Power Resource Processing Method, Device and Computer Equipment Based on Genetic Algorithm

Abstract

The present application relates to a power resource processing method, apparatus, computer device, storage medium, and computer program product based on a genetic algorithm. The method includes: obtaining an increase in virtual resources for an electricity load, a virtual resource description limit value, and an initial resource description information set corresponding to each electricity load aggregation end recorded in a resource interaction platform; for each initial resource description information set, constructing a first model with the goal that the result of resource interaction meets a first preset condition and a second model with the goal that the result of resource transfer meets a second preset condition according to the increase in virtual resources and the virtual resource description limit value; constructing a target resource description information model according to the first model and the second model; and iteratively optimizing the initial resource description information set in the target resource description information model through a genetic algorithm to obtain target resource description information for indicating resource interaction. Using this method can improve the utilization efficiency of power resources.

Description

Technical Field

[0001] The present application relates to the field of power technologies, and particularly to a power resource processing method, apparatus, computer device, storage medium, and computer program product based on a genetic algorithm. Background Art

[0002] With the development of power technologies in China, the power demand in China has been continuously increasing. In order to effectively guide and control the growth of the load during peak grid hours, it is necessary to use, to a certain extent, regulation resources on the power consumption side that are equivalent to those on the power generation side to improve the overall utilization efficiency of power resources.

[0003] However, in traditional technologies, when using power resource description information for resource scheduling, due to inaccurate power resource description information, the resource interaction effect between the power consumption side and the power generation side is poor, and the utilization efficiency of power resources cannot be improved.

[0004] Therefore, there is a problem of low utilization efficiency of power resources in traditional technologies. Summary of the Invention

[0005] Based on this, it is necessary to provide a power resource processing method, apparatus, computer device, computer-readable storage medium, and computer program product based on a genetic algorithm that can improve the utilization efficiency of power resources for the above technical problems.

[0006] In a first aspect, the present application provides a power resource processing method based on a genetic algorithm. The method includes:

[0007] Obtain the virtual resource increment for the power consumption load, the virtual resource description limit value, and the initial resource description information set corresponding to each power consumption load aggregation end recorded in the resource interaction platform; the resource interaction platform is used for resource interaction between the power consumption side and the power generation side; the power consumption load aggregation end is used for resource transfer between the power consumption side and the power generation side;

[0008] For each of the initial resource description information sets, according to the virtual resource increment and the virtual resource description limit value, construct a first model with the goal that the result of the resource interaction satisfies a first preset condition, and construct a second model with the goal that the result of the resource transfer satisfies a second preset condition;

[0009] Construct a target resource description information model according to the first model and the second model;

[0010] Iteratively optimize the initial resource description information set in the target resource description information model through a genetic algorithm to obtain target resource description information; the target resource description information is used to indicate resource interaction between the power consumption side and the power generation side.

[0011] In one embodiment, for each of the initial resource description information sets, a first model is constructed with the goal that the result of resource interaction satisfies a first preset condition, and a second model is constructed with the goal that the result of resource transfer satisfies a second preset condition according to the virtual resource increase amount and the virtual resource description limit value, including:

[0012] Construct a first objective function of the first model according to the virtual resource increase amount; the first objective function aims at the result of resource interaction satisfying the first preset condition;

[0013] Construct a first constraint condition of the first model according to the first security constraint and the second security constraint;

[0014] Construct the first model according to the first objective function and the first constraint condition.

[0015] In one embodiment, the resource interaction platform includes a first resource interaction platform and a second resource interaction platform; the virtual resource increase amount includes a first virtual resource increase amount corresponding to the first resource interaction platform and a second virtual resource increase amount corresponding to the second resource interaction platform; the constructing a first objective function of the first model according to the virtual resource increase amount includes:

[0016] For the first resource interaction platform, determine a first resource description function corresponding to the power generation side and a second resource description function corresponding to the power consumption side;

[0017] For the second resource interaction platform, determine a third resource description function corresponding to the power generation side and a fourth resource description function corresponding to the power consumption side;

[0018] Construct the first objective function according to the first resource description function, the second resource description function, the third resource description function, the fourth resource description function, the first virtual resource increase amount and the second virtual resource increase amount.

[0019] In one embodiment, the determining a first resource description function corresponding to the power generation side and a second resource description function corresponding to the power consumption side for the first resource interaction platform includes:

[0020] Determine the power generation power of the generator set on the power generation side for the first resource interaction platform in the current time period;

[0021] Determine the second resource description function according to the power generation power;

[0022] For the second resource interaction platform, determining a third resource description function corresponding to the power generation side and a fourth resource description function corresponding to the power consumption side includes:

[0023] Determining the target capacity of the generator set on the power generation side for the second resource interaction platform during the current time period;

[0024] Determining the fourth resource description function according to the target capacity.

[0025] In one embodiment, for each of the initial resource description information sets, constructing a first model with the goal that the result of resource interaction satisfies a first preset condition and constructing a second model with the goal that the result of resource transfer satisfies a second preset condition according to the virtual resource increase amount and the virtual resource description limit includes:

[0026] Obtaining the virtual resource description mean value for the power consumption load recorded in the resource interaction platform;

[0027] Determining the target power consumption of the power consumption load aggregation end for the power consumption load according to the initial resource description information set;

[0028] Constructing a second objective function of the second model according to the virtual resource description mean value and the target power consumption; the second objective function aims at the result of resource transfer satisfying the second preset condition;

[0029] Constructing a second constraint condition of the second model according to the virtual resource description limit;

[0030] Constructing the second model according to the second objective function and the second constraint condition.

[0031] In one embodiment, iteratively optimizing the initial resource description information set in the target resource description information model by using a genetic algorithm to obtain the target resource description information includes:

[0032] Obtaining the fitness of the mutant individuals obtained according to the second model;

[0033] Determining the fitness of the current population according to the fitness of the mutant individuals;

[0034] Determining the selection probability of the current population according to the fitness of the current population and the fitness of each population;

[0035] Determining the crossover probability and mutation probability corresponding to the genetic algorithm;

[0036] Iteratively optimizing the initial resource description information set according to the selection probability, the crossover probability and the mutation probability to obtain the target resource description information.

