New energy contract electric quantity decomposition method and device, electronic equipment and computer program

Abstract

The invention discloses a new energy contract electric quantity decomposition method and device, electronic equipment and a computer program, and the method comprises the steps: building a new energy output prediction model considering uncertainty, and determining a system operation constraint corresponding to a contract decomposition variable; constructing a risk measurement model and an income calculation model according to the contract decomposition variable, and determining a risk-income adaptive coupling coefficient; constructing a risk-income self-adaptive decomposition optimization model according to the risk measurement model, the income calculation model and the risk-income self-adaptive coupling coefficient; and carrying out optimization solution on the risk-income adaptive decomposition optimization model through a whale swarm algorithm improved based on chaotic disturbance to obtain an optimal solution of a contract decomposition variable, and carrying out new energy contract electric quantity decomposition according to the optimal solution. The method improves the accuracy, flexibility and real-time performance of new energy contract electric quantity decomposition, also improves the stability of the new energy electric power market, and can be applied to the technical field of the electric power market.

Description

Technical Field

[0001] This invention relates to the field of electricity market technology, and in particular to a method, apparatus, electronic device, and computer program for allocating new energy contracted electricity. Background Technology

[0002] With the large-scale grid connection of new energy sources, medium- and long-term contracts, as an important guarantee for new energy participation in the electricity market, directly impact the operational efficiency of enterprises and market stability through their scientific allocation. Currently, the allocation schemes for medium- and long-term contracts for new energy have the following shortcomings: Limitations of static decomposition: Traditional methods often use fixed proportions (such as quarterly averages) or empirical values ​​for decomposition, ignoring dynamic changes in market prices and renewable energy output, leading to a disconnect between contract execution and actual market demand. For example, a wind farm that decomposed its annual contracts according to a fixed proportion missed a high-yield opportunity during a period of sharp rise in spot prices because it failed to adjust the decomposition amount in time.

[0003] Risk-return separation: Existing research on the trade-off between risk and return mostly adopts static weights (such as a fixed risk weight of 0.3), without establishing an adaptive linkage mechanism between the two, making it difficult to cope with sudden market changes (such as when price volatility rises from 10% to 30%, making decisions based on the original weights will lead to an expansion of risk exposure).

[0004] Lack of coupling across time periods: Traditional models treat the decomposition of each time period as an independent problem, without considering the correlation between contract electricity volume across time periods (e.g., excessive decomposition in the previous time period can lead to insufficient electricity volume in the next time period), which can easily cause resource mismatch across time periods.

[0005] Insufficient solution efficiency: When faced with multi-time-period, high-dimensional decomposition problems, traditional algorithms (such as linear programming) struggle to handle nonlinear risk functions, resulting in low solution accuracy or excessive computation time, failing to meet the real-time adjustment requirements of contracts.

[0006] In summary, existing renewable energy contract power allocation schemes suffer from insufficient accuracy, flexibility, and efficiency, which affect the stability of the renewable energy power market. Summary of the Invention

[0007] The purpose of this invention is to at least partially solve one of the technical problems existing in the prior art.

[0008] Therefore, one objective of this invention is to provide a method for decomposing renewable energy contract power, which improves the accuracy, flexibility, and real-time performance of renewable energy contract power decomposition, and also enhances the stability of the renewable energy power market.

[0009] Another objective of this invention is to provide a new energy contract electricity decomposition device.

[0010] To achieve the above-mentioned technical objectives, the technical solutions adopted in the embodiments of the present invention include: On one hand, embodiments of the present invention provide a method for decomposing renewable energy contract electricity, including the following steps: Establish a new energy output prediction model that takes into account uncertainty, and determine the system operation constraints corresponding to the contract decomposition variables; Based on the contract decomposition variables, a risk measurement model and a return calculation model are constructed, and the risk-return adaptive coupling coefficient is determined. A risk-return adaptive decomposition and optimization model is constructed based on the risk measurement model, the return calculation model, and the risk-return adaptive coupling coefficient. The risk-return adaptive decomposition optimization model is optimized and solved by the whale swarm algorithm based on chaotic perturbation to obtain the optimal solution of the contract decomposition variables, and then the new energy contract electricity decomposition is performed based on the optimal solution.

[0011] Furthermore, in one embodiment of the present invention, the new energy output prediction model is as follows:

[0012] in, This represents the actual output of new energy sources during time period t. This represents the predicted output of new energy sources during time period t. This represents the error correction factor. This represents the prediction error for time period t; The contract decomposition variables are:

[0013] in, This represents the decomposed electricity of contract type k in time period t, where k=1 corresponds to the base load contract. k=2 corresponds to peak load contract ; The system operation constraints include contract power conservation constraints and output-contract matching constraints. The contract power conservation constraints are as follows:

[0014] Where T represents the set of contract execution periods, This represents the total electricity volume of the new energy contract; The output-contract matching constraint is:

[0015] in, This represents the breakdown of the base load contract's electricity volume during time period t. This represents the breakdown of the peak load contract's electricity volume during time period t. This represents the output of the backup power supply during time period t.

