Comprehensive energy network scheduling method, computer device and storage medium

Abstract

Embodiments of the present application provide a scheduling method of an integrated energy network, a computer device and a storage medium. The method comprises: scheduling energy equipment in the integrated energy network to obtain candidate scheduling data, taking the minimum cost of the integrated energy network as the target; determining an error fuzzy set according to the candidate scheduling data and corresponding prediction data of the integrated energy network; performing variational inference on the error fuzzy set to obtain target error data with distribution determined; adjusting the candidate scheduling data according to the target error data to obtain target scheduling data of the integrated energy network, and scheduling the integrated energy network according to the target scheduling data. The accuracy of scheduling the integrated energy network is improved.

Description

Technical Field

[0001] This application relates to the energy field, and more particularly to a scheduling method, computer equipment, and storage medium for an integrated energy network. Background Technology

[0002] The scheduling of energy networks can combine electricity demand and supply to allocate energy scientifically and rationally, which helps to maximize the utilization rate of electricity resources.

[0003] In related technologies, the scheduling of energy networks, which is carried out according to fixed plans and rules, is difficult to respond flexibly to emergencies and load fluctuations, resulting in low accuracy in scheduling energy networks. Summary of the Invention

[0004] This application provides a scheduling method, computer equipment, storage medium, and program product for integrated energy networks, which improves the accuracy of scheduling integrated energy networks.

[0005] In a first aspect, embodiments of this application provide a scheduling method for an integrated energy network, comprising:

[0006] With the goal of minimizing the cost of the integrated energy network, energy equipment in the integrated energy network is scheduled to obtain candidate scheduling data; based on the candidate scheduling data and the corresponding prediction data of the integrated energy network, an error fuzzy set is determined; variational inference is performed on the error fuzzy set to obtain target error data with a defined distribution; the candidate scheduling data is adjusted based on the target error data to obtain the target scheduling data of the integrated energy network, and the integrated energy network is scheduled based on the target scheduling data.

[0007] In one possible implementation, with the goal of minimizing the cost of the integrated energy network, the energy equipment in the integrated energy network is scheduled to obtain candidate scheduling data. This includes: performing day-ahead scheduling of the energy equipment in the integrated energy network based on the total cost objective function of the integrated energy network, with the goal of minimizing the total cost, to obtain day-ahead scheduling data for a first time period; and for each second time period included in the first time period, based on the day-ahead scheduling data in the first time period, performing intraday rescheduling of the energy equipment in the integrated energy network based on the operating cost objective function of the integrated energy network, with the goal of minimizing the operating cost, to obtain candidate scheduling data for the second time period.

[0008] In one possible implementation, the prediction data includes predicted wind turbine power generation, predicted photovoltaic power generation, and predicted power load. Based on candidate scheduling data and the prediction data corresponding to the integrated energy network, an error fuzzy set is determined, including: obtaining candidate wind turbine power generation, candidate photovoltaic power generation, and candidate power load from the candidate scheduling data; determining the wind turbine power generation error based on the candidate wind turbine power generation and predicted wind turbine power generation; determining the photovoltaic power generation error based on the candidate photovoltaic power generation and predicted photovoltaic power generation; determining the power load error based on the candidate power load and predicted power load; and determining the error fuzzy set based on the wind turbine power generation error, photovoltaic power generation error, and power load error.

[0009] In one possible implementation, variational inference is performed on the error fuzzy set to obtain target error data with a defined distribution, including: inputting the error fuzzy set into the variational inference model to obtain target error data with a defined distribution.

[0010] In one possible implementation, the method further includes:

[0011] Historical wind power data, historical sunshine data, and historical power load are acquired; the historical wind power data is processed using a prediction model to obtain the predicted wind turbine power generation; the historical sunshine data is processed using a prediction model to obtain the predicted photovoltaic power generation; and the historical power load is processed using a prediction model to obtain the predicted power load.

[0012] In one possible implementation, the candidate scheduling data is candidate scheduling data within a second time period; the target error data includes the target error interval within the second time period; adjusting the candidate scheduling data based on the target error data to obtain the target scheduling data of the integrated energy network includes: selecting the target error within the second time period from the target error interval; adjusting the candidate scheduling data within the second time period based on the target error within the second time period to obtain the target scheduling data of the integrated energy network in the second time period.

[0013] Secondly, embodiments of this application provide a scheduling device for an integrated energy network, comprising:

[0014] The first scheduling module is used to schedule energy equipment in the integrated energy network with the goal of minimizing the cost of the integrated energy network, and to obtain candidate scheduling data;

[0015] The first error determination module is used to determine the error fuzzy set based on the candidate scheduling data and the prediction data corresponding to the integrated energy network;

[0016] The second error determination module is used to perform variational inference on the error fuzzy set to obtain target error data with a defined distribution.