[0037] In a second aspect, the present application also provides a power resource processing device based on a genetic algorithm. The device includes:

[0038] An acquisition module, configured to acquire the virtual resource increment for the power consumption load, the virtual resource description limit value, and the initial resource description information set corresponding to each power consumption load aggregation end recorded in the resource interaction platform; the resource interaction platform is used for resource interaction between the power consumption side and the power generation side; the power consumption load aggregation end is used for resource transfer between the power consumption side and the power generation side;

[0039] A first construction module, configured to, for each of the initial resource description information sets, construct a first model with the result of the resource interaction satisfying a first preset condition as the goal and construct a second model with the result of the resource transfer satisfying a second preset condition as the goal according to the virtual resource increment and the virtual resource description limit value;

[0040] A second construction module, configured to construct a target resource description information model according to the first model and the second model;

[0041] An optimization module, configured to iteratively optimize the initial resource description information set in the target resource description information model through a genetic algorithm to obtain target resource description information; the target resource description information is used to indicate resource interaction between the power consumption side and the power generation side.

[0042] In a third aspect, the present application also provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0043] Acquire the virtual resource increment for the power consumption load, the virtual resource description limit value, and the initial resource description information set corresponding to each power consumption load aggregation end recorded in the resource interaction platform; the resource interaction platform is used for resource interaction between the power consumption side and the power generation side; the power consumption load aggregation end is used for resource transfer between the power consumption side and the power generation side;

[0044] For each of the initial resource description information sets, construct a first model with the result of the resource interaction satisfying a first preset condition as the goal and construct a second model with the result of the resource transfer satisfying a second preset condition as the goal according to the virtual resource increment and the virtual resource description limit value;

[0045] Construct a target resource description information model according to the first model and the second model;

[0046] Iteratively optimize the initial resource description information set in the target resource description information model through a genetic algorithm to obtain target resource description information; the target resource description information is used to indicate resource interaction between the power consumption side and the power generation side.

[0047] In a fourth aspect, the present application also provides a computer-readable storage medium. The computer-readable storage medium has a computer program stored thereon, and when the computer program is executed by a processor, the following steps are implemented:

[0048] Obtain the virtual resource increment for the power consumption load, the virtual resource description limit, and the initial resource description information sets corresponding to each power consumption load aggregation end recorded in the resource interaction platform; the resource interaction platform is used for resource interaction between the power consumption side and the power generation side; the power consumption load aggregation end is used for resource transfer between the power consumption side and the power generation side;

[0049] For each of the initial resource description information sets, according to the virtual resource increment and the virtual resource description limit, construct a first model with the goal that the result of the resource interaction meets a first preset condition, and construct a second model with the goal that the result of the resource transfer meets a second preset condition;

[0050] Construct a target resource description information model according to the first model and the second model;

[0051] Iteratively optimize the initial resource description information set in the target resource description information model through a genetic algorithm to obtain target resource description information; the target resource description information is used to indicate resource interaction between the power consumption side and the power generation side.

[0052] In a fifth aspect, the present application also provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0053] Obtain the virtual resource increment for the power consumption load, the virtual resource description limit, and the initial resource description information sets corresponding to each power consumption load aggregation end recorded in the resource interaction platform; the resource interaction platform is used for resource interaction between the power consumption side and the power generation side; the power consumption load aggregation end is used for resource transfer between the power consumption side and the power generation side;

[0054] For each of the initial resource description information sets, according to the virtual resource increment and the virtual resource description limit, construct a first model with the goal that the result of the resource interaction meets a first preset condition, and construct a second model with the goal that the result of the resource transfer meets a second preset condition;

[0055] Construct a target resource description information model based on the first model and the second model;

[0056] Iteratively optimize the initial resource description information set in the target resource description information model through a genetic algorithm to obtain target resource description information; the target resource description information is used to indicate resource interaction between the power consumption side and the power generation side.

[0057] The above power resource processing method, device, computer device, storage medium, and computer program product based on a genetic algorithm obtain the virtual resource increment for the power consumption load, the virtual resource description limit value, and the initial resource description information set corresponding to each power consumption load aggregation end recorded in the resource interaction platform; wherein, the resource interaction platform is used for resource interaction between the power consumption side and the power generation side; the power consumption load aggregation end is used for resource transfer between the power consumption side and the power generation side; then, for each initial resource description information set, according to the virtual resource increment and the virtual resource description limit value, a first model is constructed with the goal that the result of resource interaction meets the first preset condition, and a second model is constructed with the goal that the result of resource transfer meets the second preset condition; after that, a target resource description information model is constructed based on the first model and the second model; finally, the initial resource description information set is iteratively optimized in the target resource description information model through a genetic algorithm to obtain target resource description information; wherein, the target resource description information is used to indicate resource interaction between the power consumption side and the power generation side; in this way, it is ensured that the target resource description information finally output by the model can simultaneously meet the preset conditions for the resource interaction result between the power consumption side and the power generation side and the preset conditions for the resource transfer result between the power consumption side and the power generation side, thereby improving the enthusiasm of resource interaction among the power consumption side, the power generation side, and the power consumption load aggregation end, effectively utilizing power resources, and further improving the power resource utilization efficiency. Brief Description of the Drawings

[0058] Figure 1 It is a flowchart of a power resource processing method based on a genetic algorithm in an embodiment;

[0059] Figure 2 It is a flowchart of an improved genetic algorithm optimization process in an embodiment;

[0060] Figure 3 It is a flowchart of a method for solving target resource description information in an embodiment;

[0061] Figure 4 It is a flowchart of a power resource processing method based on a genetic algorithm in another embodiment;

[0062] Figure 5 It is a structural block diagram of a power resource processing device based on a genetic algorithm in an embodiment;

[0063] Figure 6 It is the internal structure diagram of a computer device in an embodiment. Detailed implementation manners

[0064] In order to make the objectives, technical solutions and advantages of the present application clearer and more understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0065] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects and do not necessarily need to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with the present disclosure. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0066] In one embodiment, as Figure 1 shown, a power resource processing method based on a genetic algorithm is provided, which can be applied to a server. The server can be an independent server or a server cluster composed of multiple servers. The method includes:

[0067] Step S110, obtaining the virtual resource increment for the electricity load, the virtual resource description limit value, and the initial resource description information set corresponding to each electricity load aggregation end recorded in the resource interaction platform.

[0068] Among them, the resource interaction platform is used for resource interaction between the power consumption side and the power generation side.

[0069] Among them, the electricity load aggregation end is used for resource transfer between the power consumption side and the power generation side.

[0070] Among them, the resource interaction platform can refer to the platform for resource interaction in a bilateral bidding power market in actual applications.

[0071] Among them, the virtual resource increment can be named the load return rate in actual applications, which refers to the multiple of the electricity load based on the real income in the bilateral bidding power market.

[0072] Among them, the virtual resource description limit value can be named the load bidding threshold in actual applications.

