (x c+ )=0&g c+ (x c+ )≤0,t={t c +1,...,t c+}

[0210] The subscripts (.,.) are introduced to denote the coupling variables obtained from the model on the left. The concept of a coupling time period is introduced, where the time period is divided into three segments, denoted as t. a =t c- +1 and t b =t c +1.

[0211] To ensure the feasibility of the solution to the SCUC problem, the following consistency constraints are added to the constraints of the subproblems.

[0212] The consistency constraints for thermal power units are:

[0213]

[0214]

[0215] The consistency constraint for the reservoir capacity of a hydropower station is:

[0216]

[0217]

[0218] To model the minimum start / stop time of thermal power units between two consecutive sub-time periods, a pair of start / stop variables is used. This pair of variables represents the thermal power unit y during sub-time period c. -The duration of continuous operation / shutdown within the last time period. The minimum remaining operation / shutdown duration that thermal power unit y needs to satisfy in sub-time period c. for:

[0219]

[0220]

[0221] in, This represents the shortest start-up / shutdown time for thermal power unit y.

[0222] In subproblem SP c Set a stop indicator sign in the middle. Its value is equal to the first shutdown time t of thermal power unit y in sub-time period c. The Big M method is used to model the first shutdown time t of thermal power unit y in sub-time period c. This is derived from the sub-model SP. c The obtained thermal power unit n in sub-time period c - The minimum remaining power-on time required is:

[0223]

[0224] M1 is a sufficiently large number.

[0225] Similarly, from the subproblem SP c The obtained thermal power unit y in sub-time period c - The minimum remaining downtime that needs to be satisfied is:

[0226]

[0227] M2 is a sufficiently large number.

[0228] Thermal power unit y in subproblem SP c- Sum Problem SP c The minimum start / stop consistency constraint that the boundary needs to satisfy is:

[0229]

[0230]

[0231]

[0232] Thermal power unit y in subproblem SP c Sum Problem SP c+ The minimum start / stop consistency constraint that the boundary needs to satisfy is:

[0233]

[0234]

[0235]

[0236] S4, based on the multi-scenario decoupling mechanism, divides the SCUC model into multi-time period and multi-scenario models, and establishes SCUC sub-problems for different scenarios according to the climbing coupling constraints.

[0237] A SCUC subproblem based on ramp coupling constraints is established based on a multi-scenario decoupling mechanism to facilitate scenario decoupling. For simplicity, a random scenario n with an equivalent single-station system and a baseline scenario b are used as examples. The multi-scenario decoupling mechanism adopts a strategy similar to the multi-time-period decoupling mechanism, that is, a penalty term is added to the objective function of random scenario n and baseline scenario b, and consistency constraints are added to the model. The power system needs to maintain power balance at all times. Under load or hydropower output fluctuations, thermal power units need to adjust their output power within a specific time period to meet the power balance condition. This means that within each time period t, the same thermal power unit y in different random scenarios n needs to satisfy the following ramp constraint with the corresponding thermal power unit y in baseline scenario b, and this constraint needs to be added to random scenario n:

[0238]

[0239] in, This represents the maximum uphill / downhill gradient of thermal power unit y.

[0240] The output of the baseline scenario calculated in random scenario n should also meet the output limit of thermal power units:

[0241]

[0242] The consistency constraints that need to be added to the random scenario n and the baseline scenario b are as follows:

[0243]

[0244]

[0245] S5 performs parallel computation based on the target cascade analysis algorithm to solve SCUC subproblems at different time periods and in different scenarios.

[0246] A data initialization method based on supervised BP neural networks is established to accelerate the convergence speed of parallel computation of subproblems.

[0247] See Figure 6The supervised backpropagation (BP) neural network process mainly consists of two stages. The first stage involves the signal propagating backward from the input layer to the hidden layers and finally to the output layer. The second stage involves the error propagating forward from the output layer to the hidden layers and finally to the input layer. During backward propagation, the weights and biases of the data are adjusted sequentially. The goal is to roughly estimate the expected reservoir capacity of the equivalent single-station system at the end of a specific period, based on the initial reservoir capacity, inflow, and load demand at the beginning of that period. The following activation function is used to ensure the model is usable in both linear and nonlinear cases:

[0248]

[0249] Where 'a' represents the input data.

