Power grid power quotation strategy generation method, device and equipment, storage medium and program product

Abstract

The application relates to a power grid power quotation strategy optimization method, device, equipment, storage medium and program product. The method comprises the following steps: according to a Monte Carlo simulation algorithm, simulating market scenes of each single building in a multi-element building group to generate a plurality of market scenes; obtaining an overall risk index of the multi-element building according to the plurality of market scenes; simulating market clearing of the power grid according to a plurality of candidate quotation strategies prepared in advance to obtain expected income corresponding to each candidate quotation strategy; inputting the overall risk index, the plurality of candidate quotation strategies and the expected income into an optimization model to perform strategy optimization and generating an optimal power quotation strategy. The method can realize quantification of the aggregator's risk and calculation of the income under a complex uncertain environment, effectively solves the technical problem that a traditional method is difficult to balance the income and the risk, and significantly improves the quotation decision-making ability and the risk resistance level of the aggregator in the power market.

Description

Technical Field

[0001] This application relates to the field of power grid technology, and in particular to a method, apparatus, equipment, storage medium, and program product for optimizing power grid pricing strategies. Background Technology

[0002] With the advancement of "dual-carbon" goals and the continuous increase in the penetration rate of new energy sources, the operation mode of the power system is undergoing profound changes. The large-scale integration of intermittent renewable energy sources has exacerbated fluctuations in power supply and demand, making traditional generation-side regulation insufficient to meet the future flexibility requirements of the power system. Demand response, as a crucial means of enhancing the regulation capacity of the consumption side, can guide users to proactively adjust their electricity consumption behavior, playing a key role in peak shaving and valley filling, improving the efficiency of power resource utilization, and ensuring grid security. Currently, the user response behavior of diverse building clusters is influenced by multiple factors, including environmental factors, user habits, and market electricity prices, exhibiting significant randomness and uncertainty. Simultaneously, the demand response market mechanism is gradually improving, with building load aggregators becoming important players connecting users and the market, undertaking responsibilities such as load forecasting, market pricing, and revenue and risk management.

[0003] However, existing methods mostly employ static forecasting, which is insufficient to address the dynamic characteristics of load in complex market environments, making it difficult for aggregators to formulate accurate electricity pricing strategies. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, apparatus, equipment, storage medium, and program for optimizing power grid pricing strategies to address the aforementioned technical problems.

[0005] Firstly, this application provides an optimization method for power grid pricing strategies, including:

[0006] Based on the Monte Carlo simulation algorithm, market scenarios are simulated for each individual building in a multi-building complex, generating multiple market scenarios.

[0007] Based on multiple market scenarios, we obtained the overall risk indicators for diverse buildings;

[0008] The market clearing simulation of the power grid is conducted based on multiple pre-defined candidate bidding strategies to obtain the expected returns corresponding to each candidate bidding strategy;

[0009] The overall risk index, multiple candidate pricing strategies, and expected returns are input into the optimization model to optimize the strategy and generate the optimal electricity pricing strategy.

[0010] In one embodiment, based on multiple market scenarios, a comprehensive risk index for diverse buildings is obtained, including:

[0011] Based on multiple market scenarios, the risks of each individual building are quantified to obtain a comprehensive risk index for each individual building.

[0012] Based on the comprehensive risk index of each individual building, the overall risk index of the multi-building complex is calculated.

[0013] In one embodiment, based on multiple market scenarios, the risk of each individual building is quantified to obtain a comprehensive risk index for each individual building, including:

[0014] Calculate the loss vector for each market scenario based on multiple market scenarios;

[0015] Based on each loss vector and a preset confidence level, calculate the value at risk corresponding to each loss vector.

[0016] Based on each risk value, a comprehensive risk index for each individual building is obtained.

[0017] In one embodiment, based on multiple market scenarios, a loss vector corresponding to each market scenario is calculated, including:

[0018] The user default loss vector is calculated based on the degree of inconsistency between the user's actual response volume and the promised response volume.

[0019] The market volatility loss vector is calculated based on the fluctuations between the actual market clearing price and the expected price.

[0020] The environmental change loss vector is calculated based on the degree of baseline load shift caused by changes in environmental factors.

[0021] In one embodiment, market scenarios are simulated for each individual building in a multi-building complex using the Monte Carlo simulation algorithm, generating multiple market scenarios, including:

[0022] The environmental change factors of a multi-building complex are modeled based on the Ornstein-Uhlenbeck model, and the probability distribution of the environmental change factors is obtained.

[0023] The market fluctuations of the power grid are modeled based on geometric Brownian motion combined with a jump-diffusion model, and the probability distribution of market fluctuations is obtained.

[0024] The uncertainty factors of user response to multi-building complexes are modeled based on the beta distribution model, and the probability distribution of user response uncertainty factors is obtained.

[0025] Based on the Monte Carlo simulation algorithm, samples are drawn from the probability distributions of environmental change factors, market fluctuations, and user response uncertainty factors to simulate market scenarios and generate multiple market scenarios.

[0026] In one embodiment, the method for generating a power grid pricing strategy further includes:

[0027] Based on market clearing simulation, the clearing price and winning bid volume corresponding to multiple pre-defined candidate bidding strategies are obtained;

[0028] The expected return is obtained based on the clearing price, the winning bid volume, and the overall risk indicators.