[0073] Among them, the power consumption load aggregation side can refer to the load aggregator in actual applications. With the continuous advancement of the power market reform, the power spot market mechanism is gradually developing towards multiple market players, and the bilateral quotation mode in the power spot market is gradually emerging. This quotation mode is "the power generation side reports quantity and price, and the power consumption side reports quantity and price". As an important coordination agency between the power grid side and the user side, the load aggregator can freely formulate quotation strategies and directly participate in the spot market competition. As an important coordination agency between the power consumption side and the user side, the load aggregator can integrate the adjustable power resources on the power consumption side and then participate in the resource scheduling and transfer between the power consumption side and the user side.

[0074] Among them, the initial resource description information set can be named as the initial quotation strategy set in actual applications.

[0075] Among them, the initial quotation strategy set includes at least the quotation for the power consumption load and the load scheduling quantity.

[0076] In specific implementation, the server can obtain the virtual resource increment for the power consumption load, the virtual description limit value, and the initial resource description information set corresponding to each power consumption load aggregation side recorded in the resource interaction platform. Among them, if each power consumption load aggregation side participating in resource interaction in the resource interaction platform is i, then the initial resource description information set corresponding to each power consumption load aggregation side is P i ={k 1i , k 2i}, so the total strategy set corresponding to all power consumption load aggregation sides is {P1, P2…, P n}.

[0077] Step S120, for each initial resource description information set, construct a first model with the goal that the result of resource interaction meets the first preset condition according to the virtual resource increment and the virtual resource description limit value, and construct a second model with the goal that the result of resource transfer meets the second preset condition.

[0078] Among them, the result of resource interaction can refer to the social total welfare in actual applications.

[0079] Among them, the first preset condition can refer to the maximization of social total welfare in actual applications.

[0080] Among them, the result of resource transfer can refer to the load aggregator's revenue in actual applications.

[0081] Among them, the second preset condition can refer to the maximization of the load aggregator's revenue in actual applications.

[0082] Among them, the first model can be the upper-layer model, and the second model can be the lower-layer model.

[0083] In specific implementation, the server can, for each initial resource description information set, construct a first model with the goal of the result of resource interaction meeting the first preset condition and construct a second model with the goal of the result of resource transfer meeting the second preset condition according to the virtual resource increment and the virtual resource description limit. Specifically, the objective function and constraint conditions corresponding to the first model and the objective function and constraint conditions corresponding to the second model can be determined according to the virtual resource increment and the virtual resource description limit, so that the first model and the second model can be established.

[0084] Step S130: Construct a target resource description information model according to the first model and the second model.

[0085] In specific implementation, the server can use the first model as the upper-layer model and the second model as the lower-layer model, and construct a two-layer model according to the upper-layer model and the lower-layer model to obtain the target resource description information model.

[0086] Step S140: Iteratively optimize the initial resource description information set in the target resource description information model through a genetic algorithm to obtain the target resource description information.

[0087] Among them, the target resource description information is used to indicate resource interaction between the power consumption side and the power generation side, and can refer to the target quotation strategy for the power consumption load in actual application.

[0088] In specific implementation, the server can iteratively optimize the initial resource description information set in the target resource description information model through a genetic algorithm, including selection, crossover, and mutation operations, until the iteration end condition is met to obtain the target quotation strategy.

[0089] In the above power resource processing method based on the genetic algorithm, the virtual resource increment for the power consumption load, the virtual resource description limit value, and the initial resource description information set corresponding to each power consumption load aggregation end recorded in the resource interaction platform are obtained; wherein, the resource interaction platform is used for resource interaction between the power consumption side and the power generation side; the power consumption load aggregation end is used for resource transfer between the power consumption side and the power generation side; then, for each initial resource description information set, according to the virtual resource increment and the virtual resource description limit value, a first model is constructed with the goal that the result of resource interaction meets the first preset condition, and a second model is constructed with the goal that the result of resource transfer meets the second preset condition; after that, a target resource description information model is constructed according to the first model and the second model; finally, the initial resource description information set is iteratively optimized in the target resource description information model through the genetic algorithm to obtain the target resource description information; wherein, the target resource description information is used to indicate resource interaction between the power consumption side and the power generation side; thus, it is ensured that the target resource description information finally output by the model can simultaneously meet the preset conditions for the resource interaction result between the power consumption side and the power generation side and the resource transfer result between the power consumption side and the power generation side, thereby improving the resource interaction enthusiasm among the power consumption side, the power generation side, and the power consumption load aggregation end, effectively utilizing power resources, and further improving the power resource utilization efficiency.

[0090] In one embodiment, for each initial resource description information set, according to the virtual resource increment and the virtual resource description limit value, constructing a first model with the goal that the result of resource interaction meets the first preset condition, and constructing a second model with the goal that the result of resource transfer meets the second preset condition includes: constructing a first objective function of the first model according to the virtual resource increment; constructing a first constraint condition of the first model according to the first security constraint and the second security constraint; and constructing the first model according to the first objective function and the first constraint condition.

[0091] Among them, the first objective function aims at the result of resource interaction meeting the first preset condition.

[0092] Among them, the first security constraint, the security constrained unit commitment (SCUC), refers to the unit start-stop and output plan planning considering the security constraints of the power system.

[0093] Among them, the second security constraint, the security constrained economic dispatch (SCED), refers to the function of formulating the multi-period unit power generation plan with the goal of minimizing the system power purchase cost and other under the condition of meeting the security constraints of the power system. SCED mainly decides the magnitude of the unit output power.

[0094] In specific implementation, when the server constructs a first model with the goal that the result of resource interaction meets a first preset condition and constructs a second model with the goal that the result of resource transfer meets a second preset condition for each initial resource description information set according to the virtual resource increment and the virtual resource description limit, the server can, according to the virtual resource increment, construct a first objective function of the first model with the goal that the result of resource interaction meets the first preset condition, that is, with the goal of maximizing the total social welfare; at the same time, construct a first constraint condition of the first model according to security constrained unit commitment (SCUC) and security constrained economic dispatch (SCED); finally, construct the first model according to the first objective function and the first constraint condition.

[0095] In practical applications, the resource interaction platform includes a first resource interaction platform and a second resource interaction platform; the virtual resource increment includes a first virtual resource increment corresponding to the first resource interaction platform and a second virtual resource increment corresponding to the second resource interaction platform; constructing the first objective function of the first model according to the virtual resource increment includes: for the first resource interaction platform, determining a first resource description function corresponding to the power generation side and a second resource description function corresponding to the power consumption side; for the second resource interaction platform, determining a third resource description function corresponding to the power generation side and a fourth resource description function corresponding to the power consumption side; constructing the first objective function according to the first resource description function, the second resource description function, the third resource description function, the fourth resource description function, the first virtual resource increment and the second virtual resource increment.