[0250] Using the acquired historical dataset, 70% was used for model learning, 15% for model validation, and 15% for model performance testing.

[0251] For the initialization of other variables, such as power generation and the start-up and shutdown status of thermal power units, each subproblem is solved in parallel, ignoring consistency constraints, and the corresponding results are obtained. These results, due to the lack of interconnection with consistency constraints, may be infeasible solutions, but are close to the optimal solution; therefore, these results can be used as initial values ​​for the objective cascade analysis.

[0252] See Figure 7 The goal cascade analysis algorithm is used for parallel computation of subproblems. Its basic principle is to decompose the entire optimization problem into different subproblems, introduce a coordinator to coordinate and optimize the shared variables of each subproblem, allowing each subproblem to be solved in parallel until the convergence condition is met. While optimizing its own model, each subproblem introduces a penalty term to ensure that the shared variables of each subproblem tend to be consistent. An augmented Lagrangian function is used as the penalty term to punish violations of consistency constraints. The set of shared variables *e* in the coordinator is denoted as the goal variable set, and the shared variable *γ* in each subproblem is denoted as the response variable set.

[0253] Subproblems SP of random scenario n c- The objective function is remodeled as follows:

[0254]

[0255] Where h is the number of iterations of the target cascade analysis algorithm; the target variable set e h Obtained from the coordinator; ζ h ρ is the set of Lagrange multiplier vectors; ρ is the penalty factor.

[0256] SP, a subproblem of random scenario n c The objective function is remodeled as follows:

[0257]

[0258] SP, a subproblem of random scenario n c+ The objective function is remodeled as follows:

[0259]

[0260] Similarly, the subproblem SP of baseline scenario b c- The objective function is remodeled as follows:

[0261]

[0262] Subproblem SP of baseline scenario b c The objective function is remodeled as follows:

[0263]

[0264] Subproblem SP of baseline scenario b c+ The objective function is remodeled as follows:

[0265]

[0266] The update of the target variable group in the coordinator is as follows:

[0267] e h =arg min(ζ) T (e h -γ h )+ρ||e h -γ h || 2

[0268] When the coordinator receives the response variable set γ from each subproblem h Afterwards, solving the coordinator mathematical model yields the updated target variable set e. h .

[0269] The update of the Lagrange multiplier vector set is as follows:

[0270] ζ h =ζ h-1 +2ρ 2 |e h -γ h |

[0271] The convergence condition is:

[0272] |e h -γ h |≤ε

[0273] Where ε represents the convergence accuracy.

[0274] Finally, the computational efficiency of the multi-time-period, multi-scenario SCUC problem considering the uncertainties of hydropower is improved by solving the optimization problem in parallel.

[0275] See Figure 2 The diagram below illustrates the multi-time-period, multi-scenario SCUC decoupling system modules of this invention, specifically including the following modules:

[0276] The model building module is used to build a multi-time period and multi-scenario SCUC model based on the uncertainty of hydropower.

[0277] The system equivalent module is used to obtain cascade hydropower parameters from a multi-time period and multi-scenario SCUC model, establish the original cascade hydropower system, and convert the original cascade hydropower system into a single hydropower station system.

[0278] The first decoupling module is used to divide the multi-time period and multi-scenario SCUC model based on the multi-time period decoupling mechanism and establish SCUC sub-problems for different time periods.

[0279] The second decoupling module is used to divide the SCUC model into multiple time periods and multiple scenarios based on the multi-scenario decoupling mechanism, and to establish SCUC sub-problems for different scenarios according to the climbing coupling constraints.

[0280] The data analysis and processing module is used to perform parallel computation based on the target cascaded analysis algorithm to solve the SCUC subproblems at different time periods and in different scenarios.

[0281] See Figures 8-9 The figures show the equivalent single-station system reservoir capacity change curves obtained using the traditional centralized algorithm and the parallel solution algorithm, respectively. By observing these two curves, it can be seen that the reservoir capacity curve obtained by the parallel solution algorithm is similar to that obtained by the traditional centralized algorithm, which demonstrates the effectiveness of the parallel solution algorithm proposed in this invention.