[0017] The second scheduling module is used to adjust the candidate scheduling data based on the target error data to obtain the target scheduling data of the integrated energy network, and to schedule the integrated energy network based on the target scheduling data.

[0018] Thirdly, embodiments of this application provide a computer device, including: a memory and a processor; the memory stores computer execution instructions; the processor executes the computer execution instructions stored in the memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0019] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0020] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0021] The integrated energy network scheduling method, computer equipment, storage medium, and program product provided in this application aim to minimize the cost of the integrated energy network. By determining candidate scheduling data, it can optimize economic costs while meeting energy demand. Since there are uncertain data flows in the integrated energy network, such as the power generation and load of wind turbines and photovoltaic panels, after determining the scheduling data, a fuzzy set of errors is determined between the predicted data and the scheduling data. The fuzzy set of errors characterizes the problem of complex probability distribution of errors in uncertain data flows. Variational reasoning is used to process the fuzzy set of errors to obtain a target error with a definite distribution. The candidate scheduling data is adjusted by the target error to obtain the target scheduling data, thereby reducing the impact of uncertain data flows in the integrated energy network on the operation of the integrated energy network, improving the reliability of the integrated energy network, and also improving the accuracy of scheduling the integrated energy network. Attached Figure Description

[0022] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0023] Figure 1 Flowchart of the integrated energy network scheduling method provided in this application Figure 1 ;

[0024] Figure 2 A schematic diagram of the integrated energy network provided in this application;

[0025] Figure 3A structural schematic diagram of a hydrogen energy station in the integrated energy network provided in this application;

[0026] Figure 4 Flowchart of the integrated energy network scheduling method provided in this application Figure 2 ;

[0027] Figure 5 Flowchart of the integrated energy network scheduling method provided in this application Figure 3 ;

[0028] Figure 6 A schematic diagram of the integrated energy device provided in this application;

[0029] Figure 7 A schematic diagram of the structure of the computer device provided in this application.

[0030] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0031] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0032] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0033] Figure 1 Flowchart of the integrated energy network scheduling method provided in this application Figure 1 ,like Figure 1 As shown, the method includes:

[0034] S101, with the goal of minimizing the cost of the integrated energy network, schedules the energy equipment in the integrated energy network to obtain candidate scheduling data.

[0035] The integrated energy network is a network that integrates renewable energy, electricity, hydrogen, heat and natural gas. Renewable energy can be wind and solar power.

[0036] In practical applications, such as Figure 2 As shown, the integrated energy network includes wind turbines, photovoltaic panels, combined heat and power (CHP) equipment, electric heating equipment, batteries, electrolyzers, hydrogen storage equipment, fuel cells, and natural gas supply equipment. Electricity is generated through wind turbines, photovoltaic panels, fuel cells, and CHP equipment. This electricity can be used to supply electricity demand and can also be transmitted to the main power grid. Electricity can also be supplied to electrolyzers and electric heating equipment, and can be stored in batteries.

[0037] Electric heating equipment converts electrical energy into heat energy; the electrolysis cell generates hydrogen gas, which can be stored in hydrogen storage equipment. The hydrogen gas in the storage equipment can then be transported to a hydrogen energy station via hydrogen pipelines. Figure 3 As shown, a hydrogen energy station can include multiple hydrogen refueling stations, and the hydrogen in the hydrogen storage device can be transported to multiple hydrogen refueling stations via pipelines; the hydrogen in the hydrogen storage device can also be supplied to fuel cells.

[0038] Natural gas supply equipment can supply combined heat and power (CHP) equipment and incinerators, which generate electricity and heat based on natural gas; the incinerator produces hydrogen, which can supply fuel cells; the fuel cells generate electricity and heat based on the hydrogen supplied by the incinerator and hydrogen storage equipment; the heat generated by the electric heating equipment, CHP equipment, and fuel cells is used to meet heat demand.

[0039] The energy equipment in the integrated energy network includes wind turbines, photovoltaic panels, combined heat and power equipment, electric heating equipment, fuel cells, electrolyzers, batteries, and natural gas supply equipment.

[0040] Candidate scheduling data includes: candidate wind turbine power generation, candidate photovoltaic power generation, candidate combined heat and power power generation, candidate fuel cell power generation, candidate electric heating equipment heat energy, candidate natural gas supply, candidate electrolyzer power energy, candidate battery charging amount, candidate battery discharging amount, and candidate power load.

[0041] Specifically, the computer equipment obtains the objective function for minimizing the cost of the integrated energy network, as well as the constraints of the objective function. Under the constraints, the objective function for minimizing the cost is optimized and solved to obtain candidate scheduling data for the integrated energy network.

[0042] It should be noted that constraints may include energy balance constraints, equipment capacity and operation constraints, and external energy supply constraints; constraints can be set according to the actual structure and operation of the integrated energy network.