[0096] Among them, the first resource interaction platform refers to the resource interaction platform corresponding to the electricity consumption market in the bilateral bidding power market in practical applications.

[0097] Among them, the second resource interaction platform refers to the resource interaction platform corresponding to the reserve market in the bilateral bidding power market in practical applications.

[0098] Among them, the resource description function refers to the bidding function in practical applications.

[0099] Among them, the electricity load includes interruptible load, shiftable load and deferrable load.

[0100] Among them, the first resource description function is a bidding function determined by the power generation side according to the power generation cost for the electricity consumption market.

[0101] Among them, the second resource description function includes the interruptible load bidding function, the shiftable load bidding function and the deferrable load bidding function corresponding to the power consumption side for the electricity consumption market.

[0102] Among them, the third resource description function is a reserve offer function determined by the power generation side according to the power generation cost of the generating units for the reserve market.

[0103] Among them, the fourth resource description function includes a reserve offer function for the interruptible load corresponding to the electricity consumption side and a reserve offer function for the shiftable load for the reserve market.

[0104] In specific implementation, when the server constructs the first objective function of the first model according to the virtual resource increment, the server can determine, for the first resource interaction platform, the offer function determined by the power generation side according to the power generation cost of the generating units, the interruptible load offer function, the shiftable load offer function, and the shiftable load offer function corresponding to the electricity consumption side; at the same time, for the second resource interaction platform, the server can determine the reserve offer function determined by the power generation side according to the power generation cost of the generating units, the reserve offer function for the interruptible load corresponding to the electricity consumption side, and the reserve offer function for the shiftable load. Finally, the server can construct the first objective function according to the above-mentioned offer functions, the first virtual resource increment, and the second virtual resource increment.

[0105] Among them, when the server determines the first resource description function corresponding to the power generation side and the second resource description function corresponding to the electricity consumption side for the first resource interaction platform, the server can determine the power generation power of the generating units of the power generation side for the first resource interaction platform in the current time period; and determine the second resource description function according to the power generation power.

[0106] Among them, when the server determines the third resource description function corresponding to the power generation side and the fourth resource description function corresponding to the electricity consumption side for the second resource interaction platform, the server can determine the target capacity of the generating units of the power generation side for the second resource interaction platform in the current time period; and determine the fourth resource description function according to the target capacity.

[0107] Among them, in practical application, the target capacity can refer to the winning bid reserve capacity corresponding to the generating units for the reserve market.

[0108] The first objective function is as follows:

[0109]

[0110] Among them, F represents the result of resource interaction, that is, the total social welfare; T represents the total number of time periods; k1 is the first virtual resource increment corresponding to the first resource interaction platform, that is, the load yield rate corresponding to the electricity market; k2 is the second virtual resource increment corresponding to the second resource interaction platform, that is, the load yield rate corresponding to the reserve market; F 1,m (t) is the electricity consumption income of the mth interruptible load aggregator for the electricity market.

[0111] Among them, F 1,i (t), F 2,j (t), F 3,k (t) are respectively the interruptible load bidding function, the shiftable load bidding function, and the shiftable load bidding function in the second resource description function corresponding to the power consumption side for the power consumption market; F 4,e (t) is the bidding function determined by the power generation side based on the power generation cost of the generator set for the power consumption market, that is, the first resource description function; I is the number of interruptible load users on the power consumption side, J is the number of shiftable load users on the power consumption side, K is the number of shiftable load users on the power consumption side; E is the number of generator sets on the power generation side for the power consumption market; m is the mth interruptible load aggregator.

[0112] Among them, L 4,e (t) is the reserve bidding function determined by the power generation side based on the power generation cost of the generator set for the reserve market, that is, the third resource description function; L 1,i (t), L 2,j (t) are the reserve bidding function of the interruptible load and the reserve bidding function of the shiftable load in the fourth resource description function corresponding to the power consumption side for the reserve market.

[0113] Among them, S coal (c, t) is the reserve bidding function determined by the power generation side based on the start-up cost of the generator set for the reserve market; C represents the number of coal-fired generator sets on the power generation side for the reserve market.

[0114] Among them, the calculation formula of S coal (c, t) is as follows:

[0115] S coal (c, t) = S c (t) · S sta (t)(1 - S sta (t - 1))

[0116]

[0117] Among them, t represents the tth time period; S c (t) is the start-up cost of the generator set; S sta (t) is the state function of the generator set in the tth time period; S sta (t - 1) is the state function of the generator set in the (t - 1)th time period.

[0118] Among them, the determination formulas of the interruptible load bidding function F 1,i (t), the shiftable load bidding function F 2,j (t), and the shiftable load bidding function F 3,k (t) in the second resource description function corresponding to the power consumption side are as follows:

[0119] F 1,i (t), F 2,j (t), F 3,k (t) = f(P e (t))

[0120] wherein, P e (t) is the power generation power of the power generation side generator set in the current time period, i.e., the t time period, for the electricity consumption market, that is, the power generation power of the power generation side generator set in the current time period for the first resource interaction platform.

[0121] Among them, the reserve offer function L 1,i (t) of the interruptible load and the reserve offer function L 2,j (t) of the shiftable load are determined by the following formulas:

[0122] L 1,i (t), L 2,j (t) = f(R e (t))

[0123] wherein, R e (t) is the winning bid reserve capacity corresponding to the power generation side generator set in the current time period, i.e., the t time period, for the reserve market, that is, the target capacity of the power generation side generator set in the current time period for the second resource interaction platform.

[0124] Among them, there is a quadratic function relationship between P e (t) and the second resource description function, and between R e (t) and the fourth resource description function, and the coefficients are obtained according to actual operation experience.

[0125] The first constraint condition is as follows:

[0126]

[0127]

[0128] P e,min ≤ P e (t) + R e (t) ≤ P e,max

[0129] -V e,D ≤ P e (t) - P e (t - 1) ≤ V e,U

[0130]

[0131] wherein, P1,i (t), P 2,j (t) and P 3,k (t) is the total electricity load corresponding to the interruptible load, shiftable load, and deferrable load respectively, P4(t) is the fixed load in the t time period, and P(t) is the total load in the t time period; R e (t), R 1,i (t) and R 2,j (t) is the winning bid reserve capacity corresponding to the generator set, interruptible load, and shiftable load respectively; R(t) is the total reserve demand in the t time period; P e,min and P e,max are the lower and upper limit values of the total output of the generator set respectively; P e (t) is the power generation power of the generator set on the power generation side in the current time period, i.e., the t time period, for the electricity market; P e (t - 1) is the power generation power of the generator set on the power generation side in the previous time period, i.e., the t - 1 time period, for the electricity market; V e,D and V e,U are the downward and upward ramp constraints of the generator set respectively; W h is the upper limit of the output of the corresponding hydropower unit; thus, through the first constraint condition, it can be ensured that the unit meets the requirements of system safety and stability.

