Power generation scheduling method of power system and related device

Abstract

The invention discloses a power generation scheduling method of a power system and a related device, which can be used in the field of power generation scheduling, and the method comprises the steps: firstly, obtaining the production element data of each power plant in the power system; then, on the basis of the production element data, through a pre-established production element model, the initial cost per kilowatt-hour of each power plant is determined; then, based on the production element data, stability parameters of all the power plants are determined respectively; and finally, according to the initial cost per kilowatt-hour and the stability parameter of each power plant, obtaining a power generation capacity scheduling scheme through a pre-trained scheduling model. Therefore, for a plurality of power plants in the power system, production element data can be comprehensively considered, a low-cost power generation scheduling scheme capable of meeting the stability requirement can be obtained from the two dimensions of the initial kilowatt-hour cost and the stability, and the power generation cost is reduced.

Description

Technical Field

[0001] The present application relates to the technical field of power generation dispatching, and in particular to a power generation dispatching method and related devices for a power system. Background Art

[0002] As the scale of the power system continues to expand, the number and types of power plants in the power system are also increasing.

[0003] At present, in order to meet the power grid's demand for power generation, one or more power plants that can provide sufficient power generation are usually selected to participate in power generation. However, different power plants have different power generation costs. Randomly dispatching the power generation of each power plant while only meeting the power generation demand will lead to excessively high power generation costs and reduce the competitiveness of the power system.

[0004] Therefore, how to reduce the cost of power generation has become a problem that needs to be solved. Summary of the invention

[0005] Based on the above problems, the present application provides a power generation scheduling method and related devices for an electric power system, which can reduce the cost of power generation.

[0006] The embodiments of the present application disclose the following technical solutions:

[0007] In a first aspect, an embodiment of the present application provides a method for power generation scheduling of a power system, the method comprising:

[0008] Acquire production factor data of each power plant in the power system; the production factor data includes at least one of illuminance, heat consumption, fuel consumption, water flow, water level and wind speed;

[0009] Based on the production factor data, the initial electricity cost of each power plant is determined through a pre-established production factor model; the initial electricity cost includes electricity generation cost and electricity carbon emission cost;

[0010] Based on the production factor data, stability parameters of each power plant are determined respectively; the stability parameters include frequency, system inertia and voltage;

[0011] According to the initial LCOE of each power plant and the stability parameters of each power plant, a power generation scheduling plan is obtained through a pre-trained scheduling model.

[0012] Optionally, the initial kilowatt-hour cost of each power plant is determined based on the production factor data through a pre-established production factor model, including:

[0013] Based on the production factor data, a production vector value is obtained; the production vector includes: a SOLAR vector established based on illuminance, month, reactive power, power plant efficiency, spare capacity, and monthly power generation; a COAL POWER vector established based on heat consumption, fuel consumption, fuel price, load rate, month, rotation capacity, and monthly power generation; a HYDRO POWER vector established based on water head, water inflow, water abandonment rate, rotation capacity, and monthly power generation; and a WIND POWER vector established based on wind speed, wind time, wind abandonment rate, and monthly power generation;

[0014] Based on the production vector value, the initial cost per kilowatt-hour of each power plant is determined through a pre-established production factor model.

[0015] Optionally, the initial kilowatt-hour cost of each power plant is determined based on the production factor data through a pre-established production factor model, including:

[0016] Based on the production factor data, the power generation cost per kilowatt-hour of each power plant is determined through a pre-established production factor model;

[0017] The sum of the power generation cost per kilowatt-hour and the carbon emission cost per kilowatt-hour of each power plant is calculated to obtain the initial power generation cost per kilowatt-hour of each power plant; the carbon emission cost per kilowatt-hour is obtained based on the full life cycle carbon footprint of each power plant; the full life cycle carbon footprint includes the total carbon emissions generated by the production of power generation equipment and the total carbon emissions in the power generation process.

[0018] Optionally, based on the production factor data, determining the electricity generation cost per kilowatt-hour of each power plant through a pre-established production factor model includes:

[0019] Based on the production factor data, the power generation of each power plant in the target period is determined by using a pre-established production factor model;

[0020] Based on the power generation of each power plant and the power generation cost data of each power plant, the power generation cost per kilowatt-hour of each power plant is determined respectively through the production factor model.