[0043] In one alternative approach, day-ahead scheduling of energy equipment in the integrated energy network is performed with the goal of minimizing costs to obtain candidate scheduling data. The candidate scheduling data can represent candidate scheduling data for a future period of time, such as scheduling data for the next 24 hours.

[0044] In one alternative approach, day-ahead scheduling of energy equipment in the integrated energy network is performed with the goal of minimizing total cost to obtain day-ahead scheduling data. Based on the day-ahead scheduling data, intraday rescheduling is performed with the goal of minimizing operating costs to obtain candidate scheduling data. The candidate scheduling data can represent the scheduling data for a certain period of time in the future, such as the scheduling data for a certain hour in the next 24 hours.

[0045] S102, Based on the candidate scheduling data and the prediction data corresponding to the integrated energy network, determine the error fuzzy set.

[0046] The forecast data includes forecasted wind turbine power generation, photovoltaic power generation, and power load. The forecasted wind turbine power generation and photovoltaic power generation can be obtained from historical wind power data and solar irradiance data; the forecasted power load can be determined based on the forecasted wind turbine power generation and photovoltaic power generation.

[0047] The error fuzzy set includes fuzzy errors at multiple time points. The fuzzy errors represent the errors between the predicted wind power generation, photovoltaic power generation, and power load and the wind power generation, photovoltaic power generation, and power load included in the candidate scheduling data.

[0048] It should be noted that, due to the uncertainty of renewable energy and power load, which constitutes an uncertain data stream, the dispatch data of renewable energy and power load may interfere with the integrated energy network. Specifically, the wind power generation, photovoltaic power generation, and power load in the candidate dispatch data may cause the integrated energy network's dispatch to be unable to meet the power demand, requiring the purchase of power from other energy networks, thereby increasing costs. Alternatively, the power generated by the integrated energy network's dispatch may exceed the power demand, resulting in energy waste. Thus, the uncertain data stream leads to a lower reliability of the integrated energy network.

[0049] Specifically, the computer equipment obtains candidate power loads, candidate power generation of wind turbines, and candidate power generation of photovoltaic panels from the candidate scheduling data; obtains the predicted power generation of wind turbines, photovoltaic power generation, and power load; and calculates the error fuzzy set based on the candidate power loads, candidate power generation of wind turbines and photovoltaic panels, the predicted power generation of wind turbines, photovoltaic power generation, and power load.

[0050] In one alternative approach, the error between the candidate power load and the predicted power load can be calculated, the error between the candidate power generation of the wind turbine and the predicted power generation of the wind turbine can be calculated, the error between the candidate power generation of the photovoltaic panel and the predicted photovoltaic power generation can be calculated, the total error can be determined based on the above errors, and then the error fuzzy set can be determined based on the total error.

[0051] It should be noted that the error fuzzy set includes the total error at multiple time points; the candidate scheduling data includes scheduling data at multiple time points, and the prediction data also includes prediction data at multiple time points. Based on the scheduling data and prediction data at multiple time points, the total error at multiple time points is determined, and the error fuzzy set is determined based on the total error at multiple time points.

[0052] S103, perform variational inference on the error fuzzy set to obtain target error data with a defined distribution.

[0053] Variational reasoning is a deterministic approximate reasoning method that can be used to approximate complex probability distributions.

[0054] The error fuzzy set is determined based on the scheduling data of renewable energy and power load. Since renewable energy and power load are uncertain data streams, the error fuzzy set is error data with uncertain distribution; the target error data is error data with certain distribution.

[0055] Specifically, computer equipment processes the error fuzzy set using a variational inference algorithm to obtain target error data with a defined distribution. In practical applications, an online variational inference algorithm based on a Dirichlet mixture model can be used to process the error fuzzy set to obtain target error data with a defined distribution.

[0056] S104, adjust the candidate scheduling data according to the target error data to obtain the target scheduling data of the integrated energy network, and schedule the integrated energy network according to the target scheduling data.

[0057] Specifically, the computer equipment obtains candidate power loads, candidate power generation of wind turbines, and candidate power generation of photovoltaic panels from the candidate scheduling data, and adjusts the candidate power loads, candidate power generation of wind turbines, and candidate power generation of photovoltaic panels using target error data to obtain target power loads, target power generation of wind turbines, and target power generation of photovoltaic panels.

[0058] In other words, the target error data is used to adjust the candidate power generation and candidate power load of wind turbines and photovoltaic panels, but not to adjust the candidate scheduling data of other energy equipment. The candidate scheduling data of other energy equipment can be directly used as the target scheduling data.