[0029] Secondly, this application also provides an optimization device for power grid pricing strategies, comprising:

[0030] The first simulation module is used to simulate market scenarios for each individual building in a multi-building complex based on the Monte Carlo simulation algorithm, generating multiple market scenarios.

[0031] The risk module is used to obtain the overall risk indicators of diverse buildings based on multiple market scenarios;

[0032] The second simulation module is used to simulate the market clearing of the power grid based on multiple pre-defined candidate bidding strategies, and to obtain the expected returns corresponding to each candidate bidding strategy.

[0033] The traversal module is used to input the overall risk index, multiple candidate pricing strategies, and expected returns into the optimization model to optimize the strategy and generate the optimal electricity pricing strategy.

[0034] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0035] Based on the Monte Carlo simulation algorithm, market scenarios are simulated for each individual building in a multi-building complex, generating multiple market scenarios.

[0036] Based on multiple market scenarios, we obtained the overall risk indicators for diverse buildings;

[0037] The market clearing simulation of the power grid is conducted based on multiple pre-defined candidate bidding strategies to obtain the expected returns corresponding to each candidate bidding strategy;

[0038] The overall risk index, multiple candidate pricing strategies, and expected returns are input into the optimization model to optimize the strategy and generate the optimal electricity pricing strategy.

[0039] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0040] Based on the Monte Carlo simulation algorithm, market scenarios are simulated for each individual building in a multi-building complex, generating multiple market scenarios.

[0041] Based on multiple market scenarios, we obtained the overall risk indicators for diverse buildings;

[0042] The market clearing simulation of the power grid is conducted based on multiple pre-defined candidate bidding strategies to obtain the expected returns corresponding to each candidate bidding strategy;

[0043] The overall risk index, multiple candidate pricing strategies, and expected returns are input into the optimization model to optimize the strategy and generate the optimal electricity pricing strategy.

[0044] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0045] Based on the Monte Carlo simulation algorithm, market scenarios are simulated for each individual building in a multi-building complex, generating multiple market scenarios.

[0046] Based on multiple market scenarios, we obtained the overall risk indicators for diverse buildings;

[0047] The market clearing simulation of the power grid is conducted based on multiple pre-defined candidate bidding strategies to obtain the expected returns corresponding to each candidate bidding strategy;

[0048] The overall risk index, multiple candidate pricing strategies, and expected returns are input into the optimization model to optimize the strategy and generate the optimal electricity pricing strategy.

[0049] The aforementioned optimization method, device, equipment, storage medium, and program product for power grid pricing strategies utilize Monte Carlo simulation algorithms to simulate market scenarios for individual buildings within a multi-building complex, generating multiple market scenarios. Based on these scenarios, an overall risk index for the multi-building complex is obtained. Market clearing simulation of the power grid is performed using pre-defined candidate pricing strategies to obtain the expected returns for each strategy. The overall risk index, multiple candidate pricing strategies, and expected returns are input into an optimization model for strategy optimization, generating the optimal power pricing strategy. This method quantifies the risk and calculates the returns of aggregators in complex and uncertain environments, effectively solving the technical challenge of balancing returns and risks in traditional methods, and significantly improving aggregators' pricing decision-making capabilities and risk resistance in the power market. Attached Figure Description

[0050] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0051] Figure 1 This is a diagram illustrating the application environment of an optimization method for a power grid pricing strategy in one embodiment.

[0052] Figure 2 This is one of the flowcharts illustrating an optimization method for a power grid pricing strategy in one embodiment;

[0053] Figure 3 This is a second flowchart illustrating the optimization method for power grid pricing strategy in one embodiment;

[0054] Figure 4 This is the third flowchart illustrating the optimization method for power grid pricing strategy in one embodiment;

[0055] Figure 5 This is the fourth flowchart illustrating the optimization method for power grid pricing strategy in one embodiment;

[0056] Figure 6 This is the fifth flowchart illustrating the optimization method for power grid pricing strategy in one embodiment;

[0057] Figure 7 This is a flowchart illustrating the optimization method for power grid pricing strategy in one embodiment;

[0058] Figure 8 This is a structural block diagram of an optimization device for a power grid pricing strategy in one embodiment. Detailed Implementation

[0059] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0060] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0061] With the advancement of "dual-carbon" goals and the continuous increase in the penetration rate of new energy sources, the operation mode of the power system is undergoing profound changes. The large-scale integration of intermittent renewable energy sources has exacerbated fluctuations in power supply and demand, making traditional generation-side regulation insufficient to meet the future flexibility requirements of the power system. Demand response, as a crucial means of enhancing the regulation capacity of the consumption side, can guide users to proactively adjust their electricity consumption behavior, playing a key role in peak shaving and valley filling, improving the efficiency of power resource utilization, and ensuring grid security. Currently, the user response behavior of diverse building clusters is influenced by multiple factors, including environmental factors, user habits, and market electricity prices, exhibiting significant randomness and uncertainty. Simultaneously, the demand response market mechanism is gradually improving, with building load aggregators becoming important players connecting users and the market, undertaking responsibilities such as load forecasting, market pricing, and revenue and risk management.