[0021] Optionally, before obtaining the power generation scheduling plan according to the initial KWh cost of each power plant and the stability parameter of each power plant through a pre-trained scheduling model, the method further includes:

[0022] Calculate the kilowatt-hour capacity cost of each power plant based on the power generation of each power plant in the target period and the capacity cost of each power plant;

[0023] Calculate a first weight according to the initial kilowatt-hour cost, kilowatt-hour capacity cost and generator set performance coefficient of each power plant; the first weight is the sum of the product of the kilowatt-hour carbon emission cost and the kilowatt-hour capacity cost and the product of the generator set performance coefficient and the kilowatt-hour power generation cost;

[0024] The power generation scheduling scheme is obtained according to the initial kilowatt-hour cost of each power plant and the stability parameters of each power plant through a pre-trained scheduling model, including:

[0025] Based on the first weight of each power plant, the emergency level of power demand of the power grid, the initial cost per kilowatt-hour of each power plant, and the stability parameters of each power plant, a power generation scheduling plan is obtained through a pre-trained scheduling model.

[0026] Optionally, obtaining a power generation scheduling plan based on the initial KWh cost of each power plant and the stability parameters of each power plant through a pre-trained scheduling model includes:

[0027] According to the grid stability requirement and the stability parameters of each power plant, determining the target power plant type that meets the grid stability requirement; the target power plant type is selected from at least one of thermal power, hydropower, photovoltaic power and wind power;

[0028] Based on the initial kilowatt-hour costs of each power plant that meets the target power plant type, a power generation scheduling plan is obtained through a pre-trained scheduling model; the power generation scheduling plan is a scheduling plan with the lowest initial kilowatt-hour cost.

[0029] Optionally, after obtaining the power generation scheduling scheme according to the initial KWh cost of each power plant and the stability parameter of each power plant through a pre-trained scheduling model, the method further includes:

[0030] Based on a scheduling feasibility model, determining the feasibility of the power generation scheduling plan; the scheduling feasibility model is obtained by training the virtual power plant scheduling history and scheduling failure rate;

[0031] If the power generation scheduling plan is feasible, the power generation scheduling plan is executed; if the power generation scheduling plan is not feasible, the power generation scheduling plan is re-determined.

[0032] Optionally, after executing the power generation scheduling plan, the method further includes:

[0033] Based on the real-time production factor data fed back by each working power plant participating in power generation in the power generation scheduling plan, the real-time electricity cost of each working power plant is determined through the production factor model;

[0034] If there is a working power plant whose real-time kilowatt-hour cost increases beyond the preset threshold compared with the initial kilowatt-hour cost, the power generation scheduling plan will be re-determined.

[0035] Optionally, after executing the power generation scheduling plan, the method further includes:

[0036] Each working power plant participating in power generation in the power generation scheduling scheme controls the power generation of each working power plant according to real-time production factor data, so that the power generation of each working power plant fits the power generation in the power generation scheduling scheme.

[0037] In a second aspect, an embodiment of the present application provides a power generation scheduling device for a power system, the device comprising: an acquisition module, a cost determination module, a stability determination module, and a solution output module;

[0038] The acquisition module is used to acquire production factor data of each power plant in the power system; the production factor data includes at least one of illuminance, heat consumption, fuel consumption, water flow, water level and wind speed;

[0039] The cost determination module is used to determine the initial electricity cost per kilowatt-hour of each power plant based on the production factor data and through a pre-established production factor model; the initial electricity cost per kilowatt-hour includes the electricity generation cost per kilowatt-hour and the carbon emission cost per kilowatt-hour;

[0040] The stability determination module is used to determine the stability parameters of each power plant based on the production factor data; the stability parameters include frequency, system inertia and voltage;

[0041] The scheme output module is used to obtain a power generation scheduling scheme according to the initial cost per kilowatt-hour of each power plant and the stability parameters of each power plant through a pre-trained scheduling model.

[0042] In a third aspect, an embodiment of the present application provides a power generation scheduling device for a power system, the device comprising: a memory and a processor;

[0043] The memory is used to store program code and transmit the program code to the processor;

[0044] The processor is used to execute the steps of the power generation scheduling method of the power system described in any embodiment of the first aspect according to the program code.

[0045] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which a computer program is stored. When the computer program is run on a power generation dispatching device of a power system, the power generation dispatching device of the power system executes the steps of the power generation dispatching method of the power system described in any implementation manner in the first aspect.

