A method and device for decomposing and optimizing medium and long term contract electricity

Abstract

This invention relates to the field of power system optimal dispatching technology, and discloses a method and apparatus for optimizing the decomposition of medium- and long-term contract electricity. The method includes: using the decomposition curve of medium- and long-term contract electricity within a preset dispatching period as decision variables, constructing a basic market revenue function and a nonlinear profit recovery function; constructing a physical anchoring function, and establishing a sub-Blucher bar optimization model based on the basic market revenue function, the nonlinear profit recovery function, and the physical anchoring function; transforming the sub-Blucher bar optimization model into a mixed-integer second-order cone programming model; and solving the mixed-integer second-order cone programming model to obtain the optimal contract electricity decomposition curve. This invention maximizes the total net profit under adverse operating conditions such as extreme weather and market price inversion, significantly improving the robustness and economy of decision-making.

Description

Technical Field

[0001] This invention relates to the field of power system optimization and dispatching technology, specifically to a method and apparatus for optimizing the decomposition of medium- and long-term contracted electricity volumes. Background Technology

[0002] With the advancement of energy transition, the scale of new energy grid connection continues to expand. New energy output has strong random fluctuation characteristics. In order to adapt to the random fluctuation of new energy output and ensure the real-time supply and demand balance of the power system, the power market generally adopts a combination of medium- and long-term contracts and spot market deviations. Some markets also implement full-electricity settlement and nonlinear benefit recovery constraint mechanisms, which impose stringent requirements on the accuracy of power generator contract decomposition.

[0003] However, the relevant medium- and long-term contract decomposition methods are difficult to adapt to nonlinear penalty constraints and generally ignore physical operational constraints such as grid congestion and power curtailment. The decision-making adaptability is poor and it is difficult to cope with extreme operating conditions and complex grid operation scenarios, thus affecting the stability of the electricity market. Summary of the Invention

[0004] This invention provides a method and apparatus for optimizing the decomposition of medium- and long-term contract electricity, in order to solve the problem that related medium- and long-term contract decomposition methods are difficult to balance nonlinear penalty avoidance and power grid physical constraints.

[0005] In a first aspect, the present invention provides a method for optimizing the decomposition of electricity volume in medium- and long-term contracts, the method comprising: Using the medium- and long-term contract electricity decomposition curve within the preset scheduling period as decision variables, a basic market return function and a nonlinear profit recovery function are constructed respectively. Construct a physical anchoring function, and establish a sub-Bruker bar optimization model based on the basic market return function, the nonlinear profit recovery function, and the physical anchoring function; Transform the sub-Blule bar optimization model into a mixed integer second-order cone programming model; The optimal contract power decomposition curve is obtained by solving the mixed integer second-order cone programming model.

[0006] This invention provides a method for optimizing the decomposition of medium- and long-term contract electricity. It directly presets the decomposition curve of medium- and long-term contract electricity within the scheduling period as the decision variable, couples it to construct a nonlinear benefit-recovery function, adapts to nonlinear penalty constraints, and then establishes a sub-Blu-ray optimization model based on the basic market benefit function, the nonlinear benefit-recovery function, and the physical anchoring function. By introducing the physical anchoring function, the actual physical operation constraints of the power grid are quantified, balancing nonlinear penalty avoidance with power grid physical constraints. The sub-Blu-ray optimization model takes into account stochastic risks such as renewable energy fluctuations and electricity price uncertainties, effectively coping with extreme operating conditions and complex power grid operation scenarios, avoiding the problem of insufficient robustness of a single deterministic decomposition scheme. Furthermore, the complex sub-Blu-ray model is transformed into a efficiently solvable mixed-integer second-order cone programming model, ensuring the global optimum of the contract decomposition scheme and solving the problem of the difficulty in calculating and implementing complex robust models. Finally, the mixed-integer second-order cone programming model is solved to obtain the optimal contract electricity decomposition curve, balancing economic benefits and the needs of power grid safe operation, avoiding the operational risks caused by unreasonable contract decomposition, and effectively maintaining the long-term stable operation of the electricity market.

[0007] In one optional implementation, the medium- and long-term contract electricity decomposition curve within a preset scheduling period is used as the decision variable to construct a basic market return function and a nonlinear profit recovery function, including: Obtain medium- and long-term contract prices, real-time node marginal electricity prices, and actual renewable energy output within the preset scheduling period; Basic market revenue functions are constructed based on the medium- and long-term contract power decomposition curve, medium- and long-term contract price, real-time node marginal electricity price, and actual renewable energy output, respectively. Obtain the penalty coefficient and exemption threshold, and construct a nonlinear benefit recovery function based on the price difference between the penalty coefficient, exemption threshold, medium- and long-term contract price and real-time node marginal electricity price, as well as the power deviation between the medium- and long-term contract power decomposition curve and the actual renewable energy output.

[0008] The present invention provides a method for optimizing the decomposition of medium- and long-term contract electricity volume, which accurately models the complex nonlinear benefit recovery mechanism in the electricity market. Compared with the simplified model, it can more accurately identify and avoid high penalty intervals, that is, areas where high price differences and large deviations occur simultaneously, significantly reducing nonlinear recovery costs and directly reducing the compliance costs of power generators.

[0009] In one alternative implementation, a physical anchoring function is constructed, and a sub-Bruker optimization model is established based on the underlying market return function, the nonlinear gain-recovery function, and the physical anchoring function, including: Obtain the power curtailment probability, anchoring strength coefficient, and predicted renewable energy output; construct a physical anchoring function based on the power curtailment probability, anchoring strength coefficient, predicted renewable energy output, and medium- and long-term contract power decomposition curves. Obtain the historical data empirical distribution and robust radius corresponding to renewable energy output and nodal electricity price, and construct a true distribution set based on the historical data empirical distribution and robust radius; wherein the difference between the true distribution and the historical data empirical distribution in the true distribution set does not exceed the robust radius; With the goal of maximizing the expected net return under the worst probability distribution within the true distribution set, an initial objective function is constructed based on the basic market return function and the nonlinear profit recovery function. The initial objective function is transformed into a dual function, and a split-bar optimization model is established by combining it with the physical anchoring function.