[0062] However, existing methods mostly employ static forecasting, which is insufficient to address the dynamic characteristics of load in complex market environments, making it difficult for aggregators to formulate accurate electricity pricing strategies.

[0063] In view of the above-mentioned technical problems, this application provides an optimization method for power grid pricing strategy. The following embodiments will specifically illustrate the optimization method for power grid pricing strategy.

[0064] The optimization method for power grid pricing strategy provided in this application embodiment can be applied to, for example, Figure 1The computer device shown includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements an optimization method for a power grid pricing strategy. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0065] Those skilled in the art will understand that Figure 1 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0066] In one exemplary embodiment, such as Figure 2 As shown, an optimization method for power grid pricing strategy is provided, which can be applied to... Figure 1 The following explanation uses computer equipment as an example, including:

[0067] S201 uses the Monte Carlo simulation algorithm to simulate market scenarios for each individual building in a multi-building complex, generating multiple market scenarios.

[0068] In this embodiment, for each individual building in a multi-building complex managed by an aggregator, the computer device employs a Monte Carlo simulation algorithm to randomly sample uncertainties affecting the aggregator's revenue, generating multiple market scenarios. These uncertainties include at least environmental changes, market fluctuations, and user response behavior. By randomly sampling the probability distributions of multiple uncertainties, the computer device simulates and generates multiple market scenarios with various possible states. Each market scenario includes environmental parameters, market price information, and user response status for each individual building, representing different possible future market environments and operating states.

[0069] S202, based on multiple market scenarios, yields the overall risk index for diverse buildings.

[0070] In this embodiment, after obtaining multiple market scenarios, the computer device first calculates the losses caused by uncertainties such as environmental changes, market fluctuations, and user responses for each market scenario, obtaining a loss vector for each scenario. Then, based on the distribution of loss sources across all scenarios, the computer device calculates the value at risk (VaR) of each loss source at a preset confidence level. Next, the computer device performs a weighted summation of the VaRs of each loss source to obtain the comprehensive risk of each individual building. Finally, the computer device aggregates the comprehensive risks of all individual buildings to obtain the overall risk index of the multi-building complex. This is used to characterize the overall risk level of the aggregator under the current aggregation scheme.

[0071] S203, based on multiple pre-defined candidate bidding strategies, simulates the market clearing of the power grid to obtain the expected returns corresponding to each candidate bidding strategy.

[0072] In this embodiment, the computer device calculates each candidate bidding strategy by simulating the clearing process of an aggregator participating in market bidding under a specific bidding strategy. The corresponding expected returns are determined as follows: The computer equipment first simulates the supply quotations submitted by all market participants (including this aggregator and other aggregators) and sorts them in ascending order of price. The clearing process follows the principle of low price priority, that is, supply is accepted sequentially according to the order of quotations until the cumulative supply meets the total system demand, and the last winning supply quotation is determined as the marginal clearing price. Based on this, the computer equipment inputs multiple pre-defined candidate quotation strategies into the market clearing simulation one by one to determine the expected returns of each candidate quotation strategy. Optionally, the computer equipment can also generate a stepped supply curve from the simulated supply quotations submitted by all market participants (including this aggregator and other aggregators) for reference; and generate a demand curve based on the preset total demand.

[0073] S204 inputs the overall risk index, multiple candidate pricing strategies, and expected returns into the optimization model to optimize the strategy and generate the optimal electricity pricing strategy.

[0074] In this embodiment, the computer device inputs the calculated expected returns of each candidate bidding strategy, the overall risk index of the aggregation scheme, and multiple candidate bidding strategies into the optimization model for strategy optimization to generate the optimal electricity bidding strategy. The optimization model aims to maximize expected returns while ensuring that the overall risk does not exceed a risk threshold. Its mathematical expression is shown in equation (1):

[0075] (1);

[0076] in, Indicates expected return; This indicates the overall risk associated with the pricing strategy; Indicates the risk threshold;

[0077] The computer equipment iterates through multiple candidate bidding strategies, calculating the expected return and overall risk index for each strategy. Then, it filters out all strategies that meet the criteria. The candidate strategies are those whose overall risk index cannot exceed a preset risk threshold. Based on this, the computer equipment selects the bidding strategy with the highest expected return from the selected bidding strategies as the optimal electricity bidding strategy output.

[0078] In the aforementioned optimization method for power grid pricing strategies, market clearing simulation of the power grid is performed based on multiple pre-defined candidate pricing strategies to obtain the expected returns corresponding to each candidate pricing strategy. Using the Monte Carlo simulation algorithm, market scenarios are simulated for each individual building in a multi-building complex, generating multiple market scenarios. Based on these multiple market scenarios, the overall risk index of the multi-building complex is obtained. The expected returns, overall risk index, and multiple candidate pricing strategies are input into the optimization model for strategy optimization, generating the optimal power pricing strategy. This method achieves the quantification of aggregator risk and the calculation of returns under complex and uncertain environments, effectively solving the technical problem of traditional methods struggling to balance returns and risks, and significantly improving aggregators' pricing decision-making ability and risk resistance in the power market.