[0046] Compared with the prior art, this application has the following beneficial effects:

[0047] The embodiment of the present application provides a method for power generation scheduling of an electric power system, in which, first, the production factor data of each power plant in the electric power system is obtained; the production factor data includes at least one of illuminance, heat consumption, fuel consumption, water inflow, water level and wind speed; then, based on the production factor data, the initial kilowatt-hour cost of each power plant is determined through a pre-established production factor model; the initial kilowatt-hour cost includes the kilowatt-hour power generation cost and the kilowatt-hour carbon emission cost; then, based on the production factor data, the stability parameters of each power plant are determined; the stability parameters include frequency, system inertia and voltage; finally, according to the initial kilowatt-hour cost of each power plant and the stability parameters of each power plant, a power generation scheduling plan is obtained through a pre-trained scheduling model. Therefore, for multiple power plants in the electric power system, the production factor data can be comprehensively considered, and from the two dimensions of initial kilowatt-hour cost and stability, a low-cost power generation scheduling plan that can meet the stability requirements can be obtained to reduce the power generation cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0049] Figure 1 A flow chart of a power generation scheduling method for a power system provided in an embodiment of the present application;

[0050] Figure 2 A flow chart of another power generation scheduling method for a power system provided in an embodiment of the present application;

[0051] Figure 3 An interactive diagram of a power generation dispatching process of a power system provided in an embodiment of the present application;

[0052] Figure 4 A schematic diagram of a power generation dispatching device for a power system provided in an embodiment of the present application;

[0053] Figure 5 A structural diagram of a power generation dispatching device for a power system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0054] The power generation dispatching method and related devices of a power system provided in the present application can be used in the field of power generation dispatching. The above is only an example and does not limit the application field of the power generation dispatching method and related devices of a power system provided in the present application.

[0055] The terms "first", "second", "third" and "fourth" etc. in the specification, claims and drawings of this application are used to distinguish different objects rather than to limit a specific order.

[0056] In the embodiments of the present application, the words "as an example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "as an example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the words "as an example" or "for example" is intended to present the relevant concepts in a specific way.

[0057] The terms used in the implementation section of this application are only used to explain the specific embodiments of this application and are not intended to limit this application.

[0058] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0059] See also Figure 1 , which is a flow chart of a power generation dispatching method for a power system provided in an embodiment of the present application, the method comprising:

[0060] S101: Obtain production factor data of each power plant in the power system.

[0061] Production factors include various resources and conditions used to produce electric energy. As an example, for a thermal power plant, production factor data may include one or more of the following data: heat consumption, fuel consumption, fuel price, load rate, month, and rotation capacity; for a hydropower plant, production factor data may include one or more of the following data: water head, water flow, water level, water abandonment rate, and rotation capacity; for a photovoltaic power plant, production factor data may include one or more of the following data: illuminance, month, reactive power, power plant efficiency, and spare capacity; for a wind power plant, production factor data may include one or more of the following data: wind speed, wind time, and wind abandonment rate.

[0062] S102: Based on the production factor data, the initial cost per kilowatt-hour of each power plant is determined through a pre-established production factor model.

[0063] Specifically, based on the production factor data, a digital production vector value that can reflect the characteristics of the production factor can be obtained, and the production factor data can be converted into a digital vector that can be processed by the artificial intelligence model. Among them, the production vector may include but is not limited to: a SOLAR vector based on illuminance, month, reactive power, power plant efficiency, spare capacity, and monthly power generation, a COALPOWER vector based on heat consumption, fuel consumption, fuel price, load rate, month, rotation capacity, and monthly power generation, a HYDRO POWER vector based on water head, water flow, water abandonment rate, rotation capacity, and monthly power generation, and a WIND POWER vector based on wind speed, wind time, wind abandonment rate, and monthly power generation.

[0064] Exemplarily, the production factor model may include a power generation cost operator and a carbon emission cost operator.

[0065] Among them, the power generation cost operator can determine the power generation of each power plant in the target time period according to the correlation between production factor data and power generation; among them, for photovoltaic power plants, the correlation between production factor data and power generation can be a functional relationship between illuminance and power generation; for coal-fired power plants, the correlation between production factor data and power generation can be a functional relationship between heat consumption and power generation under different working conditions; the target time period is a period of preset time length before the current moment, for example, the current moment is 13:00, the preset time length is 1 hour, then the target time period can be 12:00-13:00; then based on the power generation and power generation cost data of each power plant, the power generation cost per kilowatt-hour of each power plant is calculated.

[0066] The carbon emission cost calculator can calculate the carbon emission cost per kilowatt-hour of each power plant based on the carbon footprint of each power plant over its entire life cycle. The carbon footprint over its entire life cycle includes the total carbon emissions generated by the production of power generation equipment and the total carbon emissions during the power generation process.