[0282] Refer to Tables 1-3 for the solution times of different algorithms. A 5-hour time limit is set as the upper limit; if the solution time exceeds 5 hours, the problem is considered unsolvable. As the number of scenarios increases, the traditional centralized algorithm takes the longest to solve the SCUC problem with the original hydroelectric system, while the parallel algorithm takes the shortest time to solve the SCUC problem with the equivalent single-station system. When the number of scenarios increases to 15, the traditional centralized algorithm becomes unsolvable for the SCUC problem with the original hydroelectric system; when the number of scenarios increases to 25, the traditional centralized algorithm also becomes unsolvable for the SCUC problem with the equivalent single-station system. Compared to the traditional centralized algorithm, the parallel algorithm has a shorter solution time; however, as the number of scenarios increases, the CPU and RAM utilization increases during computation, resulting in a slight increase in the solution time of the parallel algorithm.

[0283] Table 1. Solving SCUC models with original hydropower systems using traditional centralized algorithms

[0284] Number of scenes 5 10 15 20 25 Solution time 2.44h 4.78h - - -

[0285] Table 2. Solving SCUC models with equivalent single-station systems using traditional centralized algorithms.

[0286] Number of scenes 5 10 15 20 25 Solution time 2653s 1.74h 2.93h 4.23h -

[0287] Table 3. Solving the SCUC model with equivalent single-station system using parallel solution algorithms

[0288] Number of scenes 5 10 15 20 25 Solution time 43.2s 47.7s 51.3s 53.4s 55.8s

[0289] Therefore, compared with traditional centralized algorithms, the parallel solution algorithm proposed in this invention can ensure the effectiveness of the results while significantly reducing the solution time of multi-time and multi-scenario SCUC models.

[0290] One embodiment of the present invention provides a terminal device. This terminal device includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps in the above-described embodiments of the security constraint unit combination decoupling methods. Alternatively, when the processor executes the computer program, it implements the functions of each module / unit in the above-described device embodiments.

[0291] The computer program can be divided into one or more modules / units, which are stored in the memory and executed by the processor to complete the present invention.

[0292] The security constraint unit combination decoupling device / terminal equipment can be a desktop computer, laptop, handheld computer, or cloud server, etc. The security constraint unit combination decoupling device / terminal equipment may include, but is not limited to, processors and memory.

[0293] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0294] The memory can be used to store the computer program and / or module. The processor implements various functions of the safety constraint unit combination decoupling device / terminal equipment by running or executing the computer program and / or module stored in the memory and calling the data stored in the memory.

[0295] If the modules / units integrated by the safety constraint unit combination decoupling device / terminal equipment are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content contained in the computer-readable medium may be appropriately added to or subtracted from the content as required by the legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium may not include electrical carrier signals and telecommunication signals.

[0296] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A multi-time-period, multi-scenario SCUC decoupling method, characterized in that, Includes the following steps: Based on the uncertainties of hydropower, a multi-time period and multi-scenario SCUC model is established; The parameters of cascade hydropower are obtained from the multi-time period and multi-scenario SCUC model, the original cascade hydropower system is established, and the original cascade hydropower system is equivalent to a single hydropower station system. Based on the multi-time period decoupling mechanism, the SCUC model is divided into multi-time period and multi-scenario, and SCUC sub-problems are established for different time periods; Based on the multi-scenario decoupling mechanism, a multi-time period and multi-scenario SCUC model is divided, and SCUC sub-problems are established for different scenarios according to the climbing coupling constraints. Parallel computation is performed based on the target cascade analysis algorithm to solve the SCUC subproblems at different time periods and in different scenarios; The establishment of the multi-time-period, multi-scenario SCUC model is specifically represented as follows: The objective function is to minimize the operating cost of the power system. in, x n The variable group in the SCUC model includes the output of thermal power units, the output of hydropower units, the discharge of hydropower stations, the overflow of hydropower stations, and the start-up and shutdown state variables of the units; n Random scene number; N The total number of random scenes; π n Represents a random scene n The probability, and Σ π n =1; t Number the time period; T Total number of time periods; y Number the thermal power units; Y Total number of thermal power units; subscript b Represents the baseline scenario; f n ( p t,y,n ,z t,y,n ) represents a random scenario n The operating cost of the power system under the following conditions; f b ( p t,y,n ,z t,y,n () represents the baseline scenario b The operating cost of the power system under the following conditions; p t,y,n For thermal power units y During the period t Random Scene n The effort put in; z t,y,n For thermal power units y During the period t Random Scene n The unit's start / stop status is shown below, where 1 represents start and 0 represents stop; p t,y,b For thermal power units y During the period t Baseline scenario b The effort put in; z t,y,b For thermal power units y During the period t Baseline scenario b The unit's start / stop status is shown below, where 1 represents start and 0 represents stop; The constraints are: in, h n (x n ) / h b (x b ) Including power balance and reservoir capacity balance equation constraints for cascade hydropower stations; g n (x n ) / g b (x b ) Inequality constraints include output limits for thermal power units, output limits for hydropower units, capacity limits for cascade hydropower reservoirs, and ramping constraints for thermal power units; This refers to the uphill / downhill ramp limit for thermal power unit y.