[0079] In an exemplary embodiment, the phrase "obtaining the overall risk index of diverse buildings based on multiple market scenarios" in S202 above, such as... Figure 3 As shown, it includes:

[0080] S301 quantifies the risks of each individual building based on multiple market scenarios, resulting in a comprehensive risk index for each individual building.

[0081] In this embodiment of the application, for each individual building, the computer device first analyzes the potential loss vector (such as the environmental change loss vector) caused by uncertainties such as environmental changes, market fluctuations, and user responses under different market scenarios, based on multiple market scenarios. Market volatility loss vector and user default loss vector Subsequently, based on the losses of each individual building under different market scenarios, the computer comprehensively assesses the overall risk level of each building. This assessment process fully considers the differences between various sources of loss and their impact on building revenue. Finally, the computer integrates multiple loss data points using a preset risk quantification method to obtain a comprehensive risk index for each individual building. This comprehensive risk index is used to characterize the degree of risk that a single building may face when participating in demand response in the current market environment.

[0082] S302 calculates the overall risk index of the multi-building complex based on the comprehensive risk index of each individual building.

[0083] In this embodiment of the application, the computer equipment obtains the comprehensive risk of each individual building. Subsequently, the comprehensive risks of each individual building were assessed. After calculation, the overall risk index of diversified buildings in this market scenario can be obtained. Among them, the overall risk indicators It can be defined by relation (2), which is shown below:

[0084] (2);

[0085] Where N represents the number of individual buildings.

[0086] In an exemplary embodiment, the phrase "quantifying the risk of each individual building based on multiple market scenarios to obtain a comprehensive risk index for each individual building" in S301 above, such as... Figure 4 As shown, it includes:

[0087] S401 calculates the loss vector corresponding to each market scenario based on multiple market scenarios.

[0088] In this embodiment of the application, the computer device, based on multiple market scenarios generated by the Monte Carlo simulation algorithm, analyzes each individual building... Risk quantification is performed by calculating the loss vector for each market scenario, which includes the loss vector due to environmental changes. Market volatility loss vector and user default loss vector .

[0089] Environmental change loss vector Changes in environmental factors Degree of baseline load shift caused The specific calculation expression is shown in relation (3):

[0090] (3);

[0091] in, Indicates the first Relative humidity in various scenarios; This represents the baseline load offset function.

[0092] Market volatility loss vector The actual market clearing price The uncertainty of returns caused by volatility is calculated, that is, the market volatility loss vector is calculated based on the fluctuation between the actual market clearing price and the expected price. The specific calculation expression is shown in relation (4):

[0093] (4);

[0094] in, Indicates the expected clearing price; Indicates the actual number The actual amount of electricity consumed by the user in each scenario.

[0095] User default loss vector Can be determined by the actual number of user responses With commitment response volume The degree of inconsistency is calculated, and its specific calculation expression is shown in relation (5):

[0096] (5);

[0097] in, Represents the penalty function; This indicates the user's response behavior.

[0098] S402, Calculate the value at risk corresponding to each loss vector based on a preset confidence level.

[0099] In this embodiment of the application, the computer device obtains multiple loss vectors corresponding to each market scenario, namely, environmental change loss vectors. Market volatility loss vector and user default loss vector Subsequently, the computer equipment calculates the value at risk for each loss vector. The value at risk for each loss vector can be expressed by the relation (6), which is shown below:

[0100] (6);

[0101] in, Represents the risk value of a loss vector; Represents the loss vector; This represents the percentile function.

[0102] Therefore, the computer device can obtain the first Value at Risk of Environmental Change Loss Vector for a Building , No. Value at Risk Vector of Market Volatility Losses for Buildings and the Value at Risk of User Default Loss Vector for a Building .

[0103] S403, based on each risk value, yields the comprehensive risk index for each individual building.

[0104] In this embodiment of the application, the computer obtains the first Value at Risk of Environmental Change Loss Vector for a Building , No. Value at Risk Vector of Market Volatility Losses for Buildings and the Value at Risk of User Default Loss Vector for a Building Afterwards, the value of each risk can be assessed. The values ​​are weighted and summed to obtain the comprehensive risk index for each individual building. Comprehensive risk indicators It can be represented by relation (7), which is shown below:

[0105] (7);

[0106] in, and This represents the risk weighting coefficient, and .

[0107] In an exemplary embodiment, the phrase "based on the Monte Carlo simulation algorithm, market scenario simulation is performed on each individual building in the multi-building complex to generate multiple market scenarios" in S201 above, such as... Figure 5 As shown, it includes:

[0108] S501, based on the Ornstein-Uhlenbeck model, models the environmental change factors of a multi-building complex and obtains the probability distribution of the environmental change factors.

[0109] In this embodiment, environmental change factors are key random variables affecting building load (especially air conditioning load). The computer equipment uses the Ornstein-Uhlenbeck model to model the environmental change factors of the multi-building complex, simulating temperature changes over time. Its mathematical expression can be represented by relation (8), which is shown below:

[0110] (8);

[0111] in, yes Temperature at any moment It is the long-term average temperature. It is the rate of regression to the mean. It's volatility. It is a Wiener process. Computer devices can generate [data] by discretizing and sampling this process. We can identify possible future temperature change paths and thus obtain the probability distribution of environmental change factors.