[0067] By calculating the sum of the electricity generation cost per kilowatt-hour and the carbon emission cost per kilowatt-hour of each power plant, we can obtain the initial electricity cost per kilowatt-hour of each power plant.

[0068] For example, for a thermal power plant, after determining the power generation of a thermal power plant in the target period, the power generation cost operator in the production factor model can calculate the fuel cost required for each kilowatt-hour of electricity produced by the thermal power plant, that is, the kilowatt-hour electricity cost, based on the COAL POWER vector, through the fuel price SHRcc per unit energy, the high calorific value HHV of the fuel, and the fuel unit price U, using the electricity price cost formula such as ECRm=SHRcc×(1 / HHV)×U / 1000, where the unit of SHRcc is USD / KJ, the unit of 1 / HHV is kg / KJ, the unit of U is USD / t, and the unit of ECRm is USD / kWh; the kilowatt-hour capacity cost is calculated based on the capacity cost of the thermal power plant. Similarly, by using the power generation cost operator and combining it with the current production vector value, the power generation capacity cost and power generation operation and maintenance cost of the thermal power plant can be calculated. Finally, the power generation cost of the thermal power plant is obtained by calculating the sum of the power generation cost, power generation capacity cost and power generation operation and maintenance cost. The capacity cost refers to the cost required for the construction of the power plant to ensure that the power system can meet the power demand at any time. The capacity cost is allocated to each power generation unit of the power plant to obtain the capacity cost, that is, the depreciation cost. The power generation operation and maintenance cost can be obtained by allocating the operation and maintenance cost required to operate the power plant to each power generation unit of the power plant.

[0069] The carbon emission cost operator in the production factor model can calculate the carbon emission rate per unit of power generation of the thermal power plant and obtain the carbon emissions during the power generation process within the target period. Then, based on the carbon emissions during the power generation process within the target period, the total carbon emissions generated in the production process of power generation equipment and the carbon price, the carbon emission cost per kilowatt-hour is obtained.

[0070] See Table 1, which is a table of electricity prices and costs for a selected target coal type under different working conditions (power plant load). The grid compensation coefficient for 1 kWh of electricity payment is the electricity price of the grid supply (excluding limestone costs), which generally accounts for more than 50% of the entire electricity price.

[0071] The example calculation formula for the grid compensation coefficient for 1 kWh of electricity payment is: CERm = U*N / E (1-AUX); where U represents the coal price, which is also the fuel cost subsidy, in US dollars per ton (USD / t). As an example, U = 69USD / t. E represents the unit's power generation heat consumption rate, that is, the unit's heat consumption per kWh, in kcal / kWh. N represents the specific heat index, specifically the heat required per kilowatt-hour of electricity, in kcal / kWh, and AUX represents the plant power consumption rate, in %.

[0072] In Table 1, SHRW represents the weighted specific heat index, in kJ / kWh. Ea represents the power supply (or power generation), in kWh. Ep represents the electricity cost, in USD (USD). SHRcc represents the specific heat index, in kJ / kWh. U represents the coal price, in USD / t. ECRm represents the electricity cost per kilowatt-hour, in USD / kWh. ECRm represents the electricity charge ratio, that is, the coal cost per kilowatt-hour of electricity produced, in USD / kWh.

[0073] The calculation formula of ECRm is: ECRm = SHRcc × (1 / HHV) × U / 1000

[0074] The calculation formula of Ep is: Ep = NEOm * CERx; where NEOm represents the net power generation, in kWh. CERx represents the electricity price, in USD / kWh.

[0075] As shown in Table 1, through the correlation between different values ​​of electricity prices and loads, the cost reflected by the fuel of each thermal power plant in the power grid can be given, so that the power grid can extract the unit performance, environmental protection conditions and fuel cost conditions of the power plant under different load conditions based on these data.

[0076] It can be seen from Table 1 that the higher the load, the smaller the grid compensation coefficient per kilowatt-hour, which means the electricity cost per kilowatt-hour is lower.

[0077] Table 1

[0078]

[0079]

[0080] It can be understood that in the various calculation formulas provided in the embodiments of the present application, the currency unit can be unified and is not limited to the U.S. dollar, but can also be yuan, euro, pound sterling, etc.

[0081] S103: Based on the production factor data, the stability parameters of each power plant are determined respectively.

[0082] Specifically, the stability parameters may include, but are not limited to, parameters such as frequency, system inertia, and voltage.