[0010] This invention provides a method for optimizing the decomposition of medium- and long-term contract electricity. It embeds grid physical state information (congestion probability) into the anchoring regularization term of the sub-Bluhl bar optimization, constructing a physical anchoring function. This gives the sub-Bluhl bar optimization model physical awareness, enabling it to guide the optimization direction using physical laws beyond data features. Furthermore, by constructing a set of real distributions, and aiming to maximize the expected net profit under the worst-case probability distribution within this set, an initial objective function is constructed based on the basic market return function and the nonlinear profit recovery function. This eliminates reliance on a single probability distribution assumption, effectively addressing abnormal events. The initial objective function is then transformed into a dual function, achieving precise construction of the sub-Bluhl bar optimization model.

[0011] In one optional implementation, a physical anchoring function is constructed based on the power curtailment probability, anchoring strength coefficient, renewable energy forecast output, and medium- to long-term contract power decomposition curve; wherein, the expression of the physical anchoring function is:

[0012] In the above formula, Represents the physical anchoring function. express The probability of power outages during certain time periods. Indicates the anchoring strength coefficient. express Contract breakdown power during the time period express Forecasted renewable energy output for the period This indicates the preset scheduling period.

[0013] In one alternative implementation, the sub-Bruker optimization model is transformed into a mixed-integer second-order cone programming model, including: The risk value and tail loss are obtained, and the sub-Bruker optimization model is transformed based on the risk value and tail loss to obtain the mixed integer programming objective function; By using the linearization constraint of conditional value of risk, the relaxation constraint of loss function, the rigid constraint of total monthly electricity consumption, and the upper and lower physical limits as constraints on the objective function of mixed integer programming, a mixed integer second-order cone programming model is constructed.

[0014] This invention provides a method for optimizing the decomposition of medium- and long-term contract electricity volume. It introduces risk value and tail loss quantification indicators to accurately characterize tail risks under electricity price fluctuations, renewable energy volatility, and extreme operating conditions. Based on risk value and tail loss, it completes an equivalent transformation of the robust optimization model, simplifying the complex robust optimization structure. A regular mixed-integer programming objective function is derived, improving the model's solvability. Furthermore, it incorporates conditional risk value linearization constraints, loss function relaxation constraints, rigid constraints on total monthly electricity volume, and physical upper and lower bound constraints as constraints on the mixed-integer programming objective function. This allows the mixed-integer second-order cone programming model to consider economic rules, electricity volume assessment, and grid operation boundaries. The resulting mixed-integer second-order cone programming model is compatible with nonlinear penalty constraints and complex physical constraints, adapting to complex operating scenarios such as grid congestion and power curtailment. This enhances its adaptability under extreme conditions and ensures the stable and orderly operation of the electricity market.

[0015] In one optional implementation, the sub-Bruker optimization model is transformed based on value at risk and tail loss to obtain a mixed-integer programming objective function; wherein the expression of the mixed-integer programming objective function is:

[0016] in, Value at risk (VaR) Indicates the confidence level. Indicates the number of scenes. Representing a scene Tail damage, This represents the non-blocking probability.

[0017] Secondly, the present invention provides a medium- and long-term contract electricity allocation optimization device, the device comprising: The module is used to construct the basic market return function and the nonlinear profit recovery function by taking the medium- and long-term contract electricity decomposition curve within the preset scheduling period as the decision variable. A module is established to construct the physical anchoring function, and a sub-Bruker optimization model is built based on the basic market return function, the nonlinear profit recovery function, and the physical anchoring function; The conversion module is used to convert the sub-Bruker optimization model into a mixed integer second-order cone programming model; The solver module is used to solve the mixed-integer second-order cone programming model to obtain the optimal contract power decomposition curve.

[0018] Thirdly, the present invention provides an electronic device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the medium- and long-term contract power decomposition optimization method of the first aspect or any corresponding embodiment described above.

[0019] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the medium- and long-term contract power allocation optimization method of the first aspect or any corresponding embodiment thereof.

[0020] Fifthly, the present invention provides a computer program product, including computer instructions for causing a computer to execute the medium- and long-term contract power decomposition optimization method described in the first aspect or any corresponding embodiment thereof. Attached Figure Description

[0021] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0022] Figure 1 This is a schematic diagram of an application scenario according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the first process of a medium- and long-term contract power decomposition optimization method according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the second process of a medium- and long-term contract power decomposition optimization method according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the third process of a medium- and long-term contract power decomposition optimization method according to an embodiment of the present invention. Figure 5 This is a schematic diagram of the fourth process of a medium- and long-term contract power decomposition optimization method according to an embodiment of the present invention; Figure 6 This is an improved medium- and long-term contract curve diagram according to an embodiment of the present invention; Figure 7 This is a diagram showing the comparison of the daily returns of medium- and long-term contracts for the next 15 days of the test period using different methods according to embodiments of the present invention. Figure 8 This is a diagram showing the daily spot deviation returns of different methods according to embodiments of the present invention over the next 15 days of the test period; Figure 9This is a diagram comparing the daily benefit recovery cost of different methods according to embodiments of the present invention over the next 15 days of the test period; Figure 10 This is a diagram showing the comparison of net returns for each day of the next 15 days during the test period using different methods according to embodiments of the present invention. Figure 11 This is a structural block diagram of a medium- and long-term contract power allocation optimization device according to an embodiment of the present invention; Figure 12 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0024] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.