[0112] S502 models the market fluctuations of the power grid based on geometric Brownian motion combined with a jump-diffusion model, and obtains the probability distribution of market fluctuations.

[0113] In this embodiment of the application, real-time electricity price Fluctuations in real-time electricity prices are a major source of market risk. Typically, electricity prices exhibit characteristics such as spikes, clustered fluctuations, and mean reversion. Computer equipment uses geometric Brownian motion combined with a jump-diffusion model to model market fluctuations in the power grid and describe real-time electricity prices. The dynamics of can be expressed mathematically by relation (9), which is shown below:

[0114] (9);

[0115] in, It's the drift rate. It's volatility. It is the Wiener process. It is a Poisson process, indicating whether a jump occurs. The magnitude of the price jump at the time of the jump typically follows a log-normal distribution. .

[0116] S503 models the uncertainty factors of user response to multi-building complexes based on the beta distribution model, and obtains the probability distribution of user response uncertainty factors.

[0117] In this embodiment of the application, the user-side response uncertainty The deviation between the actual and promised response amounts is modeled as a random variable. The computer equipment uses a beta distribution model to model the uncertainty factors of user responses in a multivariate building complex, representing the fulfillment rate of the response and ensuring its value is within a reasonable range, thus mitigating response uncertainty. The mathematical expression for can be represented by relation (10), which is shown below:

[0118] (10);

[0119] in, This represents the first shape parameter in the beta distribution model; This represents the second shape parameter in the beta distribution model.

[0120] S504, based on the Monte Carlo simulation algorithm, extracts samples from the probability distributions of environmental change factors, market fluctuations, and user response uncertainty factors to simulate market scenarios and generate multiple market scenarios.

[0121] In this embodiment, the computer device independently extracts samples from the probability distributions of environmental change factors, market fluctuations, and user response uncertainty factors. Each set of sample values ​​corresponds to a possible market state. Through repeated sampling, multiple simulated market scenarios covering various possible states are generated. Each generated market scenario includes at least the environmental parameters, market price information, and user response behavior characteristics under that scenario, which are used for subsequent revenue calculation and risk assessment by the computer device.

[0122] In an exemplary embodiment, the optimization method of the above-mentioned power grid pricing strategy, such as Figure 6 As shown, it includes:

[0123] S601, based on market clearing simulation, obtains the clearing price and winning bid volume corresponding to multiple pre-defined candidate bidding strategies.

[0124] The clearing price refers to the marginal clearing price of each candidate bidding strategy in various market scenarios; the winning bid volume refers to the market response volume of each candidate bidding strategy in various market scenarios.

[0125] In this embodiment, the computer device performs market clearing simulations for multiple pre-defined candidate bidding strategies to obtain the clearing price and winning volume for each candidate bidding strategy. First, the computer device acquires supply bid information submitted by all market participants (including the aggregator and other aggregators), where each bid includes at least a bid price and a committed response quantity. Then, the computer device sorts all supply bids in ascending order and accepts bids sequentially according to total demand until the cumulative supply meets total demand. The price corresponding to the last accepted bid is the marginal clearing price in this simulation scenario, and all accepted suppliers settle at this price. Finally, for each candidate bidding strategy, the computer device uses that strategy as its own bid input and substitutes it into the market clearing simulation process to determine whether the aggregator is accepted under that strategy, the accepted volume (i.e., the winning volume), and the corresponding settlement price (i.e., the marginal clearing price).

[0126] S602, based on the clearing price, the winning bid volume, and the overall risk indicators, obtains the expected returns corresponding to each candidate bidding strategy.

[0127] In this embodiment, for each candidate bidding strategy, the computer device obtains the clearing price and winning bid volume for that strategy in various market scenarios. Then, using the clearing price and winning bid volume for each market scenario, it calculates the market settlement revenue for that market scenario and subtracts the response cost and loss vector due to environmental changes for that market scenario. Market volatility loss vector and user default loss vector The resulting loss is used to obtain the net profit in this market scenario. Subsequently, the computer device can obtain the expected profit corresponding to the candidate pricing strategy by averaging the net profits in all market scenarios. Its mathematical expression can be represented by relation (11), which is shown below:

[0128] (11);

[0129] in, This indicates the total number of market scenarios; Indicates the first Market clearing prices in various scenarios; Indicates the first The winning bid volume of aggregators in various scenarios; Indicates the first Response cost in various scenarios; Indicates the first The total loss in each scenario can be obtained by adding the environmental change loss vector, the market fluctuation loss vector, and the user default loss vector.

[0130] In summary, based on all the above embodiments, an optimization method for power grid pricing strategies is also provided, such as... Figure 7 As shown, the method includes:

[0131] S701, based on the Ornstein-Uhlenbeck model, models the environmental change factors of a multi-building complex and obtains the probability distribution of the environmental change factors;

[0132] S702, based on geometric Brownian motion combined with a jump-diffusion model, models the market fluctuations of the power grid and obtains the probability distribution of market fluctuations;

[0133] S703, Based on the beta distribution model, the uncertainty factors of user response to multi-dimensional building complexes are modeled to obtain the probability distribution of user response uncertainty factors;

[0134] S704, based on the Monte Carlo simulation algorithm, extracts samples from the probability distributions of environmental change factors, market fluctuations, and user response uncertainty factors to simulate market scenarios and generate multiple market scenarios.