[0059] For example, the candidate scheduling data includes: candidate wind turbine power generation, candidate photovoltaic power generation, candidate combined heat and power (CHP) power generation, candidate fuel cell power generation, candidate electric heating equipment heat energy, candidate natural gas supply, candidate electrolyzer power energy, candidate battery charging capacity, candidate battery discharging capacity, and candidate power load; the candidate wind turbine power generation, candidate photovoltaic power generation, and candidate power load are adjusted using target error data to obtain target wind turbine power generation, target photovoltaic power generation, and target power load; the candidate CHP power generation, candidate fuel cell power generation, candidate electric heating equipment heat energy, candidate natural gas supply, candidate electrolyzer power energy, candidate battery charging capacity, and candidate battery discharging capacity are respectively used as target CHP power generation, target fuel cell power generation, target electric heating equipment heat energy, target natural gas supply, target electrolyzer power energy, target battery charging capacity, and target battery discharging capacity; after obtaining the target scheduling data for the integrated energy network, the integrated energy network is scheduled according to the target scheduling data.

[0060] The aforementioned integrated energy network scheduling method aims to minimize the cost of the integrated energy network. By determining candidate scheduling data, it can optimize economic costs while meeting energy demand. Since the integrated energy network contains uncertain data flows, such as the power generation and load of wind turbines and photovoltaic panels, after determining the scheduling data, a fuzzy error set is determined between the predicted data and the scheduling data. This fuzzy error set characterizes the complex probability distribution of errors in uncertain data flows. Variational inference is used to process the fuzzy error set to obtain a target error with a defined distribution. The candidate scheduling data is then adjusted using this target error to obtain the target scheduling data. This reduces the impact of uncertain data flows on the operation of the integrated energy network, improving its reliability and the accuracy of its scheduling.

[0061] In some embodiments, with the goal of minimizing the cost of the integrated energy network, energy devices in the integrated energy network are scheduled to obtain candidate scheduling data, including:

[0062] Based on the total cost objective function of the integrated energy network, with the goal of minimizing the total cost, day-ahead scheduling is performed on the energy equipment in the integrated energy network to obtain day-ahead scheduling data for the first time period. For each second time period included in the first time period, based on the day-ahead scheduling data in the first time period, and according to the operating cost objective function of the integrated energy network, with the goal of minimizing the operating cost, intraday rescheduling is performed on the energy equipment in the integrated energy network to obtain candidate scheduling data for the second time period.

[0063] The total cost objective function is a function constructed with the goal of minimizing total cost; the operating cost objective function is a function constructed with the goal of minimizing operating cost.

[0064] Day-ahead scheduling refers to determining the day-ahead scheduling data for the next 24 hours. It can be understood as determining the workload of each energy device in the integrated energy network in the next 24 hours and performing day-ahead scheduling with the goal of minimizing the total cost. This can ensure that the operation of each energy device in the integrated energy network can minimize the total cost of the integrated energy network.

[0065] Intraday rescheduling refers to dividing the next 24 hours into many time periods (such as 1 hour or half hour) based on the current situation, since the actual situation may change. Before the start of each time period, the intraday rescheduling is adjusted according to the current situation. The goal of intraday rescheduling is to minimize the operating cost, so that the operating cost of the integrated energy network is minimized during that time period.

[0066] In other words, in practical applications, the first time period can be the next 24 hours, and the second time period can be 1 hour or half an hour.

[0067] Specifically, the total cost objective function is shown in Formula (1), Formula (2) defines the operating cost, and Formula (3) defines the carbon emissions.

[0068] (1)

[0069] (2)

[0070] (3)

[0071] in, It is an integrated energy network Total cost This is the total duration of the first time slot scheduled the day before. It refers to every moment within the first time period. It's operating costs. It is an integrated energy network From integrated energy network The cost of purchasing energy, It is an integrated energy network The amount of hydrogen sold. It is the unit price at which the integrated energy network sells hydrogen; The electricity is purchased from the main power grid. It is the unit price for purchasing electricity. It is electricity sold to the main power grid. It is the unit price of electricity sold. This refers to the volume of natural gas purchased. That's the price per unit of natural gas. It refers to carbon emissions. It's a carbon tax. It is the operating cost of fuel cells. It refers to the charge and discharge efficiency of the fuel cell. It is the charging and discharging power of the fuel cell, It is the penalty coefficient for the battery. It refers to the storage capacity of the battery. It is the penalty coefficient for hydrogen storage equipment. It refers to the storage capacity of energy storage devices. It is the emission coefficient of natural gas. It is the power emission coefficient of the main power grid.

[0072] The computer equipment optimizes the objective function of total cost to obtain the day-ahead scheduling data of energy equipment in the integrated energy network.

[0073] The first period includes multiple second periods. For each second period, before the start of the second period, the day-ahead scheduling data of the second period is rescheduled intraday to correct the day-ahead scheduling data.

[0074] The objective function for operating costs is shown in formula (4).

[0075] (4)

[0076] in, to Indicates the second time period. It's operating costs.