2. The multi-time-period, multi-scenario SCUC decoupling method as described in claim 1, characterized in that, The original cascade hydropower system model is specifically represented as follows: The objective function is to maximize the benefits of the cascade hydropower system. Among them, superscript O This represents the original cascade hydropower system; λ t It is a time period t Electricity price; i It is the hydroelectric power station's serial number; I o This refers to the number of hydropower stations in the original cascade hydropower model. k It refers to the linearized segmentation numbering of the power output performance curve of a hydropower station; K It is the number of segments in the linearization of the power output performance curve of a hydropower station; It is a hydroelectric power station i No. k The output performance coefficient of each linearized segment; It is a hydroelectric power station i During the period t The k Section water output; λ F It is a forecast of future electricity prices; It is a hydroelectric power station i During the period T Storage capacity; For a binary parameter, when the hydropower station j It is a hydroelectric power station i If the downstream power station is a 1, it is recorded as 1; otherwise, it is recorded as 0. It is a hydroelectric power station j The future projected output performance coefficient; Storage capacity balance constraints: in, For hydroelectric power station i During the period t Overflow flow; For hydroelectric power station i During the period t Inflow; For hydroelectric power station i The collection of upstream hydropower stations; Initial storage capacity constraints: in, It is a hydroelectric power station i The percentage of initial storage capacity relative to total storage capacity; For hydroelectric power station i Maximum storage capacity; Water output limits: in, It is a hydroelectric power station i In the k Minimum discharge rate of the section; It is a hydroelectric power station i In the k Maximum water output of the section; Storage capacity constraints: in, It is a hydroelectric power station i Minimum storage capacity; Overflow flow limit constraints: in, It is a hydroelectric power station i Minimum overflow; It is a hydroelectric power station i The maximum overflow.

3. The multi-time-period, multi-scenario SCUC decoupling method as described in claim 1, characterized in that, The original cascade hydropower system is equivalent to a single hydropower station system through a two-layer optimization model, specifically represented as follows: Minimizing the revenue difference between the original cascade hydropower system and the single hydropower station system is taken as the objective function of the upper-level model: The constraints of the upper-level model are: Hydropower single-station system output performance coefficient limit: Limitations on the future projected output performance coefficient of a single hydropower station system: The objective function of the lower-level model is: The constraints of the lower-level model are: The lower-level model is transformed into equivalent constraint conditions using KKT conditions and the Big M method, resulting in an equivalent single-level model. Based on the initial hydropower energy of the original cascade hydropower system, the parameters of the single hydropower station system are calculated. The initial hydropower energy of the original cascade hydropower system is: in, E O This represents the initial hydropower energy of the original cascade hydropower system. The output performance coefficient of the first linearized segment of the hydropower single-station system is: in, It is the output performance curve of the first linearized segment of the equivalent single-station system; r i For hydroelectric power station i Total inflow; The initial reservoir capacity of a single hydropower station system is: in, This represents the initial storage capacity of an equivalent single-station system.