[0025] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0026] As an optional application scenario of this invention, such as Figure 1 As shown, the medium- and long-term contract power allocation optimization system may include at least one terminal device and at least one server. Figure 1 The system is illustrated in the example, which includes a computer 101, a mobile terminal 102, and a server 103, and the terminal devices such as the computer 101 and the mobile terminal 102 are connected to the server 103 through a network 110.

[0027] Specifically, the terminal device can be a smartphone, tablet, laptop, PDA, desktop computer, game console, smart TV, smart wearable device, in-vehicle terminal, VR (Virtual Reality) device, AR (Augmented Reality) device, etc. Server 103 can be a standalone physical server, a server cluster, a distributed system, or a cloud server providing cloud services. Network 110 can be a wired or wireless network, examples of which include, but are not limited to, the Internet, corporate intranet, local area network, wide area network, mobile communication network, and combinations thereof.

[0028] With the acceleration of the global energy transition, the installed capacity of new energy sources, represented by wind power and photovoltaics, continues to rise. In order to adapt to the random fluctuations in new energy output and ensure the real-time supply and demand balance of the power system, the power market generally implements a dual settlement mechanism of locking in medium- and long-term contracts and settling deviations in the spot market. Under this mechanism, the revenue of power generators mainly includes medium- and long-term revenue and spot settlement. Most of the revenue is locked in by signing medium- and long-term contracts on an annual / monthly / weekly / multi-day basis. In spot trading, the deviation between the actual grid-connected power volume and the contracted power volume needs to be settled according to the spot market price. This requires power generators to develop accurate contract decomposition curves to avoid the risk of negative deviations.

[0029] Meanwhile, in practice, in some provinces with large-scale renewable energy, in order to curb speculative arbitrage by power generators using the price difference between contract prices and spot prices, regulatory agencies usually introduce strict total electricity settlement rules and a corresponding non-linear profit recovery mechanism. This mechanism has significant asymmetric and punitive characteristics: when the contract price is higher than the spot price, power generators tend to sign more contracts. If the actual output is insufficient, the regulator will charge a shortfall profit recovery fee for the under-generated portion. Conversely, when the spot price is higher than the contract price, power generators tend to sign fewer contracts to sell electricity at a higher price in the spot market. If the actual output exceeds the contract price, the regulator will charge an excess profit recovery fee for the over-generated portion. This mechanism means that power generators not only have to bear the spot settlement risk caused by physical deviations, but also face huge fines due to strategic deviations.

[0030] Therefore, renewable energy generators face a double threat when allocating contracted power volumes: firstly, there is the uncertainty of source and load, as photovoltaic / wind power output is greatly affected by weather, often accompanied by sudden extreme weather events (such as cloud cover, no wind, etc.), causing actual output to deviate significantly from the predicted value, potentially resulting in negative deviation charges; secondly, there are the physical constraints of the power grid, where grid congestion leading to power rationing at the generation end often causes a sharp drop in nodal prices, and maintaining high contract volumes at this time will trigger huge penalties for profit recovery. However, relevant optimization methods are insufficient to cope with the above complex scenarios.

[0031] Among the relevant contract decomposition methods, deterministic optimization, stochastic programming, and traditional robust optimization are the main ones, but all of them have significant drawbacks: deterministic optimization usually makes decisions based on the mean of short-term power forecasts. Its disadvantage is that it completely ignores the probability distribution of forecast errors. Once deviations occur in actual operation, it is very easy to trigger nonlinear assessment thresholds, resulting in a significant reduction in returns. Stochastic programming simulates uncertainty by generating a large number of historical scenarios. Its disadvantage is that it assumes that the future distribution is completely consistent with the historical experience distribution (the same distribution assumption), which is prone to "overfitting". When facing extreme weather or sudden events outside the sample, the performance of this method is often extremely poor. Furthermore, relevant data-driven methods usually only focus on the statistical characteristics of the data and ignore the physical state of the power grid operation, such as the problem of power curtailment due to congestion. This leads to the strategy being too conservative during safe periods when the power grid is not congested. During high-risk periods of congestion, the strategy adjustment capability is insufficient, and it is impossible to achieve a dynamic balance between economic efficiency and physical feasibility.

[0032] To address the aforementioned shortcomings, this invention provides a medium- to long-term contract power decomposition optimization method applicable to contract-based optimal scheduling of renewable energy generation in dual-settlement electricity markets. This method addresses the difficulty in simultaneously addressing uncertainty handling, nonlinear penalty avoidance, and grid physical constraints by constructing a physically anchored sub-Bullish rod optimization framework. It uses Wasserstein distance (an important tool for measuring the difference between two probability distributions) to construct a fuzzy set covering the uncertainties of power output and electricity price, explicitly models a non-convex piecewise linear excess / deficit benefit recovery mechanism, and transforms it into a solvable form of mixed-integer second-order cone programming. A physically anchored regularization term is designed to dynamically adjust the conservatism of the strategy based on the probability of time-based power curtailment, achieving a dynamic balance between tracking predicted values ​​during non-blocking periods and flexibly avoiding risks during blocked periods. Ultimately, this maximizes the total net revenue of power generators under adverse conditions such as extreme weather and market price inversions, significantly improving the robustness and economy of decision-making.

[0033] According to an embodiment of the present invention, an embodiment of a method for optimizing the decomposition of medium- and long-term contract electricity is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0034] This embodiment provides a method for optimizing the allocation of electricity under medium- and long-term contracts, which can be used in the aforementioned terminal devices. Figure 2 This is a flowchart of a medium- and long-term contract power allocation optimization method according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps: Step S201: Using the medium- and long-term contract electricity decomposition curve within the preset scheduling period as decision variables, construct the basic market return function and the nonlinear profit recovery function respectively.