[0077] In the above embodiments, in the scheduling of the integrated energy network, day-ahead scheduling is performed first to formulate a preliminary scheduling plan for energy demand in the future. Intraday rescheduling is based on the day-ahead scheduling and dynamically adjusts the day-ahead scheduling data according to real-time changes in energy demand. In each second time period, the optimization problem is resolved based on the scheduling data of the previous time period to obtain candidate scheduling data for the current second time period. This process is continuously rolled out, which can adjust the scheduling data in a timely manner according to the uncertain changes in energy demand and equipment status, thereby improving the flexibility and real-time performance of scheduling and making the candidate scheduling data more accurate.

[0078] In some embodiments, the forecast data includes forecasted wind turbine power generation, forecasted photovoltaic power generation, and forecasted power load; determining an error fuzzy set based on candidate scheduling data and forecast data corresponding to the integrated energy network includes: obtaining candidate wind turbine power generation, candidate photovoltaic power generation, and candidate power load from the candidate scheduling data; determining wind turbine power generation error based on candidate wind turbine power generation and forecasted wind turbine power generation; determining photovoltaic power generation error based on candidate photovoltaic power generation and forecasted photovoltaic power generation; determining power load error based on candidate power load and forecasted power load; and determining an error fuzzy set based on wind turbine power generation error, photovoltaic power generation error, and power load error.

[0079] The forecasts for wind turbine power generation, photovoltaic power generation, and power load are based on historical data.

[0080] The candidate scheduling data is obtained after intraday rescheduling, and includes candidate scheduling data for each time point within the second time period; correspondingly, the predicted scheduling data includes candidate scheduling data for each time point within the second time period.

[0081] For each moment in the second time period, the computer equipment obtains the candidate wind turbine power generation, candidate photovoltaic power generation, and candidate power load from the candidate scheduling data at the current moment; calculates the difference between the candidate wind turbine power generation and the predicted wind turbine power generation at the current moment to obtain the wind turbine power generation error at the current moment; calculates the difference between the candidate photovoltaic power generation and the predicted photovoltaic power generation at the current moment to obtain the photovoltaic power generation error at the current moment; calculates the difference between the candidate power load and the predicted power load at the current moment to obtain the power load error at the current moment; calculates the sum of the wind turbine power generation error and the photovoltaic power generation error at the current moment, and calculates the error between this sum and the power load error at the current moment to obtain the total error at the current moment; based on the total error at multiple moments in the second time period, an error fuzzy set is obtained.

[0082] For example, the wind turbine power generation error, photovoltaic power generation error and power load error can be determined according to formulas (5), (6) and (7).

[0083] (5)

[0084] (6)

[0085] (7)

[0086] in, It is a moment The power generation of candidate wind turbines. It is a moment Predicted wind turbine power generation, It is a moment The error in wind turbine power generation, It is a moment Candidate photovoltaic power generation. It is a moment Predicted photovoltaic power generation It is a moment The error in photovoltaic power generation, It is a moment Candidate power loads, It is a moment Forecasted power load, It is a moment The power load error.

[0087] The total error can be determined according to formula (8).

[0088] (8)

[0089] in, It is a moment The total error, It is a moment The error in wind turbine power generation, It is a moment The error in photovoltaic power generation, It is a moment The power load error; the error fuzzy set can be represented as .

[0090] In the above embodiments, since there are uncertainties in photovoltaic panels, wind turbines and power loads, an error fuzzy set is determined based on the predicted data and candidate scheduling data of photovoltaic panels, wind turbines and power loads. Subsequently, the candidate scheduling data of photovoltaic panels, wind turbines and power loads can be adjusted to reduce the impact of uncertain data flow in the integrated energy network on the operation of the integrated energy network, improve the reliability of the integrated energy network, and also improve the accuracy of scheduling the integrated energy network.

[0091] In some embodiments, the scheduling method for the integrated energy network further includes: acquiring historical wind power data and historical solar irradiance data; performing predictive processing on the historical wind power data using a predictive model to obtain predicted wind turbine power generation; performing predictive processing on the historical solar irradiance data using a predictive model to obtain predicted photovoltaic power generation; and determining the predicted power load based on the predicted wind turbine power generation and predicted photovoltaic power generation; the predicted data includes predicted wind turbine power generation, predicted photovoltaic power generation, and predicted power load.

[0092] Among them, historical wind data and historical sunshine data can be the wind data and sunshine data corresponding to the second time period in history; for example, the current second time period is 8:00 to 9:00, the historical wind data can be the wind data from 8:00 to 9:00 three days ago, the historical sunshine data can be the sunshine data from 8:00 to 9:00 three days ago, and the historical power load can be the power load from 8:00 to 9:00 three days ago.

[0093] Specifically, computer equipment acquires historical wind power data and historical sunshine data. The historical wind power data is input into a prediction model, such as an LSTM (Long Short-Term Memory) model, to obtain the predicted wind turbine power generation. The historical sunshine data is input into an LSTM model to obtain the predicted photovoltaic power generation. The historical power load is input into an LSTM model to obtain the predicted power load.