4. The multi-time-period, multi-scenario SCUC decoupling method as described in claim 1, characterized in that, The multi-time-period, multi-scenario SCUC model is divided based on a multi-time-period decoupling mechanism, and SCUC sub-problems for different time periods are established. The specific representations of the SCUC sub-problems for different time periods are as follows: Suppose the SCUC model for different scenarios is divided into three time periods, and the corresponding time periods are as follows: c - , c and c + The corresponding SCUC subproblems are as follows: SP c- , SP c and SP c+ ; SCUC subproblems SP c- The corresponding time period is from 1 to t c- +1, the objective function is: The constraints are: SCUC subproblems SP c The corresponding time period is t c- +1 to t c +1, the objective function is: The constraints are: SCUC subproblems SP c+ The corresponding time period is t c +1 to T The objective function is: The constraints are: in, x c- , x c and x c+ Subproblems SP c- , SP c and SP c+ The variable group includes the output of thermal power units, the output of hydropower units, the discharge of hydropower stations, the overflow of hydropower stations, and the start-up and shutdown status variables of the units.

5. The multi-time-period, multi-scenario SCUC decoupling method as described in claim 1, characterized in that, The multi-scenario decoupling mechanism-based SCUC model is divided into multi-time-period, multi-scenario sub-problems. Specifically, a penalty term and a consistency constraint are added to the objective functions of the random and baseline scenarios of the hydropower single-station system. This ensures that, within each time period, the same thermal power unit in different random scenarios satisfies the climbing constraint as well as the corresponding thermal power unit in the baseline scenario. The climbing constraint is expressed as: The output of the baseline scenario in the random scenario meets the output limit of the thermal power unit, specifically as follows: The consistency constraints added to the random scenario and the baseline scenario are specifically expressed as follows: in, Indicates thermal power unit y Maximum uphill / downhill gradient.

6. The multi-time-period, multi-scenario SCUC decoupling method as described in claim 1, characterized in that, When the target cascade analysis algorithm performs parallel computation, a coordinator is introduced to coordinate and optimize the SCUC subproblems, and each subproblem is solved in parallel until the convergence condition is met; the initial value of the target cascade analysis is obtained through a supervised BP neural network.

7. A multi-time-period, multi-scenario SCUC decoupling system, characterized in that, Includes the following modules: The model building module is used to build a multi-time period and multi-scenario SCUC model based on the uncertainty of hydropower. The system equivalent module is used to obtain cascade hydropower parameters from a multi-time period and multi-scenario SCUC model, establish the original cascade hydropower system, and convert the original cascade hydropower system into a single hydropower station system. The first decoupling module is used to divide the multi-time period and multi-scenario SCUC model based on the multi-time period decoupling mechanism and establish SCUC sub-problems for different time periods. The second decoupling module is used to divide the SCUC model into multiple time periods and multiple scenarios based on the multi-scenario decoupling mechanism, and to establish SCUC sub-problems for different scenarios according to the climbing coupling constraints. The data analysis and processing module is used to perform parallel computation based on the target cascade analysis algorithm to solve the SCUC subproblems at different time periods and in different scenarios. The establishment of the multi-time-period, multi-scenario SCUC model is specifically represented as follows: The objective function is to minimize the operating cost of the power system. in, x n The variable group in the SCUC model includes the output of thermal power units, the output of hydropower units, the discharge of hydropower stations, the overflow of hydropower stations, and the start-up and shutdown state variables of the units; n Random scene number; N The total number of random scenes; π n Represents a random scene n The probability, and Σ π n =1; t Number the time period; T Total number of time periods; y Number the thermal power units; Y Total number of thermal power units; subscript b Represents the baseline scenario; f n ( p t,y,n ,z t,y,n ) represents a random scenario n The operating cost of the power system under the following conditions; f b ( p t,y,n ,z t,y,n () represents the baseline scenario b The operating cost of the power system under the following conditions; p t,y,n For thermal power units y During the period t Random Scene n The effort put in; z t,y,n For thermal power units y During the period t Random Scene n The unit's start / stop status is shown below, where 1 represents start and 0 represents stop; p t,y,b For thermal power units y During the period t Baseline scenario b The effort put in; z t,y,b For thermal power units y During the period t Baseline scenario b The unit's start / stop status is shown below, where 1 represents start and 0 represents stop; The constraints are: in, h n (x n ) / h b (x b ) Including power balance and reservoir capacity balance equation constraints for cascade hydropower stations; g n (x n ) / g b (x b ) Inequality constraints include output limits for thermal power units, output limits for hydropower units, capacity limits for cascade hydropower reservoirs, and ramping constraints for thermal power units; This refers to the uphill / downhill ramp limit for thermal power unit y.

8. An apparatus comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1-6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1-6.

Images