[0035] Specifically, the preset scheduling period is defined as follows: (The time resolution can be set to 15 minutes, i.e.) The decision variable is the decomposition curve of the declared medium- and long-term contract electricity volume. ,in for Contract breakdown power (MW) for the time period.

[0036] Step S202: Construct the physical anchoring function, and establish a sub-Blu-ray optimization model based on the basic market return function, the nonlinear profit recovery function, and the physical anchoring function.

[0037] Specifically, since renewable energy output and nodal electricity prices have strong spatiotemporal coupling and non-Gaussian distribution characteristics, and face the dual tail risks of extreme weather (such as sudden cloud cover) and grid congestion, the relevant stochastic programming is prone to failure in out-of-sample tests due to its over-reliance on historical experience distributions. Therefore, a distributed bar optimization model is established to solve the above problems.

[0038] Step S203: Transform the sub-Bruker optimization model into a mixed integer second-order cone programming model.

[0039] Specifically, since the above-mentioned sub-Bruker optimization model cannot be solved directly, in order to solve the sub-Bruker optimization model, it is transformed into a discretized mixed integer programming or linear programming problem, that is, the sub-Bruker optimization model is transformed into a solvable MISOCP (Mixed-Integer Second-Order Cone Programming) form, thus obtaining the mixed integer second-order cone programming model.

[0040] Step S204: Solve the mixed integer second-order cone programming model to obtain the optimal contract electricity decomposition curve.

[0041] Specifically, by solving the above mixed-integer second-order cone programming model, an optimal contract decomposition curve that balances economy and robustness can be obtained under the conditions of distribution uncertainty and physical congestion risk.

[0042] Among them, the mixed integer second-order cone programming model can be solved by methods such as branch and bound method, branch and cut method, Lagrange decomposition method, and commercial solvers (such as CPLEX solver).

[0043] This embodiment provides a method for optimizing the decomposition of medium- and long-term contract electricity. It directly presets the decomposition curve of medium- and long-term contract electricity within the scheduling period as the decision variable, couples it to construct a nonlinear benefit-recovery function, adapts to nonlinear penalty constraints, and then establishes a sub-Blu-ray optimization model based on the basic market benefit function, the nonlinear benefit-recovery function, and the physical anchoring function. By introducing the physical anchoring function, the actual physical operation constraints of the power grid are quantified, balancing nonlinear penalty avoidance with power grid physical constraints. The sub-Blu-ray optimization model takes into account stochastic risks such as renewable energy fluctuations and electricity price uncertainty, effectively coping with extreme operating conditions and complex power grid operation scenarios, avoiding the problem of insufficient robustness of a single deterministic decomposition scheme. Furthermore, the complex sub-Blu-ray model is transformed into a efficiently solvable mixed-integer second-order cone programming model, ensuring the global optimum of the contract decomposition scheme and solving the problem of the difficulty in calculating and implementing complex robust models. Finally, the mixed-integer second-order cone programming model is solved to obtain the optimal contract electricity decomposition curve, balancing economic benefits and the needs of power grid safe operation, avoiding the operational risks caused by unreasonable contract decomposition, and effectively maintaining the long-term stable operation of the electricity market.

[0044] This embodiment provides a method for optimizing the allocation of electricity under medium- and long-term contracts, which can be used in the aforementioned terminal devices. Figure 3 This is a flowchart of a medium- and long-term contract power allocation optimization method according to an embodiment of the present invention, such as... Figure 3 As shown, the process includes the following steps: Step S301: Using the medium- and long-term contract electricity decomposition curve within the preset scheduling period as decision variables, construct the basic market return function and the nonlinear profit recovery function respectively.

[0045] In some optional implementations, step S301 above includes: Step S3011: Obtain the medium- and long-term contract prices, real-time node marginal electricity prices, and actual renewable energy output within the preset scheduling period.

[0046] Step S3012: Construct basic market revenue functions based on the medium- and long-term contract power decomposition curve, medium- and long-term contract price, real-time node marginal electricity price, and actual renewable energy output.

[0047] Specifically, considering medium- and long-term contract prices With real-time node marginal electricity price , Basic return per period Including settlement gains from medium- and long-term contracts and settlement gains from spot market deviations, the expression for the basic market return function is as follows: (1) in, For random scene vectors, for Actual renewable energy output (MW) during the period.

[0048] Step S3013: Obtain the penalty coefficient and exemption threshold. Based on the penalty coefficient, exemption threshold, price difference between medium- and long-term contract price and real-time node marginal electricity price, and power deviation between medium- and long-term contract power decomposition curve and actual renewable energy output, construct a nonlinear benefit recovery function.

[0049] Specifically, the price difference between medium- and long-term contract prices and real-time node marginal electricity prices. The calculation formula is: (2) Power Deviation Between Medium- and Long-Term Contract Power Decomposition Curve and Actual Renewable Energy Output The calculation formula is: (3) Furthermore, based on price differences and power deviation Construct a piecewise nonlinear recovery cost function, i.e., a nonlinear benefit recovery function. Its expression is: (4) in, , ,or ; Penalty coefficient ( ), The exemption threshold (e.g., 5%) corresponds to the recovery penalty rules for the "shortage profit" and "excess profit" scenarios, respectively. The penalty coefficient and exemption threshold are parameters specified in the power trading settlement rules of each province and region.

[0050] The price difference between medium- and long-term contract prices and real-time node marginal electricity prices, combined with real-time power output and medium- and long-term contract power output, can determine whether power generators are engaging in arbitrage using this price difference. Once determined, excess or shortfall profits will be recovered. .