[0132] The technical solution of this embodiment constructs the first objective function of the first model according to the virtual resource increment; wherein, the first objective function aims to make the result of resource interaction meet the first preset condition; constructs the first constraint condition of the first model according to the first safety constraint and the second safety constraint; constructs the first model according to the first objective function and the first constraint condition; thus, through the target resource description information model constructed and trained based on the first model, the output target resource description information can ensure that the target resource description information is used to indicate that when the power consumption side interacts with the power generation side, the result of resource interaction meets the preset condition, and through the first constraint condition, it is ensured that the unit meets the safety and stability of the system, while improving the enthusiasm of resource interaction between the power consumption side and the power generation side, it can ensure the safety and stability of the system unit.

[0133] In one embodiment, for each initial resource description information set, a first model is constructed with the goal of the result of resource interaction satisfying a first preset condition and a second model is constructed with the goal of the result of resource transfer satisfying a second preset condition, including: obtaining the average value of virtual resource descriptions for the electricity load recorded in the resource interaction platform; determining the target electricity quantity for the electricity load at the electricity load aggregation end according to the initial resource description information set; constructing the second objective function of the second model according to the average value of virtual resource descriptions and the target electricity quantity; constructing the second constraint condition of the second model according to the virtual resource description limit value and the virtual resource increase amount; and constructing the second model according to the second objective function and the second constraint condition.

[0134] Among them, the second objective function is targeted at the result of resource transfer satisfying the second preset condition.

[0135] Among them, the result of resource transfer can refer to the profit of the load aggregator in actual application.

[0136] Among them, the second preset condition can refer to the maximization of the profit of the load aggregator in actual application.

[0137] Among them, the average value of virtual resource descriptions can refer to the average nodal price in the bilateral electricity price bidding market in actual application, including the average nodal price for the electricity market (corresponding to the first resource interaction platform) and the average nodal price for the reserve market (corresponding to the second resource interaction platform).

[0138] Among them, the target electricity quantity can refer to the winning bid quantity of the interruptible load in the bilateral electricity price bidding market in actual application, including the winning bid quantity of the interruptible load in the electricity market and the winning bid quantity of the interruptible load in the reserve market.

[0139] Among them, the virtual resource description limit value can be named the load bidding threshold in actual application, and the load bidding threshold includes the preset upper and lower limits of the load bid.

[0140] Among them, the virtual resource increase amount can be named the load rate of return in actual application, which refers to the multiple of the electricity load based on the real profit in the bilateral price bidding market; it includes the first virtual resource increase amount corresponding to the first resource interaction platform and the second virtual resource increase amount corresponding to the second resource interaction platform.

[0141] In specific implementation, when the server constructs a first model for each initial resource description information set with the goal that the result of resource interaction meets a first preset condition based on the virtual resource increment and the virtual resource description limit, and constructs a second model with the goal that the result of resource transfer meets a second preset condition, the server can obtain the average virtual resource description of the power consumption load recorded in the resource interaction platform, that is, obtain the average nodal price of the electricity market and the average nodal price of the reserve market; at the same time, according to the initial resource description information set, the server can determine the target electricity quantity of the power consumption load aggregation end for the power consumption load, that is, the winning bid quantity of the load aggregator for the interruptible load in the electricity market and the winning bid quantity of the load aggregator for the interruptible load in the reserve market; then, according to the average nodal price of the electricity market, the average nodal price of the reserve market, the winning bid quantity of the load aggregator for the interruptible load in the electricity market, and the winning bid quantity of the load aggregator for the interruptible load in the reserve market, the server can construct the second objective function of the second model, that is, the second objective function of the lower-level model, and this second objective function aims to make the result of resource transfer meet the second preset condition, that is, aims to maximize the profit of the load aggregator.

[0142] In practical application, the second objective function is as follows:

[0143]

[0144] Among them, F m is the result of resource transfer, that is, the profit of the load aggregator; F 1,m (t) is the electricity profit of the mth interruptible load aggregator for the electricity market; L1(t) is the average virtual resource description of the power consumption load recorded in the first resource interaction platform, that is, the average nodal price of the electricity market; P 1,m (t) is the target electricity quantity of the power consumption load aggregation end for the power consumption load in the first resource platform, that is, the winning bid quantity of the load aggregator for the interruptible load in the electricity market; L 1,m (t) is the reserve profit of the mth interruptible load aggregator for the reserve market, L2(t) is the average virtual resource description of the power consumption load recorded in the second resource interaction platform, that is, the average nodal price of the reserve market, R 1,m (t) is the target electricity quantity of the power consumption load aggregation end for the power consumption load in the second resource platform, that is, the winning bid quantity of the load aggregator for the interruptible load in the reserve market.

[0145] Among them, the second constraint condition is as follows:

[0146] k min ≤k1≤k max

[0147] kmin ≤ k2 ≤ k max

[0148] Wherein, k1 is the first virtual resource increment corresponding to the first resource interaction platform, i.e., the load return rate corresponding to the electricity market; k2 is the second virtual resource increment corresponding to the second resource interaction platform, i.e., the load return rate corresponding to the reserve market; k min is the lower limit of the load offer in the load offer threshold; k max is the upper limit of the load offer in the load offer threshold; wherein, k min and k max According to general experience, it can be selected in the range of (0, 5]; thus, through the second constraint condition, the abuse of market power can be prevented.

[0149] The technical solution of this embodiment obtains the average value of the virtual resource description for the electricity load recorded in the resource interaction platform; determines the target power consumption of the power consumption load aggregation end for the electricity load according to the initial resource description information set; constructs the second objective function of the second model according to the average value of the virtual resource description and the target power consumption; wherein, the two-objective function aims to make the result of resource transfer meet the second preset condition; constructs the second constraint condition of the second model according to the virtual resource description limit value and the virtual resource increment; constructs the second model according to the second objective function and the second constraint condition; thus, through the target resource description information model constructed and trained based on the second model, the target resource description information is output, which can ensure that when the target resource description information is used to indicate the resource interaction between the power consumption side and the power generation side, the result of the resource transfer between the power consumption load aggregation end on the power consumption side and the power generation side meets the preset condition, and by setting the second constraint condition through the virtual resource description limit value and the virtual resource increment, the reliability of the power consumption load aggregation end in the resource transfer process is ensured, and while improving the enthusiasm of the power consumption load aggregation end to participate in resource interaction, the reliability of the resource transfer result can be ensured.