[0016] Furthermore, in one embodiment of the present invention, the risk measurement model is:

[0017]

[0018] in, Indicates confidence level Conditional Value at Risk (VaR) Represents the conditional expectation function. This represents the loss function for time period t. Indicates confidence level Value at risk (VaR) This represents the spot market electricity price during time period t. This indicates the execution price of contract type k during time period t; The revenue calculation model is as follows:

[0019] in, This represents the contract execution revenue during time period t; The risk-return adaptive coupling coefficient is:

[0020] in, This represents the risk-return adaptive coupling coefficient for time period t.

[0021] Furthermore, in one embodiment of the present invention, the risk-return adaptive decomposition optimization model includes an objective function with the optimization objective of maximizing risk-adjusted return, as well as multi-period coupling constraints and upper and lower bound constraints on the decomposition amount. The objective function is:

[0022]

[0023] Where F represents the risk-adjusted return. This represents the dynamic risk aversion coefficient for time period t. The multi-time-period coupling constraint is:

[0024] in, This represents the decomposed electricity amount of contract type k during time period t+1. Indicates the adjustment factor between time periods; The upper and lower limits of the decomposition amount are constrained as follows:

[0025] in, , These represent the minimum and maximum decomposed electricity amounts for contract type k during time period t, respectively.

[0026] Furthermore, in one embodiment of the present invention, the step of optimizing the risk-return adaptive decomposition optimization model using a whale swarm algorithm based on chaotic perturbation to obtain the optimal solution for the contract decomposition variables specifically includes: The initial whale pod position corresponding to the contract decomposition variable is determined by chaotic mapping, and the risk-return guiding factor is determined according to the risk-return adaptive coupling coefficient. Initialize the whale pod based on the initial whale pod location; Determine the fitness of each individual whale in the pod; The global optimal position is determined based on the fitness, and the current convergence factor and the current coefficient vector are calculated. The individual guiding position for each individual in the next iteration is calculated based on the global optimal position, the current convergence factor, the current coefficient vector, and the risk-return guiding factor. The process involves updating the pod based on the individual's guiding position and returning to determine the fitness of each individual in the pod until a preset convergence condition is met. Finally, the optimal solution for the contract decomposition variable is determined based on the position of the current best individual.

[0027] Furthermore, in one embodiment of the present invention, the fitness is calculated using the following formula:

[0028] in, Indicates fitness. This represents the penalty coefficient.

[0029] Furthermore, in one embodiment of the present invention, the initial whale pod location is determined by the following formula:

[0030] in, This represents the coordinate value of the i-th individual in the d-th dimension, where d=1 corresponds to the base load contract dimension and d=2 corresponds to the peak load contract dimension. and Let represent the minimum and maximum values ​​of the contract decomposition variable in the d-th dimension, respectively. This represents the i-th element in the chaotic sequence of the d-th dimension of the contract decomposition convenience; The risk-return guiding factor is calculated using the following formula:

[0031] in, This indicates a risk-return guiding factor. This represents the maximum value of the risk-return adaptive coupling coefficient over the entire time period; The individual guidance position is calculated using the following formula:

[0032]

[0033]

[0034]

[0035] in, This represents the individual guiding position of the i-th particle in iteration t+1. This represents the current individual position of the i-th particle. Indicates the current iteration number. Indicates the maximum number of iterations. Let A and C represent the current convergence factor, A and C represent the current coefficient vector, r represent the first random number in [0,1], and p represent the selection probability, where p∈[0,1]. This represents the distance parameter, where b is a preset constant. This represents the second random number within the range [-1, 1]. This represents the globally optimal position after t iterations.

[0036] On the other hand, embodiments of the present invention provide a new energy contract electricity allocation device, comprising: The contract decomposition modeling module is used to establish a new energy output prediction model that takes into account uncertainties and to determine the system operation constraints corresponding to the contract decomposition variables. The risk-return coupling analysis module is used to construct a risk measurement model and a return calculation model based on the contract decomposition variables, and to determine the risk-return adaptive coupling coefficient. The risk-return adaptive decomposition modeling module is used to construct a risk-return adaptive decomposition optimization model based on the risk measurement model, the return calculation model, and the risk-return adaptive coupling coefficient. The optimization solution module optimizes the risk-return adaptive decomposition optimization model by using a whale swarm algorithm based on chaotic perturbation to obtain the optimal solution for the contract decomposition variables, and then decomposes the new energy contract electricity volume based on the optimal solution.