[0051] The aforementioned physical anchoring mechanism solves the problem of traditional robust optimization being too conservative. The regularized construction of physical-data fusion takes into account both physical feasibility and economy, and only activates the defense mode during high-risk periods of grid congestion, while pursuing high-yield tracking during safe periods. This achieves intelligent dynamic switching between aggressive and conservative strategies, which is more in line with the actual operation of the power grid.

[0052] Step S302: Construct the physical anchoring function and establish a sub-Bruker bar optimization model based on the basic market return function, the nonlinear gain-recovery function, and the physical anchoring function. For details, please refer to [link to details]. Figure 2 Step S202 of the illustrated embodiment will not be described again here.

[0053] Step S303 transforms the sub-Bruker optimization model into a mixed-integer second-order cone programming model. For details, please refer to [link to relevant documentation]. Figure 2 Step S203 of the illustrated embodiment will not be described again here.

[0054] Step S304 involves solving the mixed-integer second-order cone programming model to obtain the optimal contracted electricity decomposition curve. For details, please refer to [link to relevant documentation]. Figure 2 Step S204 of the illustrated embodiment will not be described again here.

[0055] This embodiment provides a method for optimizing the decomposition of medium- and long-term contract electricity volume. It accurately models the complex nonlinear benefit recovery mechanism in the electricity market. Compared with the simplified model, it can more accurately identify and avoid high penalty intervals, that is, areas where high price differences and large deviations occur simultaneously, significantly reducing nonlinear recovery costs and directly reducing the compliance costs of power generators.

[0056] This embodiment provides a method for optimizing the allocation of electricity under medium- and long-term contracts, which can be used in the aforementioned terminal devices. Figure 4 This is a flowchart of a medium- and long-term contract power allocation optimization method according to an embodiment of the present invention, such as... Figure 4 As shown, the process includes the following steps: Step S401 involves using the medium- and long-term contract electricity decomposition curves within a preset scheduling period as decision variables to construct the basic market return function and the nonlinear profit recovery function, respectively. For details, please refer to [link to relevant documentation]. Figure 3 Step S301 of the illustrated embodiment will not be described again here.

[0057] Step S402: Construct the physical anchoring function, and establish a sub-Blu-ray bar optimization model based on the basic market return function, the nonlinear profit recovery function, and the physical anchoring function.

[0058] In some optional implementations, step S402 above includes: Step S4021: Obtain the power curtailment probability, anchoring strength coefficient, and predicted renewable energy output; construct a physical anchoring function based on the power curtailment probability, anchoring strength coefficient, predicted renewable energy output, and medium- and long-term contract power decomposition curve.

[0059] Specifically, for regions with a high proportion of renewable energy, power curtailment frequently occurs on the generation side due to grid congestion. Therefore, a grid state indication function is defined, combined with time periods. of Construct the physical anchoring regularization term, i.e., the physical anchoring function. The expression is: (5) In the above formula, Represents the physical anchoring function. express The probability of power outages during certain time periods. Indicates the anchoring strength coefficient. express Contract breakdown power during the time period express High-precision short-term renewable energy output forecasts This indicates the preset scheduling period.

[0060] In the aforementioned physical anchoring function, the penalty coefficient is large during the non-blocking period, forcing... Anchored predicted values; the penalty coefficient for congestion periods approaches 0, allowing Adjust flexibly.

[0061] Step S4022: Obtain the historical data empirical distribution and robust radius corresponding to the new energy output and node electricity price, and construct a true distribution set based on the historical data empirical distribution and robust radius; wherein, the difference between the true distribution and the historical data empirical distribution in the true distribution set does not exceed the robust radius.

[0062] Specifically, assuming a random scene vector The true distribution Unknown, based on historical data and empirical distribution Construct a set of true distributions, which can be a Wasserstein spherical fuzzy set. Represented as: (6) in, The distance is 1-Wasserstein. The robust radius represents the confidence interval for the degree of trust in the distribution of historical data. for The probability distribution space; Wasserstein spherical fuzzy set Includes all distributions that differ from historical distributions by no more than [a certain percentage]. The potential true distribution.

[0063] Step S4023: With the goal of maximizing the expected net return under the worst probability distribution within the true distribution set, an initial objective function is constructed based on the basic market return function and the nonlinear profit recovery function.

[0064] Specifically, in the Wasserstein spherical fuzzy set Maximizing the expected net gain under the worst-case probability distribution is equivalent to minimizing the expected loss, i.e., random variables Satisfy a specific probability distribution At that time, the decision The average negative returns are borne by the initial objective function, which is a minimization-maximization objective function, and its expression is: (7) in, Let the feasible region be the decision variable. For loss function, The total net return function is calculated as: (Medium- to long-term contract returns + Spot deviation settlement returns - Non-linear profit recovery). Its expression is: (8) in, The duration of the time period (e.g., 0.25 hours).

[0065] Step S4024: The initial objective function is transformed into a dual function, and a split-bar optimization model is established by combining the physical anchoring function.

[0066] Specifically, since the aforementioned infinite-dimensional optimization problem is usually difficult to solve directly, duality theory is used for tractability transformation. When the loss function is convex, it can be transformed into a regularized conditional value at risk (CVaR) problem. To balance engineering practicality and tail risk control, the aforementioned minima-maximum objective function is transformed into: (9) in, For different confidence levels Conditional Value at Risk (VaR) under worst-case scenarios (e.g., the worst 10% scenario).

[0067] Furthermore, the above formula (9) is used as the expression for the sub-Bruker optimization model.