[0150] In one embodiment, the initial resource description information set is iteratively optimized in the target resource description information model through a genetic algorithm to obtain the target resource description information, including: obtaining the fitness of the mutant individuals according to the second model; determining the fitness of the current population according to the fitness of the mutant individuals; determining the selection probability of the current population according to the fitness of the current population and the fitness of each population; determining the crossover probability and mutation probability corresponding to the genetic algorithm; and iteratively optimizing the initial resource description information set according to the selection probability, crossover probability, and mutation probability to obtain the target resource description information.

[0151] Wherein, the target resource description information is used to indicate the resource interaction between the power consumption side and the power generation side.

[0152] In a specific implementation, when the server iteratively optimizes the initial resource description information set in the target resource description information model through a genetic algorithm to obtain the target resource description information, the server can obtain the fitness of the mutant individuals obtained according to the second model. Specifically, the fitness of the mutant individuals can be determined based on the power consumption load aggregation end obtained by solving the second model. Then, the fitness of the current population is determined according to the fitness of the mutant individuals and a constant coefficient. After that, according to the fitness of the current population and the fitness of each population, the selection probability of the current population is determined. Then, the server can determine the crossover probability and mutation probability corresponding to the genetic algorithm. Finally, based on the selection probability, crossover probability, and mutation probability, the target resource description information model is solved to iteratively optimize the initial resource description information set. When the number of iterations reaches the preset maximum number of iterations, the target resource description information is finally obtained. This target resource description information is used to indicate the resource interaction between the power consumption side and the power generation side.

[0153] Among them, the formula for determining the fitness of the current population is as follows:

[0154] F fit,k = αF m + b

[0155] Among them, F fit,k is the fitness of the k-th population and can represent the fitness of the current population; F is the fitness of the mutant individuals, and a, b, and m are preset constant coefficients related to the composition of the actual bilateral bidding electricity market. When selecting, it is necessary to meet the condition that as the number of iterations increases, the difference in population fitness increases.

[0156] Among them, the calculation method of the parameters involved in the genetic algorithm is as follows:

[0157] The formula for the selection probability of the current population is as follows:

[0158]

[0159] Among them, p fit,k is the selection probability of the k-th population and can represent the selection probability of the current population; represents the sum of the fitness of all populations, and n represents the number of populations.

[0160] Among them,

[0161] p sub_fit,k = p fit,k + p sub_fit,k-1

[0162] Among them, p sub_fit,k is the cumulative probability of the k-th population. Similarly, p sub_fit,k-1It represents the cumulative probability of the (k - 1)-th population. According to the idea of roulette wheel selection method, the cumulative probability of the k-th population is the sum of the selection probabilities of the first k populations.

[0163] Among them, the formulas for the new strategy factors k′1 and k′2 after linear transformation are as follows:

[0164] k′1 = σk1+(1 - σ)k2

[0165] k′2 = σk2+(1 - σ)k1

[0166] Among them, k1 is the first virtual resource increment corresponding to the first resource interaction platform, that is, the load return rate corresponding to the electricity market; k2 is the second virtual resource increment corresponding to the second resource interaction platform, that is, the load return rate corresponding to the reserve market; σ is the linear transformation multiplier, which satisfies within the range of (0, 1).

[0167] Among them, the crossover probability p pcr The formula is as follows:

[0168]

[0169] Among them, is the preset maximum crossover probability, is the preset minimum crossover probability; is the average fitness value of the current population; is the maximum fitness value of the current population; F′ is the fitness value of the crossover individual; k0 is the initial strategy factor, and its value is the constant 9.90.

[0170] Among them, the mutation probability p pmu The formula is as follows:

[0171]

[0172] Among them, is the preset maximum mutation probability, is the preset minimum mutation probability; F″ is the fitness value of the individual to be mutated.

[0173] In this way, the iterative optimization of the initial resource description information set is realized based on the improved genetic algorithm. For the convenience of those skilled in the art to understand, Figure 2 a schematic diagram of the optimization process of the improved genetic algorithm is provided. As Figure 2As shown, population initialization is performed through preset initial parameters: virtual resource increment (load return rate), virtual resource description limit (quotation threshold), initial population size, and initial number of iterations. Then, the fitness of individuals and the population is calculated. Next, selection operation, crossover operation, and mutation operation are performed on the population in sequence. If the iteration end condition is not met, return to execute the steps of calculating the fitness of individuals and the population until the iteration end condition is met, and the process ends.

[0174] In practical applications, the first objective function and the first constraint condition corresponding to the upper-layer model, as well as the second objective function and the second constraint condition corresponding to the upper and lower models, and the initial parameters can be set. The initial parameters include: virtual resource increment (load return rate), virtual resource description limit (load quotation threshold), the set initial population size n, where n is generally selected as a positive integer greater than or equal to 30, and preferably can be set to 50; the initial number of iterations m, where m is generally selected as a positive integer greater than or equal to 30, and preferably can be set to 50. Substituting each objective function, each constraint condition, and the initial parameters into the CPLEX solver for calculation can solve the target resource description information model to obtain the target resource description information and the corresponding revenues of the power generation side, power consumption side, and power load aggregation side.

[0175] For the convenience of those skilled in the art to understand, Figure 3 a flowchart of a method for solving the target resource description information (i.e., the target quotation strategy) is provided. As Figure 3 shown: The method includes: forming a bilateral quotation curve by setting initial parameters and obtaining an initial quotation strategy set, performing bilateral market clearing according to the goal of maximizing social welfare to obtain the market clearing result; according to the market clearing result, with the goal of maximizing the revenue of the load aggregator, determining the revenue of the load aggregator and determining the fitness; if the iteration end condition is met, output the target quotation strategy; if the iteration end condition is not met, select the current optimal quotation strategy, dynamically adjust the crossover probability, and dynamically adjust the mutation probability according to the improved genetic algorithm, output a new quotation strategy and perform a new round of bilateral market clearing; iterate until the clearing goals of maximizing both social welfare and the revenue of the power consumption side of the load aggregator are met, and output the target quotation strategy.