[0135] S705, calculate the user default loss vector based on the degree of inconsistency between the user's actual response volume and the promised response volume;

[0136] S706, calculates the market volatility loss vector based on the fluctuations between the actual market clearing price and the expected price;

[0137] S707, calculates the environmental change loss vector based on the degree of baseline load shift caused by changes in environmental factors;

[0138] S708, Calculate the value at risk corresponding to each loss vector based on a preset confidence level;

[0139] S709, based on each risk value, obtains the comprehensive risk index for each individual building;

[0140] S710 calculates the overall risk index of the multi-building complex based on the comprehensive risk index of each individual building.

[0141] S711 simulates market clearing of the power grid based on multiple pre-defined candidate bidding strategies;

[0142] S712, based on market clearing simulation, obtains the clearing price and winning bid volume corresponding to multiple pre-defined candidate bidding strategies;

[0143] S713, based on the clearing price, the winning bid volume, and the overall risk indicators, yields the expected return;

[0144] S714 inputs expected returns, overall risk indicators, and multiple candidate pricing strategies into the optimization model to optimize the strategy and generate the optimal electricity pricing strategy.

[0145] The methods described in each of the above steps have been described in the foregoing embodiments. For details, please refer to the foregoing descriptions. They will not be repeated here.

[0146] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0147] Based on the same inventive concept, this application also provides a power grid pricing strategy optimization device for implementing the aforementioned power grid pricing strategy optimization method. The solution provided by this device is similar to the implementation described in the above method. Therefore, the specific limitations of one or more power grid pricing strategy optimization device embodiments provided below can be found in the limitations of the power grid pricing strategy optimization method described above, and will not be repeated here.

[0148] In one exemplary embodiment, such as Figure 8 As shown, an optimization device for power grid pricing strategy is provided, comprising:

[0149] The first simulation module 11 is used to simulate market scenarios for each individual building in the multi-building complex according to the Monte Carlo simulation algorithm, and generate multiple market scenarios.

[0150] Risk module 12 is used to obtain the overall risk index of diverse buildings based on multiple market scenarios;

[0151] The second simulation module 13 is used to simulate the market clearing of the power grid based on multiple pre-defined candidate bidding strategies, and to obtain the expected returns corresponding to each candidate bidding strategy.

[0152] The traversal module 14 is used to input expected returns, overall risk indicators and multiple candidate pricing strategies into the optimization model for strategy optimization, and generate the optimal electricity pricing strategy.

[0153] In one embodiment, the risk module 13 includes:

[0154] The quantification unit is used to quantify the risks of each individual building based on multiple market scenarios, and obtain the comprehensive risk index of each individual building.

[0155] The calculation unit is used to calculate the overall risk index of the multi-building complex based on the comprehensive risk index of each individual building.

[0156] In one embodiment, the quantization unit includes:

[0157] The first calculation subunit is used to calculate the loss vector corresponding to each market scenario based on multiple market scenarios.

[0158] The second calculation subunit is used to calculate the value at risk corresponding to each loss vector based on a preset confidence level.

[0159] The third calculation subunit is used to obtain the comprehensive risk index of each individual building based on each risk value.

[0160] In one embodiment, the first computing subunit described above is specifically used for:

[0161] The user default loss vector is calculated based on the degree of inconsistency between the user's actual response volume and the promised response volume.

[0162] The market volatility loss vector is calculated based on the fluctuations between the actual market clearing price and the expected price.

[0163] The environmental change loss vector is calculated based on the degree of baseline load shift caused by changes in environmental factors.

[0164] In one embodiment, the second simulation module 12 includes:

[0165] The first modeling subunit is used to model the environmental change factors of a multi-building complex based on the Ornstein-Uhlenbeck model, and obtain the probability distribution of the environmental change factors.

[0166] The second modeling subunit is used to model the market fluctuations of the power grid based on geometric Brownian motion combined with a jump-diffusion model, and obtain the probability distribution of market fluctuations.

[0167] The third modeling subunit is used to model the uncertainty factors of user response to multi-dimensional building complexes based on the beta distribution model, and obtain the probability distribution of user response uncertainty factors.

[0168] The fourth modeling subunit is used to extract samples from the probability distributions of environmental change factors, market fluctuations, and user response uncertainty factors based on the Monte Carlo simulation algorithm, to simulate market scenarios and generate multiple market scenarios.

[0169] In one embodiment, the first simulation module 11 includes:

[0170] The winning bid unit is used to obtain the clearing price and winning bid volume corresponding to multiple pre-defined candidate bidding strategies based on market clearing simulation;

[0171] The revenue unit is used to obtain the expected revenue based on the clearing price, the winning bid volume, and the overall risk indicators.

[0172] The modules in the aforementioned power grid pricing strategy optimization device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the computer device's memory as software, so that the processor can call and execute the corresponding operations of each module.

[0173] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0174] Based on the Monte Carlo simulation algorithm, market scenarios are simulated for each individual building in a multi-building complex, generating multiple market scenarios.