[0068] Step S403 transforms the sub-Bruker optimization model into a mixed-integer second-order cone programming model. For details, please refer to [link to relevant documentation]. Figure 3 Step S303 of the illustrated embodiment will not be described again here.

[0069] Step S404 involves solving the mixed-integer second-order cone programming model to obtain the optimal contracted electricity decomposition curve. For details, please refer to [link to relevant documentation]. Figure 3 Step S304 of the illustrated embodiment will not be described again here.

[0070] This embodiment provides a method for optimizing the decomposition of medium- and long-term contract power. It embeds grid physical state information (congestion probability) into the anchoring regularization term of the distributed bluing bar optimization, constructing a physical anchoring function. This imbues the distributed bluing bar optimization model with physical awareness, enabling it to guide the optimization direction using physical laws beyond data features. Furthermore, by introducing the Wasserstein distributed bluing bar framework and CVaR risk metric, it no longer relies on a single probability distribution assumption, effectively addressing abnormal events such as sudden power output drops due to extreme weather or price inversions caused by sudden grid congestion. Even in the worst-case scenario, it can still guarantee a minimum return, avoiding huge losses and improving risk aversion and survivability. Finally, for the non-convex and asymmetric payback functions in actual market rules, a complete linearization / second-order cone relaxation method is proposed and successfully embedded into the minima-maximum framework of Wasserstein-DRO (Wasserstein Distributionally Robust Optimization, an advanced method for handling distributional uncertainty in optimization problems), forming a convex DRO with a nonlinear payback mechanism. The optimization framework solves the problem of finding robust strategies under complex market rules.

[0071] This embodiment provides a method for optimizing the allocation of electricity under medium- and long-term contracts, which can be used in the aforementioned terminal devices. Figure 5 This is a flowchart of a medium- and long-term contract power allocation optimization method according to an embodiment of the present invention, such as... Figure 5 As shown, the process includes the following steps: Step S501 involves using the medium- and long-term contract electricity decomposition curves within a preset scheduling period as decision variables to construct the basic market return function and the nonlinear profit recovery function, respectively. For details, please refer to [link to relevant documentation]. Figure 4 Step S401 of the illustrated embodiment will not be described again here.

[0072] Step S502: Construct the physical anchoring function and establish a sub-Bruker bar optimization model based on the basic market return function, the nonlinear gain-recovery function, and the physical anchoring function. For details, please refer to [link to details]. Figure 4 Step S402 of the illustrated embodiment will not be described again here.

[0073] Step S503: Transform the sub-Bruker optimization model into a mixed integer second-order cone programming model.

[0074] Specifically, introduce auxiliary variables (VaR, or Value at Risk, corresponds to the maximum possible loss threshold at a given confidence level.) (Scene) Tail loss, specifically referring to the scenario The portion of the actual loss exceeding the VaR value is used to quantify the additional loss caused by extreme risks. A positive tail loss exists only when the actual loss is greater than the VaR value; otherwise, it is zero. (Representing a possible future scenario constructed based on historical data), transforming the sub-Bruker optimization model into a solvable MISOCP form.

[0075] In some optional implementations, step S503 above includes: Step S5031: Obtain the value at risk and tail loss. Based on the value at risk and tail loss, perform model transformation on the split-bar optimization model to obtain the mixed-integer programming objective function.

[0076] Specifically, the expression for the objective function is: (10) in, Value at risk (VaR) Indicates the confidence level. Indicates the number of scenes. Representing a scene Tail damage, This represents the non-blocking probability, and the formula for calculating the non-blocking probability is: (11) Step S5032: The linearization constraint of conditional risk value, the relaxation constraint of loss function, the rigid constraint of monthly electricity consumption, and the upper and lower physical limits are used as constraints of the objective function of mixed integer programming to construct a mixed integer second-order cone programming model.

[0077] Specifically, the expression for the conditional value at risk linearization constraint (i.e., CVaR linearization constraint) is as follows: , , (12) in, For the scene The total loss.

[0078] The expression for the relaxation constraint of the loss function is: (13) (14) (15) (16) The expression for the rigid constraint on total monthly electricity consumption is: (17) in, The target is the average daily electricity consumption.

[0079] The expressions for the physical upper and lower bound constraints are: (18) in, This refers to the installed capacity of the power station.

[0080] Step S504 involves solving the mixed-integer second-order cone programming model to obtain the optimal contracted electricity decomposition curve. For details, please refer to [link to relevant documentation]. Figure 4 Step S404 of the illustrated embodiment will not be described again here.

[0081] This embodiment provides a method for optimizing the decomposition of medium- and long-term contract electricity volume. It introduces risk value and tail loss quantification indicators to accurately characterize tail risks under electricity price fluctuations, renewable energy volatility, and extreme operating conditions. Based on risk value and tail loss, it completes an equivalent transformation of the robust optimization model, simplifying the complex robust optimization structure. A regular mixed-integer programming objective function is derived, improving the model's solvability. Furthermore, it incorporates conditional risk value linearization constraints, loss function relaxation constraints, rigid constraints on total monthly electricity volume, and physical upper and lower bound constraints as constraints on the mixed-integer programming objective function. This allows the mixed-integer second-order cone programming model to consider economic rules, electricity volume assessment, and grid operation boundaries. The resulting mixed-integer second-order cone programming model is compatible with nonlinear penalty constraints and complex physical constraints, adapting to complex operating scenarios such as grid congestion and power curtailment. This enhances its adaptability under extreme scenarios and ensures the stable and orderly operation of the electricity market.

[0082] The effectiveness and practicality of a medium- and long-term contract power allocation optimization method are verified through a specific embodiment below.

[0083] Example 1: A 30-day rolling test was conducted using electricity trading data from a photovoltaic power station. The data from the first 15 days was used to generate medium- and long-term contract curves, and the data from the last 15 days was used for profit comparison testing. The relevant data has been anonymized or generated through simulation.