[0176] The technical solution of this embodiment obtains the fitness of the mutant individuals according to the second model; determines the fitness of the current population according to the fitness of the mutant individuals; determines the selection probability of the current population according to the fitness of the current population and the fitness of each population; determines the crossover probability and mutation probability corresponding to the genetic algorithm; and iteratively optimizes the initial resource description information set according to the selection probability, crossover probability, and mutation probability to obtain the target resource description information. In this way, the target resource description information is solved according to the improved genetic algorithm, improving the model optimization speed and convergence performance.

[0177] In another embodiment, as Figure 4 shown, a power resource processing method based on a genetic algorithm is provided and applied to a server. In this embodiment, the method includes the following steps:

[0178] Step S402: Obtain the virtual resource increment for the power consumption load, the virtual resource description limit value, and the initial resource description information set corresponding to each power consumption load aggregation end recorded in the resource interaction platform.

[0179] Step S404: Construct the first objective function of the first model according to the virtual resource increment.

[0180] Step S406: Construct the first constraint condition of the first model according to the first security constraint and the second security constraint.

[0181] Step S408: Construct the first model according to the first objective function and the first constraint condition.

[0182] Step S410: Obtain the virtual resource description mean value for the power consumption load recorded in the resource interaction platform.

[0183] Step S412: Determine the target power consumption for the power consumption load aggregation end according to the initial resource description information set.

[0184] Step S414: Construct the second objective function of the second model according to the virtual resource description mean value and the target power consumption.

[0185] Step S416: Construct the second constraint condition of the second model according to the virtual resource description limit value and the virtual resource increment.

[0186] Step S418: Construct the second model according to the second objective function and the second constraint condition.

[0187] Step S420: Construct the target resource description information model according to the first model and the second model.

[0188] Step S422: Iteratively optimize the initial resource description information set in the target resource description information model through a genetic algorithm to obtain the target resource description information.

[0189] It should be noted that the specific limitations of the above steps can refer to the specific limitations of a power resource processing method based on a genetic algorithm described above.

[0190] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0191] Based on the same inventive concept, an embodiment of the present application also provides a genetic algorithm-based power resource processing device for implementing the above-mentioned genetic algorithm-based power resource processing method. The solution provided by this device for solving problems is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the genetic algorithm-based power resource processing device provided below can refer to the limitations on a genetic algorithm-based power resource processing method in the above text, and will not be repeated here.

[0192] In one embodiment, as Figure 5 shown, a genetic algorithm-based power resource processing device is provided, including: an acquisition module 510, a first construction module 520, a second construction module 530, and an optimization module 540, where:

[0193] The acquisition module 510 is configured to acquire the virtual resource increment for the power consumption load, the virtual resource description limit value, and the initial resource description information set corresponding to each power consumption load aggregation end recorded in the resource interaction platform; the resource interaction platform is used for resource interaction between the power consumption side and the power generation side; the power consumption load aggregation end is used for resource transfer between the power consumption side and the power generation side.

[0194] The first construction module 520 is configured to, for each of the initial resource description information sets, construct a first model with the goal that the result of the resource interaction satisfies a first preset condition, and construct a second model with the goal that the result of the resource transfer satisfies a second preset condition, based on the virtual resource increment and the virtual resource description limit value.

[0195] The second construction module 530 is configured to construct a target resource description information model based on the first model and the second model.

[0196] An optimization module 540 is configured to iteratively optimize the initial resource description information set in the target resource description information model through a genetic algorithm to obtain target resource description information; the target resource description information is used to indicate resource interaction between the power consumption side and the power generation side.

[0197] In one embodiment, the first construction module 520 is specifically configured to construct a first objective function of the first model according to the virtual resource increment; the first objective function aims to make the result of the resource interaction meet the first preset condition; construct first constraint conditions of the first model according to a first safety constraint and a second safety constraint; and construct the first model according to the first objective function and the first constraint conditions.

[0198] In one embodiment, the resource interaction platform includes a first resource interaction platform and a second resource interaction platform; the virtual resource increment includes a first virtual resource increment corresponding to the first resource interaction platform and a second virtual resource increment corresponding to the second resource interaction platform; the first construction module 520 is specifically configured to, for the first resource interaction platform, determine a first resource description function corresponding to the power generation side and a second resource description function corresponding to the power consumption side; for the second resource interaction platform, determine a third resource description function corresponding to the power generation side and a fourth resource description function corresponding to the power consumption side; and construct the first objective function according to the first resource description function, the second resource description function, the third resource description function, the fourth resource description function, the first virtual resource increment, and the second virtual resource increment.

[0199] In one embodiment, the first construction module 520 is specifically configured to determine the power generation power of the power generation side's generator set for the first resource interaction platform in the current time period; determine the second resource description function according to the power generation power; determine the target capacity of the power generation side's generator set for the second resource interaction platform in the current time period; and determine the fourth resource description function according to the target capacity.

[0200] In one embodiment, the first construction module 520 is specifically configured to obtain the virtual resource description mean value of the power consumption load recorded in the resource interaction platform; determine the target power consumption of the power consumption load aggregation end for the power consumption load according to the initial resource description information set; construct the second objective function of the second model according to the virtual resource description mean value and the target power consumption; the second objective function aims to satisfy the second preset condition with the result of the resource transfer; construct the second constraint condition of the second model according to the virtual resource description limit value and the virtual resource increase amount; and construct the second model according to the second objective function and the second constraint condition.

[0201] In one embodiment, the optimization module 540 is specifically configured to obtain the fitness of the mutant individuals obtained according to the second model; determine the fitness of the current population according to the fitness of the mutant individuals; determine the selection probability of the current population according to the fitness of the current population and the fitness of each population; determine the crossover probability and the mutation probability corresponding to the genetic algorithm; and perform iterative optimization on the initial resource description information set according to the selection probability, the crossover probability, and the mutation probability to obtain the target resource description information.

[0202] Each module in the above power resource processing device based on the genetic algorithm can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor in the computer device in hardware form or be independent of it, or be stored in the memory in the computer device in software form, so that the processor can call and execute the operations corresponding to the above modules.

[0203] In one embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as Figure 6 shown. The computer device includes a processor, a memory, and a network interface connected by a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the power resource processing data based on the genetic algorithm. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a power resource processing method based on the genetic algorithm.

[0204] Those skilled in the art can understand, Figure 6The structure shown is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0205] In one embodiment, a computer device is further provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are implemented.