[0094] In the above embodiments, the predicted wind turbine power generation, predicted photovoltaic power generation, and predicted power load are determined by using historical wind power data, historical sunshine data, and historical power load. The predicted data provides a basis for subsequent adjustment of candidate scheduling data, making the target scheduling data more consistent with the actual operation of the integrated energy network and improving the quality of the target scheduling data.

[0095] In some embodiments, performing variational inference on the error fuzzy set to obtain target error data with a defined distribution includes: inputting the error fuzzy set into the variational inference model to obtain target error data with a defined distribution.

[0096] Among them, the variational inference model can be a Dirichlet mixture model, which is a nonparametric Bayesian model.

[0097] Specifically, the error fuzzy set is input into a variational inference model (such as a Dirichlet mixture model). The Dirichlet mixture model can update its parameters based on the error fuzzy set, for example, by minimizing the variational objective function to find the optimal parameters. After the parameters are updated, cluster analysis can be performed on the error fuzzy set. Based on the clustering results, the error distribution characteristics of each cluster can be calculated, such as mean and variance. The error interval is determined based on the distribution characteristics, thus obtaining the target error data with a defined distribution. Therefore, the target error data can represent the error interval.

[0098] In the above embodiments, the uncertain error fuzzy set is processed by the variational inference model to obtain target error data with a definite distribution, thereby eliminating the influence of uncertain data streams. The candidate scheduling data is adjusted by the target error data, and the integrated energy network is scheduled according to the obtained target scheduling data, which improves the reliability of the integrated energy network and the accuracy of scheduling the integrated energy network.

[0099] In some embodiments, the candidate scheduling data is the candidate scheduling data of energy equipment in a second time period; the target error data includes the target error interval in the second time period; adjusting the candidate scheduling data according to the target error data to obtain the target scheduling data of the integrated energy network includes: selecting the target error in the second time period from the target error interval; adjusting the candidate scheduling data of energy equipment in the second time period according to the target error in the second time period to obtain the target scheduling data of energy equipment in the integrated energy network.

[0100] The target error can be any value within the target error interval. For example, the target error can be the maximum value of the target error interval, the minimum value of the target error interval, or a value randomly selected from the target error interval.

[0101] Specifically, the computer equipment randomly selects the target error within the second time period from the target error interval, and adjusts the candidate scheduling data within the second time period based on the target error within the second time period to obtain the target scheduling data of the integrated energy network in the second time period.

[0102] In some embodiments, the second time period includes multiple third time periods. After obtaining the target scheduling data for the second time period, the scheduling data of the integrated energy network in the third time period can be determined based on the target scheduling data of the second time period, with the goal of minimizing the total cost. Then, the integrated energy network is operated in the third time period according to the scheduling data of the third time period.

[0103] Based on the target scheduling data for the second time period, with the goal of minimizing the total cost, the scheduling data for the integrated energy network in the third time period is determined. The objective function for the third time period can then be optimized and solved.

[0104] In the above embodiments, the candidate scheduling data is adjusted by the target error data to obtain the target scheduling data, which eliminates the impact of uncertain data flow. The candidate scheduling data is adjusted by the target error data, and the integrated energy network is scheduled according to the obtained target scheduling data, which improves the reliability of the integrated energy network and the accuracy of scheduling the integrated energy network.

[0105] Figure 4 Flowchart of the integrated energy network scheduling method provided in this application Figure 2 ,like Figure 4 As shown, in this embodiment... Figure 2 Based on the embodiments, the scheduling method of the integrated energy network is described in detail, which includes:

[0106] S401. Based on the total cost objective function of the integrated energy network, with the goal of minimizing the total cost, perform day-ahead scheduling of the energy equipment in the integrated energy network to obtain day-ahead scheduling data for the first time period.

[0107] S402. For each second period included in the first period, based on the day-ahead scheduling data in the first period, and according to the operating cost objective function of the integrated energy network, with the goal of minimizing operating costs, the energy equipment in the integrated energy network is rescheduled intraday to obtain candidate scheduling data for the second period.

[0108] S403. Obtain historical wind power data, historical sunshine data, and historical power load; use a prediction model to process the historical wind power data to obtain the predicted wind turbine power generation; use a prediction model to process the historical sunshine data to obtain the predicted photovoltaic power generation; use a prediction model to process the historical power load to obtain the predicted power load.

[0109] S404. Obtain candidate wind turbine power generation, candidate photovoltaic power generation, and candidate power load from the candidate scheduling data; determine the wind turbine power generation error based on the candidate wind turbine power generation and the predicted wind turbine power generation; determine the photovoltaic power generation error based on the candidate photovoltaic power generation and the predicted photovoltaic power generation; determine the power load error based on the candidate power load and the predicted power load; determine the error fuzzy set based on the wind turbine power generation error, photovoltaic power generation error, and power load error.