[0037] On the other hand, embodiments of the present invention provide an electronic device, including: At least one processor; At least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the above-described method for decomposing new energy contract electricity.

[0038] On the other hand, embodiments of the present invention also provide a computer-readable storage medium storing a processor-executable computer program that, when executed by a processor, implements the above-described method for decomposing renewable energy contract electricity.

[0039] On the other hand, embodiments of the present invention also provide a computer program product, including a computer program that, when executed by a processor, implements the above-described method for decomposing new energy contract electricity.

[0040] The advantages and beneficial effects of the present invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention: This invention establishes a new energy output prediction model considering uncertainty and determines the system operation constraints corresponding to the contract decomposition variables. Based on the contract decomposition variables, a risk measurement model and a return calculation model are constructed, and a risk-return adaptive coupling coefficient is determined. A risk-return adaptive decomposition optimization model is then constructed based on the risk measurement model, return calculation model, and risk-return adaptive coupling coefficient. This model is optimized and solved using a whale swarm algorithm based on chaotic perturbation to obtain the optimal solution for the contract decomposition variables. The new energy contract power volume is then decomposed based on the optimal solution. This invention, by constructing an adaptive decomposition optimization model that considers dynamic risk-return coupling and multi-time-period correlation, and combining it with a whale swarm algorithm based on chaotic perturbation for efficient solution, achieves controllable risk and optimal return in contract decomposition, improves the accuracy, flexibility, and real-time performance of new energy contract power volume decomposition, and also enhances the stability of the new energy power market. Attached Figure Description

[0041] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the embodiments of the present invention are described below. It should be understood that the drawings described below are only for the convenience of clearly describing some embodiments of the technical solutions of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0042] Figure 1 A flowchart illustrating the steps of a new energy contract power allocation method provided in this embodiment of the invention; Figure 2 This is a structural block diagram of a new energy contract power allocation device provided in an embodiment of the present invention; Figure 3This is a structural block diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0043] To make the objectives, technical solutions, and advantages of this invention clearer, the invention 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 merely illustrative of the invention and are not intended to limit the invention. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of this invention; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this invention as detailed in the appended claims.

[0044] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein is for the purpose of describing embodiments of the invention only and is not intended to limit the invention.

[0045] The new energy contract electricity decomposition method provided in this invention can be applied to a terminal, a server, or software running on a terminal or server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, or vehicle terminal, but is not limited to these. The server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network. The software can be an application that implements the new energy contract electricity decomposition method, but is not limited to the above forms.

[0046] This invention can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This invention can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This invention can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0047] This invention aims to solve the problems of risk and return imbalance, poor dynamic adaptability and multi-period mismatch in the decomposition of medium and long-term new energy contracts, improve the risk resistance and return stability of new energy power generation enterprises in the process of contract execution, and enhance their dynamic adjustment ability to cope with market price fluctuations and output uncertainty.

[0048] Reference Figure 1 This invention provides a method for decomposing new energy contract electricity, specifically including the following steps: S101. Establish a new energy output prediction model that considers uncertainty, and determine the system operation constraints corresponding to the contract decomposition variables; S102. Construct a risk measurement model and a return calculation model based on the contract decomposition variables, and determine the risk-return adaptive coupling coefficient; S103. Construct a risk-return adaptive decomposition and optimization model based on the risk measurement model, the return calculation model, and the risk-return adaptive coupling coefficient. S104. The risk-return adaptive decomposition optimization model is optimized and solved by the whale swarm algorithm based on chaotic perturbation to obtain the optimal solution of the contract decomposition variables, and then the new energy contract electricity is decomposed according to the optimal solution.

[0049] This invention constructs an adaptive decomposition optimization model that considers the dynamic coupling of risk and return and the correlation of multiple time periods. It combines a whale swarm algorithm based on chaotic perturbation for efficient solution, thereby achieving controllable risk and optimal return in contract decomposition. This improves the accuracy, flexibility and real-time performance of new energy contract power decomposition, and also enhances the stability of the new energy power market.

[0050] As an optional implementation method, the new energy output prediction model is as follows:

[0051] in, This represents the actual output of new energy sources during time period t. This represents the predicted output of new energy sources during time period t. This represents the error correction factor. This represents the prediction error for time period t; Contract decomposition variables are:

[0052] in, This represents the decomposed electricity of contract type k in time period t, where k=1 corresponds to the base load contract. k=2 corresponds to peak load contract ; System operational constraints include contract power conservation constraints and output-contract matching constraints. The contract power conservation constraints are as follows:

[0053] Where T represents the set of contract execution periods, This represents the total electricity volume of the new energy contract; The output-contract matching constraint is:

[0054] in, This represents the breakdown of the base load contract's electricity volume during time period t. This represents the breakdown of the peak load contract's electricity volume during time period t. This represents the output of the backup power supply during time period t.