[0206] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0207] In one embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0208] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0209] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memory can include Read-Only Memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0210] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0211] The above-described embodiments only represent several implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A power resource processing method based on genetic algorithm, characterized in that The method includes: Obtaining the virtual resource increment for the electricity load, the virtual resource description limit value, and the initial resource description information set corresponding to each electricity load aggregation end recorded in the resource interaction platform; the resource interaction platform is used for resource interaction between the power consumption side and the power generation side; the electricity load aggregation end is used for resource transfer between the power consumption side and the power generation side; For each of the initial resource description information sets, according to the virtual resource increment and the virtual resource description limit value, a first model is constructed with the goal that the result of the resource interaction satisfies a first preset condition, and a second model is constructed with the goal that the result of the resource transfer satisfies a second preset condition; including: constructing a first objective function of the first model according to the virtual resource increment; the first objective function is aimed at the result of the resource interaction satisfying the first preset condition; constructing a first constraint condition of the first model according to a first safety constraint and a second safety constraint; constructing the first model according to the first objective function and the first constraint condition; obtaining the virtual resource description mean value for the electricity load recorded in the resource interaction platform; determining the target electricity quantity of the electricity load aggregation end for the electricity load according to the initial resource description information set; constructing a second objective function of the second model according to the virtual resource description mean value and the target electricity quantity; the second objective function is aimed at the result of the resource transfer satisfying the second preset condition; constructing a second constraint condition of the second model according to the virtual resource description limit value and the virtual resource increment; constructing the second model according to the second objective function and the second constraint condition; Wherein, the resource interaction platform includes a first resource interaction platform and a second resource interaction platform; the virtual resource increment includes a first virtual resource increment corresponding to the first resource interaction platform and a second virtual resource increment corresponding to the second resource interaction platform; constructing the first objective function of the first model according to the virtual resource increment includes: for the first resource interaction platform, determining a first resource description function corresponding to the power generation side and a second resource description function corresponding to the power consumption side; for the second resource interaction platform, determining a third resource description function corresponding to the power generation side and a fourth resource description function corresponding to the power consumption side; constructing the first objective function according to the first resource description function, the second resource description function, the third resource description function, the fourth resource description function, the first virtual resource increment and the second virtual resource increment; Constructing a target resource description information model according to the first model and the second model; Iteratively optimizing the initial resource description information set in the target resource description information model through a genetic algorithm to obtain target resource description information; the target resource description information is used to indicate resource interaction between the power consumption side and the power generation side.

2. The method according to claim 1, characterized in that, For the first resource interaction platform, determining a first resource description function corresponding to the power generation side and a second resource description function corresponding to the power consumption side includes: Determining the power generation power of the generator set on the power generation side for the first resource interaction platform in the current time period; Determining the second resource description function according to the power generation power; For the second resource interaction platform, determining a third resource description function corresponding to the power generation side and a fourth resource description function corresponding to the power consumption side includes: Determining the target capacity of the generator set on the power generation side for the second resource interaction platform in the current time period; Determining the fourth resource description function according to the target capacity.

3. The method according to claim 1, characterized in that, The iterative optimization of the initial resource description information set in the target resource description information model by using a genetic algorithm to obtain target resource description information includes: Obtaining the fitness of the mutant individuals obtained according to the second model; Determining the fitness of the current population according to the fitness of the mutant individuals; Determining the selection probability of the current population according to the fitness of the current population and the fitness of each population; Determining the crossover probability and mutation probability corresponding to the genetic algorithm; Performing iterative optimization on the initial resource description information set in the target resource description information model according to the selection probability, the crossover probability, and the mutation probability to obtain the target resource description information.

4. A power resource processing device based on a genetic algorithm, characterized in that, The device includes: An acquisition module, configured to acquire the virtual resource increment for the electricity consumption load, the virtual resource description limit value, and the initial resource description information set corresponding to each electricity consumption load aggregation end recorded in the resource interaction platform; the resource interaction platform is used for resource interaction between the power consumption side and the power generation side; the electricity consumption load aggregation end is used for resource transfer between the power consumption side and the power generation side; A first construction module, configured to, for each of the initial resource description information sets, construct a first model with the goal that the result of the resource interaction meets a first preset condition and construct a second model with the goal that the result of the resource transfer meets a second preset condition according to the virtual resource increment and the virtual resource description limit value; A second construction module, configured to construct a target resource description information model according to the first model and the second model; An optimization module, configured to perform iterative optimization on the initial resource description information set in the target resource description information model by using a genetic algorithm to obtain target resource description information; the target resource description information is used to indicate resource interaction between the power consumption side and the power generation side; Among them, the first construction module is specifically configured to construct a first objective function of the first model according to the virtual resource increment; the first objective function aims at the result of the resource interaction meeting the first preset condition; constructing a first constraint condition of the first model according to a first safety constraint and a second safety constraint; constructing the first model according to the first objective function and the first constraint condition; Among them, the resource interaction platform includes a first resource interaction platform and a second resource interaction platform; the virtual resource increment includes a first virtual resource increment corresponding to the first resource interaction platform and a second virtual resource increment corresponding to the second resource interaction platform; the first construction module is specifically configured to, for the first resource interaction platform, determine a first resource description function corresponding to the power generation side and a second resource description function corresponding to the power consumption side; for the second resource interaction platform, determine a third resource description function corresponding to the power generation side and a fourth resource description function corresponding to the power consumption side; and construct the first objective function according to the first resource description function, the second resource description function, the third resource description function, the fourth resource description function, the first virtual resource increment, and the second virtual resource increment. Among them, the first construction module is specifically configured to obtain the virtual resource description mean value for the power consumption load recorded in the resource interaction platform; determine the target power consumption of the power consumption load aggregation end for the power consumption load according to the initial resource description information set; construct the second objective function of the second model according to the virtual resource description mean value and the target power consumption; the second objective function aims to make the result of the resource transfer meet the second preset condition; construct the second constraint condition of the second model according to the virtual resource description limit value and the virtual resource increment; and construct the second model according to the second objective function and the second constraint condition.

5. The device according to claim 4, characterized in that, The first construction module is specifically configured to determine the power generation power of the power generation side's generator set for the first resource interaction platform in the current time period; determine the second resource description function according to the power generation power; determine the target capacity of the power generation side's generator set for the second resource interaction platform in the current time period; and determine the fourth resource description function according to the target capacity.

6. The device according to claim 4, characterized in that, The optimization module is specifically configured to obtain the mutant individual fitness obtained according to the second model; determine the current population fitness according to the mutant individual fitness; determine the selection probability of the current population according to the current population fitness and the fitness of each population; determine the crossover probability and mutation probability corresponding to the genetic algorithm; and perform iterative optimization on the initial resource description information set according to the selection probability, the crossover probability, and the mutation probability to obtain the target resource description information.

7. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 3.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the method according to any one of claims 1 to 3.

9. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the method according to any one of claims 1 to 3.

Images