[0175] Based on multiple market scenarios, we obtained the overall risk indicators for diverse buildings;

[0176] The market clearing simulation of the power grid is conducted based on multiple pre-defined candidate bidding strategies to obtain the expected returns corresponding to each candidate bidding strategy;

[0177] The overall risk index, multiple candidate pricing strategies, and expected returns are input into the optimization model to optimize the strategy and generate the optimal electricity pricing strategy.

[0178] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0179] Based on multiple market scenarios, the risks of each individual building are quantified to obtain a comprehensive risk index for each individual building.

[0180] Based on the comprehensive risk index of each individual building, the overall risk index of the multi-building complex is calculated.

[0181] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0182] Calculate the loss vector for each market scenario based on multiple market scenarios;

[0183] Based on each loss vector and a preset confidence level, calculate the value at risk corresponding to each loss vector.

[0184] Based on each risk value, a comprehensive risk index for each individual building is obtained.

[0185] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0186] The user default loss vector is calculated based on the degree of inconsistency between the user's actual response volume and the promised response volume.

[0187] The market volatility loss vector is calculated based on the fluctuations between the actual market clearing price and the expected price.

[0188] The environmental change loss vector is calculated based on the degree of baseline load shift caused by changes in environmental factors.

[0189] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0190] The environmental change factors of a multi-building complex are modeled based on the Ornstein-Uhlenbeck model, and the probability distribution of the environmental change factors is obtained.

[0191] The market fluctuations of the power grid are modeled based on geometric Brownian motion combined with a jump-diffusion model, and the probability distribution of market fluctuations is obtained.

[0192] The uncertainty factors of user response to multi-building complexes are modeled based on the beta distribution model, and the probability distribution of user response uncertainty factors is obtained.

[0193] Based on the Monte Carlo simulation algorithm, samples are drawn from the probability distributions of environmental change factors, market fluctuations, and user response uncertainty factors to simulate market scenarios and generate multiple market scenarios.

[0194] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0195] Based on market clearing simulation, the clearing price and winning bid volume corresponding to multiple pre-defined candidate bidding strategies are obtained;

[0196] The expected return is obtained based on the clearing price, the winning bid volume, and the overall risk indicators.

[0197] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0198] Based on the Monte Carlo simulation algorithm, market scenarios are simulated for each individual building in a multi-building complex, generating multiple market scenarios.

[0199] Based on multiple market scenarios, we obtained the overall risk indicators for diverse buildings;

[0200] The market clearing simulation of the power grid is conducted based on multiple pre-defined candidate bidding strategies to obtain the expected returns corresponding to each candidate bidding strategy;

[0201] The overall risk index, multiple candidate pricing strategies, and expected returns are input into the optimization model to optimize the strategy and generate the optimal electricity pricing strategy.

[0202] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0203] Based on multiple market scenarios, the risks of each individual building are quantified to obtain a comprehensive risk index for each individual building.

[0204] Based on the comprehensive risk index of each individual building, the overall risk index of the multi-building complex is calculated.

[0205] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0206] Calculate the loss vector for each market scenario based on multiple market scenarios;

[0207] Based on each loss vector and a preset confidence level, calculate the value at risk corresponding to each loss vector.

[0208] Based on each risk value, a comprehensive risk index for each individual building is obtained.

[0209] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0210] The user default loss vector is calculated based on the degree of inconsistency between the user's actual response volume and the promised response volume.

[0211] The market volatility loss vector is calculated based on the fluctuations between the actual market clearing price and the expected price.

[0212] The environmental change loss vector is calculated based on the degree of baseline load shift caused by changes in environmental factors.

[0213] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0214] The environmental change factors of a multi-building complex are modeled based on the Ornstein-Uhlenbeck model, and the probability distribution of the environmental change factors is obtained.

[0215] The market fluctuations of the power grid are modeled based on geometric Brownian motion combined with a jump-diffusion model, and the probability distribution of market fluctuations is obtained.

[0216] The uncertainty factors of user response to multi-building complexes are modeled based on the beta distribution model, and the probability distribution of user response uncertainty factors is obtained.

[0217] Based on the Monte Carlo simulation algorithm, samples are drawn from the probability distributions of environmental change factors, market fluctuations, and user response uncertainty factors to simulate market scenarios and generate multiple market scenarios.

[0218] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0219] Based on market clearing simulation, the clearing price and winning bid volume corresponding to multiple pre-defined candidate bidding strategies are obtained;

[0220] The expected return is obtained based on the clearing price, the winning bid volume, and the overall risk indicators.

[0221] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0222] Based on the Monte Carlo simulation algorithm, market scenarios are simulated for each individual building in a multi-building complex, generating multiple market scenarios.

[0223] Based on multiple market scenarios, we obtained the overall risk indicators for diverse buildings;

[0224] The market clearing simulation of the power grid is conducted based on multiple pre-defined candidate bidding strategies to obtain the expected returns corresponding to each candidate bidding strategy;

[0225] The overall risk index, multiple candidate pricing strategies, and expected returns are input into the optimization model to optimize the strategy and generate the optimal electricity pricing strategy.

[0226] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0227] Based on multiple market scenarios, the risks of each individual building are quantified to obtain a comprehensive risk index for each individual building.

[0228] Based on the comprehensive risk index of each individual building, the overall risk index of the multi-building complex is calculated.