[0055] Specifically, step S101 is used to clearly describe the interaction between the characteristics of new energy output, the structure of medium- and long-term contracts and the external market environment (spot market, ancillary service market), clarify the core constraints of system operation, and provide a data framework for subsequent analysis of risk-return coupling characteristics and construction of optimization models.

[0056] 1. Modeling of New Energy Output Taking wind power as an example, an output prediction model considering uncertainties is established:

[0057] in, The actual wind power output during time period t. For wind power predicted for period t, This is the error correction coefficient (with a value range of [0, 0.2], reflecting the prediction accuracy). The prediction error for time period t (with a mean of 0 and a standard deviation of ) (Normal distribution).

[0058] Traditional models only use predicted output Ignoring the impact of prediction errors on contract execution, this model adds an error correction term. By introducing a random error term, the uncertainty of output can be more accurately characterized, and the deviation between the decomposition scheme and the actual output can be reduced.

[0059] 2. Modeling of medium- and long-term contract structures.

[0060] Define contract decomposition variables to distinguish base load contracts Contract with Peak Lotus Amount of decomposition:

[0061] in, For contract type k in time period t, the decomposed electricity (positive values ​​are the execution electricity, which must meet the total contract electricity constraint), k=1 represents the base load contract (electricity price is fixed). k=2 represents a peak load contract (electricity price fluctuates with time of day, denoted as...). ).

[0062] Traditional contract decomposition does not distinguish between base load and peak load characteristics and uses a uniform proportional decomposition; this model uses categorical variables. To achieve differentiated decomposition and adapt to market price characteristics at different times.

[0063] 3. System operation constraints (1) Contract electricity conservation constraint: The sum of the electricity decomposed in each time period must be equal to the total contract electricity to ensure the integrity of contract performance:

[0064] Where T is the set of contract execution periods (e.g., 12 months). This represents the total electricity volume under medium- and long-term contracts. (2) Output-Contract Matching Constraints: The actual output of new energy sources must support the execution of the allocated electricity to avoid the risk of default due to insufficient output.

[0065] in, It provides backup power output for period t (to make up for the power output gap of new energy sources). This step clarifies the basic interaction between new energy output, contract structure, and market environment. The output data and contract parameters will provide input for the next step of analyzing the coupling characteristics of risk and return. Therefore, it is necessary to further construct a risk-return adaptive coupling analysis model.

[0066] As an optional implementation method, the risk measurement model is as follows:

[0067]

[0068] in, Indicates confidence level Conditional Value at Risk (VaR) Represents the conditional expectation function. This represents the loss function for time period t. Indicates confidence level Value at risk (VaR) This represents the spot market electricity price during time period t. This indicates the execution price of contract type k during time period t; The profit calculation model is as follows:

[0069] in, This represents the contract execution revenue during time period t; The risk-return adaptive coupling coefficient is:

[0070] in, This represents the risk-return adaptive coupling coefficient for time period t.

[0071] Specifically, step S102, based on the system model, quantifies the dynamic correlation characteristics and multi-period coupling effects of risk and return, reveals the adaptive balance law of risk-return, and provides a basis for the target setting and constraint design of the subsequent optimization model.

[0072] 1. Risk Measurement Model Conditional Value at Risk (CVaR) is used to measure the potential risk of contract decomposition, taking into account the combined effects of market price volatility and output uncertainty:

[0073]

[0074] in, Confidence level Conditional Value at Risk (VaR) (reflecting the average level of extreme losses). The confidence level is (e.g., 95%). Let be the loss function for time period t, when the spot electricity price Higher than the contracted electricity price (At that time, executing the contract incurs a loss). Confidence level Value at risk (maximum possible loss threshold).

[0075] Traditional risk measures often use variance, which cannot effectively characterize extreme risks. This model uses CVaR to more accurately capture tail risks and adapt to extreme fluctuations in new energy output and market prices.

[0076] 2. Profit Calculation Model Considering the price difference between contracted electricity prices and spot electricity prices, and combining this with the breakdown of electricity volume, the revenue for each time period is calculated as follows:

[0077] in, This represents the contract execution profit during time period t (positive value indicates profit, negative value indicates loss). Let $t$ be the execution price for contract type $k$ during time period $t$. Let t be the spot market electricity price for period t.

[0078] Step 3: Risk-Return Adaptive Coupling Coefficient The dynamic elasticity coefficient describes the adaptive relationship between risk and return, reflecting their marginal substitution relationship.