[0110] S405. Input the error fuzzy set into the variational inference model to obtain target error data with a defined distribution;

[0111] S406. Select the target error within the second time period from the target error interval; adjust the candidate scheduling data within the second time period based on the target error within the second time period to obtain the target scheduling data of the integrated energy network in the second time period.

[0112] like Figure 5 As shown, the scheduling method of the integrated energy network includes: constructing a total cost objective function with the goal of minimizing total cost; optimizing and solving the total cost objective function to determine the day-ahead scheduling data of the integrated energy network for the next 24 hours (the first time period); for a certain hour in the next 24 hours (the second time period), performing intraday rescheduling on the day-ahead scheduling data of the second time period to correct the day-ahead scheduling data and obtain candidate scheduling data for that hour; and making predictions based on historical wind power data, historical solar irradiance data, and historical power load to obtain the predicted wind turbine power generation, predicted photovoltaic power generation, and predicted power load for that hour.

[0113] Based on the candidate scheduling data for a certain hour, including candidate wind turbine power generation, candidate photovoltaic power generation, and candidate power load, as well as the predicted wind turbine power generation, predicted photovoltaic power generation, and predicted power load for a certain hour, calculate the error fuzzy set.

[0114] Variational inference is performed on the fuzzy error set to obtain target error data with a defined distribution; the candidate scheduling data is adjusted using the target error data to obtain the target scheduling data; and the integrated energy network is scheduled for a certain hour based on the target scheduling data.

[0115] The aforementioned integrated energy network scheduling method aims to minimize the cost of the integrated energy network. By determining candidate scheduling data, it can optimize economic costs while meeting energy demand. Since the integrated energy network contains uncertain data flows, such as the power generation and load of wind turbines and photovoltaic panels, after determining the scheduling data, a fuzzy error set is determined between the predicted data and the scheduling data. This fuzzy error set characterizes the complex probability distribution of errors in uncertain data flows. Variational inference is used to process the fuzzy error set to obtain a target error with a defined distribution. The candidate scheduling data is then adjusted using this target error to obtain the target scheduling data. This reduces the impact of uncertain data flows on the operation of the integrated energy network, improving its reliability and the accuracy of its scheduling.

[0116] Figure 6 A schematic diagram of the structure of the dispatching device for the integrated energy network provided in this application is shown below. Figure 6 As shown, the integrated energy network scheduling device 60 provided in this embodiment includes:

[0117] The first scheduling module 601 is used to schedule energy equipment in the integrated energy network with the goal of minimizing the cost of the integrated energy network, and to obtain candidate scheduling data;

[0118] The first error determination module 602 is used to determine the error fuzzy set based on the candidate scheduling data and the prediction data corresponding to the integrated energy network;

[0119] The second error determination module 603 is used to perform variational inference on the error fuzzy set to obtain target error data with a defined distribution.

[0120] The second scheduling module 604 is used to adjust the candidate scheduling data based on the target error data to obtain the target scheduling data of the integrated energy network, and to schedule the integrated energy network based on the target scheduling data.

[0121] In one possible implementation, the first scheduling module 601 is further configured to perform day-ahead scheduling of energy equipment in the integrated energy network based on the total cost objective function of the integrated energy network, with the goal of minimizing the total cost, to obtain day-ahead scheduling data for a first time period; and for each second time period included in the first time period, based on the day-ahead scheduling data in the first time period, and based on the operating cost objective function of the integrated energy network, with the goal of minimizing the operating cost, to perform intraday rescheduling of energy equipment in the integrated energy network, to obtain candidate scheduling data for the second time period.

[0122] In one possible implementation, the prediction data includes predicted wind turbine power generation, predicted photovoltaic power generation, and predicted power load; a first error determination module 602 is used to obtain candidate wind turbine power generation, candidate photovoltaic power generation, and candidate power load from candidate scheduling data; determine wind turbine power generation error based on candidate wind turbine power generation and predicted wind turbine power generation; determine photovoltaic power generation error based on candidate photovoltaic power generation and predicted photovoltaic power generation; determine power load error based on candidate power load and predicted power load; and determine an error fuzzy set based on wind turbine power generation error, photovoltaic power generation error, and power load error.

[0123] In one possible implementation, the first error determination module 602 is used to input the error fuzzy set into the variational inference model to obtain target error data with a defined distribution.

[0124] In one possible implementation, the scheduling device of the integrated energy network further includes: a prediction module for acquiring historical wind power data, historical solar radiation data, and historical power load; performing prediction processing on the historical wind power data using a prediction model to obtain predicted wind turbine power generation; performing prediction processing on the historical solar radiation data using a prediction model to obtain predicted photovoltaic power generation; and performing prediction processing on the historical power load using a prediction model to obtain predicted power load.