[0084] The improved medium- and long-term contract curve is as follows: Figure 6 As shown, the method for decomposing and optimizing the electricity volume of medium- and long-term contracts (i.e. Figure 6Comparing the decomposition curve obtained by the proposed method with the original strategy curve reveals that during normal periods when the grid is operating smoothly, both curves closely follow the actual output of photovoltaic power. However, during high-risk periods such as midday when photovoltaic power generation is high and power curtailment is caused by grid congestion, the original curve remains high, blindly trusting the predicted value and resulting in serious "under-generating, over-signing" of power. In contrast, the curve obtained by the medium- and long-term contract power decomposition optimization method shows a clear "concave" shape, accurately reducing the contract amount before the congestion occurs and trying to match the actual output as closely as possible. This indicates that the physical anchoring mechanism has successfully played its role, enabling the strategy to perceive and avoid physical risks of the grid.

[0085] like Figure 7-10 As shown, a comparison is made between the medium- and long-term contract electricity decomposition optimization method (i.e. Figure 7-10 The proposed method), stochastic programming, deterministic optimization, and original strategy are used to calculate the daily medium- to long-term contract returns, spot deviation returns, profit recovery costs, and net returns for the next 15 days during the test period.

[0086] Although the medium- and long-term contract power allocation optimization method is slightly lower than stochastic programming in terms of spot deviation revenue (because it actively abandons some contract volume in high-risk periods), it significantly reduces the "profit recovery cost". Ultimately, after deducting all recovery costs, the net profit of the medium- and long-term contract power allocation optimization method is the highest among all methods. This confirms that this method achieves optimal economic benefits by sacrificing small deviation revenue for huge penalty exemption.

[0087] This embodiment also provides a medium- and long-term contract power allocation optimization device, which is used to implement the above embodiments and preferred embodiments, and will not be repeated as already described. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0088] This embodiment provides a device for optimizing the allocation of electricity under medium- and long-term contracts, such as... Figure 11 As shown, it includes: Module 1101 is used to construct a basic market return function and a nonlinear profit recovery function by taking the medium- and long-term contract power decomposition curve within a preset scheduling period as decision variables. Module 1102 is established to construct the physical anchoring function and to establish a sub-Bruker optimization model based on the basic market return function, the nonlinear profit recovery function and the physical anchoring function. The conversion module 1103 is used to convert the sub-Bruker optimization model into a mixed integer second-order cone programming model; The solver module 1104 is used to solve the mixed integer second-order cone programming model to obtain the optimal contract power decomposition curve.

[0089] In some alternative implementations, the construction module 1101 includes: The acquisition unit is used to acquire the medium- and long-term contract prices, real-time node marginal electricity prices, and actual renewable energy output within a preset scheduling period; The first building unit is used to construct basic market revenue functions based on the medium- and long-term contract power decomposition curve, medium- and long-term contract price, real-time node marginal electricity price, and actual renewable energy output, respectively. The second building unit is used to obtain the penalty coefficient and exemption threshold. Based on the penalty coefficient, exemption threshold, price difference between medium- and long-term contract price and real-time node marginal electricity price, and power deviation between medium- and long-term contract power decomposition curve and actual renewable energy output, a nonlinear benefit recovery function is constructed.

[0090] In some alternative implementations, the establishment module 1102 includes: The third building unit is used to obtain the power curtailment probability, anchoring strength coefficient, and renewable energy forecast output, and to construct a physical anchoring function based on the power curtailment probability, anchoring strength coefficient, renewable energy forecast output, and medium- and long-term contract power decomposition curve. The fourth building unit is used to obtain the historical data empirical distribution and robust radius corresponding to the renewable energy output and the node electricity price, and to construct a set of real distributions based on the historical data empirical distribution and robust radius; wherein the difference between the real distribution and the historical data empirical distribution in the set of real distributions does not exceed the robust radius; The fifth building unit is used to construct an initial objective function based on the basic market return function and the nonlinear profit recovery function, with the goal of maximizing the expected net return under the worst probability distribution within the true distribution set. The dual transformation unit is used to perform dual transformation on the initial objective function and establish a split-bar optimization model in combination with the physical anchoring function.

[0091] In some optional implementations, the expression for the physical anchoring function in the third building block is:

[0092] In the above formula, Represents the physical anchoring function. express The probability of power outages during certain time periods. Indicates the anchoring strength coefficient. express Contract breakdown power during the time period express Forecasted renewable energy output for the period This indicates the preset scheduling period.

[0093] In some alternative implementations, the conversion module 1103 includes: The model transformation unit is used to obtain the value at risk and tail loss. Based on the value at risk and tail loss, the sub-Bruker optimization model is transformed to obtain the mixed integer programming objective function. The sixth building unit is used to construct a mixed-integer second-order cone programming model by taking the linearization constraint of conditional risk value, the relaxation constraint of loss function, the rigid constraint of monthly electricity consumption, and the upper and lower physical limits as constraints of the objective function of mixed-integer programming.

[0094] In some optional implementations, the expression for the mixed-integer programming objective function in the model transformation unit is:

[0095] in, Value at risk (VaR) Indicates the confidence level. Indicates the number of scenes. Representing a scene Tail damage, This represents the non-blocking probability.

[0096] The medium- and long-term contract power allocation optimization device provided in this embodiment of the invention can execute the medium- and long-term contract power allocation optimization method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method. Further functional descriptions of the above modules and units are the same as in the corresponding embodiments described above, and will not be repeated here.