[0079] in, The risk-return elasticity coefficient for time period t (a positive value indicates that the return increases with increasing risk, and a negative value indicates that the return decreases with increasing risk), its value varies with market volatility. Dynamic adjustment (when volatility increases) An increase in absolute value reflects a risk-sensitive adjustment. Traditional models use fixed weights (e.g., risk weight 0.4, return weight 0.6) to balance risk and return; this model uses... It achieves dynamic adaptation, increasing the risk weight when the market is volatile and increasing the return weight when the market is stable, thereby improving decision-making flexibility.

[0080] This step reveals the dynamic coupling law between risk and return. The calculated CVaR, return value and elasticity coefficient need to be integrated into the objective function and constraints of the subsequent optimization model (such as using the elasticity coefficient to adjust the risk-return weight). Therefore, it is necessary to further establish a risk-return adaptive decomposition optimization model.

[0081] As an optional implementation, the risk-return adaptive decomposition optimization model includes an objective function that maximizes risk-adjusted return, as well as multi-period coupling constraints and upper and lower bound constraints on the decomposition amount. The objective function is:

[0082]

[0083] Where F represents the risk-adjusted return. This represents the dynamic risk aversion coefficient for time period t. Multi-time coupling constraints are:

[0084] in, This represents the decomposed electricity amount of contract type k during time period t+1. Indicates the adjustment factor between time periods; The upper and lower limits of the decomposition amount are constrained as follows:

[0085] in, , These represent the minimum and maximum decomposed electricity amounts for contract type k during time period t, respectively.

[0086] Specifically, step S103, based on the system model and the results of coupling characteristic analysis, sets a function with the goal of maximizing returns under controllable risk, integrates contract rules and risk constraints, constructs a quantifiable optimization model, and achieves an adaptive balance between risk and return.

[0087] 1. Construction of the objective function With the goal of maximizing risk-adjusted returns, a dynamic elasticity coefficient is incorporated to achieve an adaptive trade-off between risk and return.

[0088]

[0089] Where F is the total risk-adjusted return. Let be the dynamic risk aversion coefficient for time period t, with a value range of [0,1]. The larger, The closer it is to 1, the higher the risk aversion tendency.

[0090] Traditional objective functions only maximize returns or minimize risks, ignoring the dynamic relationship between the two; this function, through... By adaptively coupling risk and return, the risk weight is automatically increased during market volatility, while the focus is on return optimization during stable periods.

[0091] 2. Multi-time period coupling constraints Considering the correlation between electricity allocation across time periods, avoid excessive allocation in one time period leading to insufficient electricity in subsequent time periods:

[0092] in, This is an inter-period adjustment coefficient (with a value range of [0, 0.2], which controls the maximum increase in the amount of electricity distributed between adjacent periods to avoid drastic fluctuations).

[0093] 3. Upper and lower limits of decomposition quantity constraints The amount of electricity allocated in each time period must be within a reasonable range to meet the power output capacity of new energy sources and market demand.

[0094] in, , These are the minimum and maximum decomposed electricity volumes for contract type k during time period t (determined by the maximum output of new energy and the upper limit of market demand).

[0095] The optimization model established in this step is a nonlinear model with dynamic risk terms and multiple time-period coupling, which is difficult to solve efficiently using traditional algorithms. Therefore, it is necessary to design a targeted solution method (based on the improved whale swarm algorithm with chaotic perturbation) to meet the time requirements for real-time contract adjustment.

[0096] As an optional implementation, the risk-return adaptive decomposition optimization model is further optimized using a whale swarm algorithm based on chaotic perturbation to obtain the optimal solution for the contract decomposition variables, which specifically includes: The initial whale pod positions corresponding to the contract decomposition variables are determined by chaotic mapping, and the risk-return guiding factor is determined based on the risk-return adaptive coupling coefficient. Initialize the whale pod based on its initial location; Determine the fitness of each individual whale in the pod; The global optimum is determined based on fitness, and the current convergence factor and current coefficient vector are calculated. Calculate the individual guiding position of each individual in the next iteration based on the global optimal position, the current convergence factor, the current coefficient vector, and the risk-reward guiding factor; The process involves updating the pod based on the individual guide position and returning to determine the fitness of each individual in the pod until a preset convergence condition is met. Finally, the optimal solution for the contract decomposition variables is determined based on the position of the current best individual.

[0097] As an optional implementation, the fitness is calculated using the following formula:

[0098] in, Indicates fitness. This represents the penalty coefficient.