[0229] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0230] Calculate the loss vector for each market scenario based on multiple market scenarios;

[0231] Based on each loss vector and a preset confidence level, calculate the value at risk corresponding to each loss vector.

[0232] Based on each risk value, a comprehensive risk index for each individual building is obtained.

[0233] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0234] The user default loss vector is calculated based on the degree of inconsistency between the user's actual response volume and the promised response volume.

[0235] The market volatility loss vector is calculated based on the fluctuations between the actual market clearing price and the expected price.

[0236] The environmental change loss vector is calculated based on the degree of baseline load shift caused by changes in environmental factors.

[0237] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0238] The environmental change factors of a multi-building complex are modeled based on the Ornstein-Uhlenbeck model, and the probability distribution of the environmental change factors is obtained.

[0239] The market fluctuations of the power grid are modeled based on geometric Brownian motion combined with a jump-diffusion model, and the probability distribution of market fluctuations is obtained.

[0240] The uncertainty factors of user response to multi-building complexes are modeled based on the beta distribution model, and the probability distribution of user response uncertainty factors is obtained.

[0241] Based on the Monte Carlo simulation algorithm, samples are drawn from the probability distributions of environmental change factors, market fluctuations, and user response uncertainty factors to simulate market scenarios and generate multiple market scenarios.

[0242] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0243] Based on market clearing simulation, the clearing price and winning bid volume corresponding to multiple pre-defined candidate bidding strategies are obtained;

[0244] The expected return is obtained based on the clearing price, the winning bid volume, and the overall risk indicators.

[0245] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0246] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0247] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for generating a power grid pricing strategy, characterized in that, The method includes: Based on the Monte Carlo simulation algorithm, market scenarios are simulated for each individual building in a multi-building complex, generating multiple market scenarios. Based on the aforementioned multiple market scenarios, the overall risk index of the diverse buildings is obtained; The market clearing simulation of the power grid is conducted based on multiple pre-defined candidate bidding strategies to obtain the expected returns corresponding to each candidate bidding strategy; The overall risk index, the multiple candidate pricing strategies, and the expected return are input into the optimization model to optimize the strategy and generate the optimal electricity pricing strategy.

2. The method according to claim 1, characterized in that, The overall risk index for the diversified buildings, obtained based on the multiple market scenarios, includes: Based on the multiple market scenarios, the risks of each individual building are quantified to obtain a comprehensive risk index for each individual building. Based on the comprehensive risk index of each individual building, the overall risk index of the multi-building complex is calculated.

3. The method according to claim 2, characterized in that, The process of quantifying the risk of each individual building based on the multiple market scenarios to obtain a comprehensive risk index for each individual building includes: Based on the multiple market scenarios, calculate the loss vector corresponding to each market scenario; Based on each loss vector, and according to a preset confidence level, calculate the value at risk corresponding to each loss vector; Based on the risk values ​​described, a comprehensive risk index is obtained for each individual building.

4. The method according to claim 3, wherein the loss vector includes at least one of a user default loss vector, a market volatility loss vector, and an environmental change loss vector, characterized in that, The step of calculating the loss vector corresponding to each market scenario based on the multiple market scenarios includes: The user default loss vector is calculated based on the degree of inconsistency between the user's actual response volume and the promised response volume. The market volatility loss vector is calculated based on the fluctuations between the actual market clearing price and the expected price. The environmental change loss vector is calculated based on the degree of baseline load shift caused by changes in environmental factors.

5. The method according to any one of claims 1-4, characterized in that, The method uses the Monte Carlo simulation algorithm to simulate market scenarios for each individual building in the multi-building complex, generating multiple market scenarios, including: The environmental change factors of the multi-dimensional building complex were modeled based on the Ornstein-Uhlenbeck model, and the probability distribution of the environmental change factors was obtained. The market fluctuations of the power grid are modeled based on geometric Brownian motion combined with a jump-diffusion model, and the probability distribution of the market fluctuations is obtained. The uncertainty factors of user response to the multi-dimensional building complex are modeled based on the beta distribution model to obtain the probability distribution of the uncertainty factors of user response. Based on the Monte Carlo simulation algorithm, samples are drawn from the probability distributions of the environmental change factors, the market fluctuations, and the user response uncertainty factors to simulate market scenarios and generate multiple market scenarios.

6. The method according to any one of claims 1-4, characterized in that, The method further includes: Based on the market clearing simulation, the clearing price and winning bid volume corresponding to the pre-defined multiple candidate bidding strategies are obtained; The expected return is obtained based on the clearing price, the winning bid volume, and the overall risk indicators.

7. An optimization device for electricity pricing strategies in a multi-building complex, characterized in that, The device includes: The first simulation module is used to simulate market scenarios for each individual building in the multi-building complex according to the Monte Carlo simulation algorithm, and generate multiple market scenarios. The risk module is used to obtain the overall risk index of the diverse buildings based on the multiple market scenarios. The second simulation module is used to simulate the market clearing of the power grid based on multiple pre-defined candidate bidding strategies, and to obtain the expected returns corresponding to each candidate bidding strategy. The traversal module is used to input the overall risk index, the multiple candidate pricing strategies, and the expected return into the optimization model for strategy optimization, and generate the optimal electricity pricing strategy.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images