[0125] In one possible implementation, the candidate scheduling data is the candidate scheduling data within the second time period; the target error data includes the target error interval within the second time period; the second scheduling module 604 is used to select the target error within the second time period from the target error interval; and the candidate scheduling data within the second time period is adjusted according to the target error within the second time period to obtain the target scheduling data of the integrated energy network in the second time period.

[0126] The integrated energy network scheduling device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0127] Figure 7 A schematic diagram of the structure of the computer device provided in this application. Figure 7As shown, the computer device 70 provided in this embodiment includes at least one processor 701 and a memory 702. Optionally, the device 70 further includes a communication component 703. The processor 701, memory 702, and communication component 703 are connected via a bus 704.

[0128] In a specific implementation, at least one processor 701 executes computer execution instructions stored in memory 702, causing at least one processor 701 to perform the above-described method.

[0129] The specific implementation process of processor 701 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0130] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0131] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0132] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0133] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0134] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0135] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0136] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0137] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0138] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0139] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0140] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0141] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0142] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A scheduling method for an integrated energy network, characterized in that, include: With the goal of minimizing the cost of the integrated energy network, energy devices in the integrated energy network are scheduled to obtain candidate scheduling data; Based on the candidate scheduling data and the prediction data corresponding to the integrated energy network, an error fuzzy set is determined; Variational inference is performed on the error fuzzy set to obtain target error data with a defined distribution; The candidate scheduling data is adjusted based on the target error data to obtain the target scheduling data for the integrated energy network, and the integrated energy network is scheduled based on the target scheduling data.

2. The method according to claim 1, characterized in that, The goal is to minimize the cost of the integrated energy network, which involves scheduling energy devices within the integrated energy network to obtain candidate scheduling data, including: Based on the total cost objective function of the integrated energy network, with the goal of minimizing the total cost, day-ahead scheduling is performed on the energy equipment in the integrated energy network to obtain day-ahead scheduling data for the first time period; For each second time period included in the first time period, based on the day-ahead scheduling data within the first time period, and according to the operating cost objective function of the integrated energy network, with the goal of minimizing operating costs, the energy equipment in the integrated energy network is rescheduled intraday to obtain candidate scheduling data for the second time period.

3. The method according to claim 1, characterized in that, The forecast data includes forecasted wind turbine power generation, forecasted photovoltaic power generation, and forecasted power load; The step of determining the error fuzzy set based on the candidate scheduling data and the prediction data corresponding to the integrated energy network includes: From the candidate scheduling data, obtain candidate wind turbine power generation, candidate photovoltaic power generation, and candidate power load; Based on the power generation of the candidate wind turbines and the power generation of the predicted wind turbines, the wind turbine power generation error is determined; Based on the candidate photovoltaic power generation and the predicted photovoltaic power generation, the photovoltaic power generation error is determined; Based on the candidate power load and the predicted power load, the power load error is determined; Based on the wind turbine power generation error, the photovoltaic power generation error, and the power load error, an error fuzzy set is determined.

4. The method according to claim 1, characterized in that, The step of performing variational inference on the error fuzzy set to obtain target error data with a defined distribution includes: The error fuzzy set is input into the variational inference model to obtain target error data with a defined distribution.

5. The method according to any one of claims 1 to 4, characterized in that, The method further includes: Acquire historical wind data, historical sunshine data, and historical power load; The historical wind power data is processed by a predictive model to obtain the predicted wind turbine power generation. The historical sunshine data is processed by the prediction model to obtain the predicted photovoltaic power generation. The predicted power load is obtained by performing prediction processing on the historical power load using the prediction model.

6. The method according to any one of claims 1 to 4, characterized in that, The candidate scheduling data is the candidate scheduling data within the second time period; the target error data includes the target error interval within the second time period. The step of adjusting the candidate scheduling data based on the target error data to obtain the target scheduling data for the integrated energy network includes: Select the target error within the second time period from the target error interval; Based on the target error in the second time period, the candidate scheduling data in the second time period are adjusted to obtain the target scheduling data of the integrated energy network in the second time period.

7. A dispatching device for an integrated energy network, characterized in that, include: The first scheduling module is used to schedule energy devices in the integrated energy network with the goal of minimizing the cost of the integrated energy network, and to obtain candidate scheduling data. The first error determination module is used to determine the error fuzzy set based on the candidate scheduling data and the prediction data corresponding to the integrated energy network; The second error determination module is used to perform variational inference on the error fuzzy set to obtain target error data with a defined distribution. The second scheduling module is used to adjust the candidate scheduling data based on the target error data to obtain the target scheduling data of the integrated energy network, and to schedule the integrated energy network based on the target scheduling data.

8. A computer device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-6.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method described in any one of claims 1-6.

Images