[0099] As a further optional implementation, the initial whale pod location is determined by the following formula:

[0100] in, This represents the coordinate value of the i-th individual in the d-th dimension, where d=1 corresponds to the base load contract dimension and d=2 corresponds to the peak load contract dimension. and Let represent the minimum and maximum values ​​of the contract decomposition variable in the d-th dimension, respectively. This represents the i-th element in the chaotic sequence of the d-th dimension of the contract decomposition convenience; The risk-return leading factor is calculated using the following formula:

[0101] in, This indicates a risk-return guiding factor. This represents the maximum value of the risk-return adaptive coupling coefficient over the entire time period; The individual guiding position is calculated using the following formula:

[0102]

[0103]

[0104]

[0105] in, This represents the individual guiding position of the i-th particle in iteration t+1. This represents the current individual position of the i-th particle. Indicates the current iteration number. Indicates the maximum number of iterations. Let A and C represent the current convergence factor, A and C represent the current coefficient vector, r represent the first random number in [0,1], and p represent the selection probability, where p∈[0,1]. This represents the distance parameter, where b is a preset constant. This represents the second random number within the range [-1, 1]. This represents the globally optimal position after t iterations.

[0106] Specifically, step S104 addresses the high-dimensionality and strong nonlinearity of the risk-return adaptive decomposition optimization model by designing an efficient solution algorithm to improve convergence speed and global optimal solution search capability, ensuring that optimization calculations are completed within the contract adjustment timescale (e.g., monthly).

[0107] 1. Population initialization Chaotic Tent mappings are used to initialize whale pod positions, improving the uniformity of the initial solution:

[0108]

[0109] in, The position of the i-th whale in the d-th dimension (corresponding to the decomposed variable) ), , For the minimum and maximum values ​​of the d-th dimension variable, It is a chaotic sequence (range [0,1]). This is the Tent mapping parameter (taken as 0.5). Let be the nth element in the chaotic sequence, a chaotic variable generated iteratively through the Tent mapping. Traditional whale swarm algorithms randomly initialize the population, which can easily lead to uneven solution distribution; this model initializes the population through chaotic mapping, improving population diversity and avoiding getting trapped in local optima in the early stages.

[0110] 2. Adaptive predation strategy The algorithm's exploration and development capabilities are dynamically adjusted, and a risk-return guiding factor is introduced to optimize the search direction.

[0111]

[0112]

[0113]

[0114] in, This is the convergence factor (which decreases linearly with iteration to control the exploration range). This represents the current iteration number. Let A and C be the coefficient vectors, r be a random number in the range [0,1], and p be the selection probability. is the distance parameter, and b is a constant (controlling the spiral shape). A random number in the range [-1, 1] The globally optimal position is defined for time period t, and a risk-reward guiding factor is introduced during position updates. (Enhancing the search tendency towards regions with high elasticity coefficients).

[0115] Traditional whale pod algorithms employ fixed foraging strategies, making it difficult to balance exploration and exploitation; this model, through... Dynamically adjust the search scope and introduce... It guides the search direction and significantly improves the convergence speed.

[0116] 3. Constraint handling and iteration termination The penalty function method is used to handle constraint violations, imposing penalties on decompositions that exceed the upper and lower limits:

[0117] in, For the fitness function, The penalty coefficient is set to 1000. The iteration termination condition is reaching the maximum number of iterations or the fitness change being less than 10 after 20 consecutive iterations. -5 .

[0118] The solution method designed in this step targets the high-dimensional and nonlinear characteristics of the optimization model. Through improvements such as chaotic initialization, adaptive strategies, and risk-return guiding factors, it achieves efficient model solving and is the key to the practical application of the preceding steps (system model, coupling analysis, optimization model).

[0119] The method steps of the embodiments of the present invention have been described above. It can be understood that the embodiments of the present invention, by constructing an adaptive decomposition optimization model that considers the dynamic coupling of risk and return and the correlation of multiple time periods, and combining it with the whale swarm algorithm based on chaotic perturbation for efficient solution, achieve controllable risk and optimal return in contract decomposition, improve the accuracy, flexibility and real-time performance of new energy contract electricity decomposition, and also improve the stability of the new energy electricity market.

[0120] Compared with the prior art, the embodiments of the present invention also have the following advantages: 1) Risk-return adaptive coupling innovation: A risk-return correlation model based on dynamic elasticity coefficient is proposed, which breaks through the limitations of traditional static weights, realizes adaptive trade-offs under market fluctuations, and improves the flexibility of contract decomposition.

[0121] 2) Multi-period coupling optimization innovation: Construct a decomposition model with cross-period adjustment constraints to solve the resource mismatch problem caused by traditional independent period decomposition and enhance the continuity of contract execution.

[0122] 3) Innovative solution algorithm: An improved whale swarm algorithm is designed that integrates chaotic initialization and risk-reward guiding factors to improve the solution efficiency and global optimality of high-dimensional models and meet the requirements of real-time adjustment.