[0097] Figure 12 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0098] The following is a detailed reference. Figure 12 The diagram illustrates a structural schematic suitable for implementing an electronic device according to embodiments of the present invention. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 1201, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 1202 or a program loaded from memory 1208 into random access memory (RAM) 1203. The RAM 1203 also stores various programs and data required for the operation of the electronic device. The processor 1201, ROM 1202, and RAM 1203 are interconnected via a bus 1204. An input / output (I / O) interface 1205 is also connected to the bus 1204.

[0099] Typically, the following devices can be connected to I / O interface 1205: input devices 1206 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 1207 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 1208 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1209. Communication device 1209 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 12 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0100] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 1209, or installed from a memory 1208, or installed from a ROM 1202. When the computer program is executed by the processor 1201, it performs the functions defined in the medium-to-long-term contract power allocation optimization method of the embodiments of the present invention.

[0101] Figure 12 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0102] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as recordable on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and subsequently stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, it implements the medium- to long-term contract power allocation optimization method shown in the above embodiments.

[0103] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0104] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for optimizing the decomposition of electricity volume in medium- and long-term contracts, characterized in that, The method includes: Using the medium- and long-term contract electricity decomposition curve within the preset scheduling period as decision variables, a basic market return function and a nonlinear profit recovery function are constructed respectively. Construct a physical anchoring function, and establish a sub-Bruker optimization model based on the basic market return function, the nonlinear profit recovery function, and the physical anchoring function; The sub-Blule bar optimization model is transformed into a mixed integer second-order cone programming model; The optimal contract power decomposition curve is obtained by solving the mixed integer second-order cone programming model.

2. The method according to claim 1, characterized in that, The step of using the medium- and long-term contract electricity decomposition curve within a preset scheduling period as decision variables to construct a basic market return function and a nonlinear profit recovery function includes: Obtain medium- and long-term contract prices, real-time node marginal electricity prices, and actual renewable energy output within the preset scheduling period; The basic market revenue function is constructed based on the medium- and long-term contract power decomposition curve, the medium- and long-term contract price, the real-time node marginal electricity price, and the actual renewable energy output, respectively. Obtain the penalty coefficient and exemption threshold, and construct the nonlinear benefit recovery function based on the penalty coefficient, the exemption threshold, the price difference between the medium- and long-term contract price and the real-time node marginal electricity price, and the power deviation between the medium- and long-term contract power decomposition curve and the actual renewable energy output.

3. The method according to claim 1, characterized in that, The construction of the physical anchoring function, and the establishment of a sub-Bruker optimization model based on the basic market return function, the nonlinear profit recovery function, and the physical anchoring function, includes: Obtain the power curtailment probability, anchoring strength coefficient, and predicted renewable energy output; and construct a physical anchoring function based on the power curtailment probability, the anchoring strength coefficient, the predicted renewable energy output, and the medium- and long-term contract power decomposition curve. Obtain the historical data empirical distribution and robust radius corresponding to renewable energy output and nodal electricity price, and construct a true distribution set based on the historical data empirical distribution and the robust radius; wherein, the difference between the true distribution in the true distribution set and the historical data empirical distribution does not exceed the robust radius; With the objective of maximizing the expected net return under the worst probability distribution within the true distribution set, an initial objective function is constructed based on the basic market return function and the nonlinear profit recovery function. The initial objective function is transformed into a dual function, and the physical anchoring function is combined to establish the sub-Bruker optimization model.

4. The method according to claim 3, characterized in that, The physical anchoring function is constructed based on the power curtailment probability, the anchoring strength coefficient, the predicted output of renewable energy, and the medium- and long-term contract power decomposition curve; wherein, the expression of the physical anchoring function is: In the above formula, Represents the physical anchoring function. express The probability of power outages during certain time periods. Indicates the anchoring strength coefficient. express Contract breakdown power during the time period express Forecasted renewable energy output for the period This indicates the preset scheduling period.

5. The method according to claim 1, characterized in that, The step of transforming the sub-Bruker optimization model into a mixed integer second-order cone programming model includes: Obtain the value at risk and the tail loss, and transform the sub-Bruker optimization model based on the value at risk and the tail loss to obtain the mixed integer programming objective function; The mixed-integer second-order cone programming model is constructed by using the linearization constraint of conditional value of risk, the relaxation constraint of loss function, the rigid constraint of total monthly electricity consumption, and the upper and lower physical limits as constraints on the objective function of the mixed-integer programming.

6. The method according to claim 5, characterized in that, The model transformation based on the value at risk and the tail loss yields a mixed-integer programming objective function; wherein the expression of the mixed-integer programming objective function is: in, Value at risk (VaR) Indicates the confidence level. Indicates the number of scenes. Representing a scene Tail damage, This represents the non-blocking probability.

7. A device for optimizing the allocation of medium- and long-term contract electricity, characterized in that, The device includes: The module is used to construct the basic market return function and the nonlinear profit recovery function by taking the medium- and long-term contract electricity decomposition curve within the preset scheduling period as the decision variable. A module is established to construct the physical anchoring function, and a sub-Bruker optimization model is established based on the basic market return function, the nonlinear profit recovery function, and the physical anchoring function; The conversion module is used to convert the sub-Bruker optimization model into a mixed integer second-order cone programming model; The solution module is used to solve the mixed integer second-order cone programming model to obtain the optimal contract power decomposition curve.

8. An electronic device, characterized in that, include: The system includes a memory and a processor, which are interconnected. The memory stores computer instructions, and the processor executes the computer instructions to perform the medium- and long-term contract power decomposition optimization method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the medium- and long-term contract power decomposition optimization method according to any one of claims 1 to 6.

10. A computer program product, characterized in that, It includes computer instructions for causing a computer to execute the medium- and long-term contract power decomposition optimization method according to any one of claims 1 to 6.

Images