[0123] Reference Figure 2 This invention provides a new energy contract electricity allocation device, comprising: The contract decomposition modeling module is used to establish a new energy output prediction model that takes into account uncertainties and to determine the system operation constraints corresponding to the contract decomposition variables. The risk-return coupling analysis module is used to construct risk measurement models and return calculation models based on contract decomposition variables, and to determine the risk-return adaptive coupling coefficient. The risk-return adaptive decomposition modeling module is used to construct a risk-return adaptive decomposition optimization model based on the risk measurement model, the return calculation model, and the risk-return adaptive coupling coefficient. The optimization solution module uses a whale swarm algorithm based on chaotic perturbation to optimize the risk-return adaptive decomposition optimization model, obtains the optimal solution for the contract decomposition variables, and then decomposes the new energy contract electricity volume based on the optimal solution.

[0124] It is understood that the content of the above method embodiments is applicable to the present device embodiments. The specific functions implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0125] Reference Figure 3 This invention provides an electronic device, comprising: At least one processor; At least one memory for storing at least one program; When the above-mentioned at least one program is executed by the above-mentioned at least one processor, the above-mentioned at least one processor implements the above-mentioned method for decomposing new energy contract electricity.

[0126] It is understood that the content of the above method embodiments is applicable to this device embodiment. The specific functions implemented by this device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0127] This invention also provides a computer-readable storage medium storing a processor-executable computer program that, when executed by a processor, implements the above-described method for decomposing renewable energy contract electricity.

[0128] This invention provides a computer-readable storage medium that can execute a new energy contract electricity decomposition method provided in the method embodiment of this invention. It can execute any combination of the implementation steps of the method embodiment and has the corresponding functions and beneficial effects of the method.

[0129] This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method for decomposing new energy contract electricity.

[0130] It is understood that the content of the above method embodiments is applicable to the embodiments of this program product. The specific functions implemented by the embodiments of this program product are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0131] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0132] The embodiments described in this invention are for the purpose of more clearly illustrating the technical solutions of the embodiments of this invention, and do not constitute a limitation on the technical solutions provided by the embodiments of this invention. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this invention are also applicable to similar technical problems.

[0133] The terms "first," "second," "third," "fourth," etc. (if present) in the specification and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0134] In some alternative embodiments, the functions / operations mentioned in the block diagrams may not occur in the order shown in the operation diagrams. For example, depending on the functions / operations involved, two consecutively shown blocks may actually be executed substantially simultaneously, or the aforementioned blocks may sometimes be executed in reverse order. Furthermore, the embodiments presented and described in the flowcharts of this invention are provided by way of example to provide a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed and sub-operations described as part of a larger operation are executed independently.

[0135] Furthermore, although the invention has been described in the context of functional modules, it should be understood that, unless otherwise stated, one or more of the aforementioned functions and / or features may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the invention. Rather, given the properties, functions, and internal relationships of the various functional modules in the apparatus disclosed herein, the actual implementation of the module will be understood within the scope of conventional skill of an engineer. Therefore, those skilled in the art can implement the invention as set forth in the claims using ordinary techniques without excessive experimentation. It is also understood that the specific concepts disclosed are merely illustrative and not intended to limit the scope of the invention, which is determined by the full scope of the appended claims and their equivalents.

[0136] If the aforementioned functions 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, the technical solution of this invention, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0137] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0138] More specific examples (a non-exhaustive list) of computer-readable media include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the aforementioned program can be printed, because the aforementioned program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0139] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0140] In the foregoing description of this specification, references to terms such as "one embodiment," "another embodiment," or "some embodiments" indicate that a specific feature, structure, material, or characteristic described in connection with an embodiment or example is included in at least one embodiment or example of the present invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0141] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

[0142] The above is a detailed description of the preferred embodiments of the present invention. However, the present invention is not limited to the above embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention. All such equivalent modifications or substitutions are included within the scope defined by the claims of the present invention.

Claims

1. A new energy contract electricity decomposition method, characterized in that, The method comprises the following steps: a new energy output prediction model considering uncertainty is established, and system operation constraints corresponding to contract decomposition variables are determined; a risk measurement model and a benefit calculation model are constructed according to the contract decomposition variables, and a risk-benefit adaptive coupling coefficient is determined; a risk-benefit adaptive decomposition optimization model is constructed according to the risk measurement model, the benefit calculation model and the risk-benefit adaptive coupling coefficient; the risk-benefit adaptive decomposition optimization model is optimized and solved by using a whale optimization algorithm improved based on chaotic disturbance, so that an optimal solution of the contract decomposition variables is obtained, and then new energy contract power decomposition is performed according to the optimal solution.

2. The method of claim 1, wherein, The new energy output prediction model is: wherein, denotes the actual output of new energy at time period t, denotes the predicted output of new energy at time period t, denotes the error correction coefficient, denotes the prediction error at time period t; The contract decomposition variables are: wherein, represents the disaggregated electrical quantity of contract type k for the time period t, k = 1 corresponds to a baseload contract , k = 2 corresponds to a peak load contract ; The system operation constraints include a contract power conservation constraint and an output-contract matching constraint, and the contract power conservation constraint is: wherein T represents a contract execution period set, represents the total power of the new energy contract; The output-contract matching constraint is: wherein, the decomposed electric power of the base load contract for the t period, the decomposed electric power of the peak load contract for the t period, the reserve power output for the t period.

3. The method of claim 2, wherein, The risk measurement model is: wherein, represents the conditional value at risk at a confidence level represents the conditional expectation function, represents the loss function for period t, represents the risk value at a confidence level represents the spot market electricity price for period t, represents the execution price for contract type k for period t;​​ The benefit calculation model is: wherein, represents the contract execution revenue for the period t; The risk-benefit adaptive coupling coefficient is: wherein, represents the risk-reward adaptive coupling coefficient for the period t.

4. The method of claim 3, wherein, The risk-benefit adaptive decomposition optimization model includes an objective function with a risk-adjusted benefit maximization as an optimization target, and multi-period coupling constraints and decomposition quantity upper and lower limit constraints, and the objective function is: where F denotes the risk-adjusted return, denotes the dynamic risk aversion coefficient at time t. The multi-period coupling constraints are: wherein, represents the disaggregated electrical quantity of contract type k at time period t+1, represents the inter-period adjustment factor; The decomposition quantity upper and lower limit constraints are: wherein, , respectively represent the minimum and maximum decomposed power of the time period contract type k.

5. The method of claim 4, wherein, The risk-benefit adaptive decomposition optimization model is optimized and solved by using a whale optimization algorithm improved based on chaotic disturbance, so that an optimal solution of the contract decomposition variables is obtained, and the specific steps include: an initial whale position corresponding to the contract decomposition variables is determined by using chaotic mapping, and a risk-benefit guide factor is determined according to the risk-benefit adaptive coupling coefficient; a whale is initialized according to the initial whale position; fitness of each individual in the whale is determined; a global optimal position is determined according to the fitness, and a current convergence factor and a current coefficient vector are calculated; an individual guide position of each individual in the next iteration is calculated according to the global optimal position, the current convergence factor, the current coefficient vector and the risk-benefit guide factor; the whale is updated according to the individual guide position, and the step of determining the fitness of each individual in the whale is returned until a preset convergence condition is reached, and an optimal solution of the contract decomposition variables is determined according to a position of a current optimal individual.

6. The method of claim 5, wherein, The fitness is calculated by the following formula: wherein, represents the fitness, represents the penalty coefficient.

7. The method of claim 5, wherein, The initial whale position is determined by the following formula: wherein, represents the coordinate value of the ith individual in the dth dimension, d = 1 corresponds to the base load contract dimension, d = 2 corresponds to the peak load contract dimension, and respectively represent the minimum value and the maximum value of the contract decomposition variable in the dth dimension, represents the ith element in the chaotic sequence in the dth dimension of the contract decomposition convenience; The risk-benefit guide factor is calculated by the following formula: wherein, represents a risk-reward guiding factor, represents a maximum value of the risk-reward self-adaptive coupling coefficient in the whole period. The individual guide position is calculated by the following formula: wherein, represents an individual guide position of the i-th particle at the t+1th iteration, represents a current individual position of the i-th particle, represents a current iteration number, represents a maximum iteration number, represents a current convergence factor, A and C represent a current coefficient vector, r represents a first random number within [0, 1], p represents a selection probability, p ∈ [0, 1], represents a distance parameter, b is a preset constant, represents a second random number within [-1, 1], represents a global optimal position at the tth iteration.

8. A new energy contract electricity decomposition device, characterized in that, The method comprises the following steps: a contract decomposition modeling module is configured to establish a new energy output prediction model considering uncertainty, and to determine system operation constraints corresponding to contract decomposition variables; a risk-benefit coupling analysis module is configured to construct a risk measurement model and a benefit calculation model according to the contract decomposition variables, and to determine a risk-benefit adaptive coupling coefficient; a risk-benefit adaptive decomposition modeling module is configured to construct a risk-benefit adaptive decomposition optimization model according to the risk measurement model, the benefit calculation model and the risk-benefit adaptive coupling coefficient. The optimization solving module optimizes and solves the risk-reward adaptive decomposition optimization model based on a whale optimization algorithm improved based on chaotic disturbance, obtains an optimal solution of the contract decomposition variable, and then performs new energy contract power decomposition according to the optimal solution.

9. An electronic device, comprising: The method comprises the following steps: at least one processor; at least one memory for storing at least one program; when the at least one program is executed by the at least one processor, the at least one processor implements the new energy contract power decomposition method according to any one of claims 1 to 7.

10. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the new energy contract power decomposition method according to any one of claims 1 to 7. The computer program is executed by the processor to implement the new energy contract power decomposition method according to any one of claims 1 to 7.

Images