[0083] As an example, key factors in production factors can be extracted as data views, where key factors are parameters that directly affect the performance and reliability of the generator set. For example, for a photovoltaic power plant, key factors can be parameters such as photovoltaic power generation efficiency, capacity ratio, temperature coefficient, and maximum power point voltage; for a thermal power plant, key factors can be parameters such as heat consumption and actual output power; for a hydropower plant, key factors can be parameters such as water inflow, water head, and unit vibration level.

[0084] Through the data view, the stability parameters of the power plant such as system inertia, frequency and voltage can be determined. Among them, the system inertia (also called rotational inertia or rotational inertia) is an important parameter to measure the sum of the kinetic energy of the rotors of all synchronous generators in the system. The larger the system inertia, the stronger the resistance to frequency changes, the smaller the frequency fluctuation, and the more stable it is during operation; and for frequency and voltage, it can be considered that the closer to the frequency and voltage of the current power system, the higher the degree of stability. The stability parameters can include parameters such as system inertia, frequency and voltage, or any one of the parameters such as system inertia, frequency and voltage, or can be calculated based on the parameters such as system inertia, frequency and voltage.

[0085] S104: According to the initial LCOE of each power plant and the stability parameters of each power plant, a power generation scheduling plan is obtained through a pre-trained scheduling model.

[0086] As an example, the target power plant type that meets the grid stability requirements can be determined based on the grid stability requirements and the stability parameters of each power plant; wherein the target power plant type is selected from at least one of thermal power, hydropower, photovoltaic power and wind power; then, based on the initial kilowatt-hour cost of each power plant that meets the target power plant type, the power generation scheduling plan is obtained through the pre-trained scheduling model; wherein the power generation scheduling plan is a scheduling plan that maximizes the difference between the kilowatt-hour revenue and the initial kilowatt-hour cost. Taking into account the safety of the power plant grid, when the unit capacity is large, the determination of the power generation scheduling plan can refer to the data samples of the impact of the load shedding units of each large unit under 0-100% load on the system frequency and voltage, so that the impact of the unit on the system frequency and voltage under any load can be quantified, so that the power grid can adopt the corresponding power generation scheduling plan to reduce the changes in system frequency and voltage during the scheduling process, and improve the safety and stability of the power grid.

[0087] For example, in general, thermal power plants can provide electricity continuously and stably, have strong peak-shaving capabilities, and the power generation process is highly controllable, and their stability is relatively high; hydropower plants can provide electricity relatively stably, can quickly increase or decrease output in a short period of time to provide good peak-shaving capabilities, and can adjust the power generation by adjusting the sluice gates and excitation. The power generation process is relatively controllable and their stability is relatively high; while photovoltaic power plants can only generate electricity when there is sunlight during the day, and the power generation is significantly reduced or even zero at night and on cloudy days. The peak-shaving capability is weak, the controllability is low, and their stability is poor; the output of wind power plants is greatly affected by wind speed. Unstable wind speed will cause large fluctuations in power generation. Wind speeds that are too low or too high will cause wind turbines to stop generating electricity. The peak-shaving capability is weak, the controllability is low, and their stability is poor.

[0088] As an example, if the current power system has a low system inertia, the grid stability requirement is high, and a power plant with higher stability is needed to meet the grid stability requirement. At this time, the target power plant type can be thermal power; if the current power system has a high system inertia and can cope with larger frequency fluctuations, the grid stability requirement is low, and thermal power, hydropower, and even photovoltaic and wind power can be used as target power plant types. After determining the target power plant type, the initial kilowatt-hour cost of each power plant that meets the target power plant type can be calculated, and the power generation scheduling plan with the lowest initial kilowatt-hour cost can be obtained through the pre-trained scheduling model. The power generation scheduling plan can include one or more working power plants involved in power generation, as well as the power generation of each working power plant.

[0089] For example, the target power plant types include thermal power, hydropower and photovoltaic power, and the power plants that meet the target power plant types include thermal power plant A, hydropower plant B and photovoltaic power plant C. Among them, when the load of thermal power plant A is 100%, the initial cost per kilowatt-hour is 0.43 yuan; when the load of thermal power plant A is 55%, the initial cost per kilowatt-hour is 0.465 yuan; when the load of thermal power plant A is 40%, the initial cost per kilowatt-hour is 0.49 yuan; the initial cost per kilowatt-hour of hydropower plant B is 0.47 yuan; the initial cost per kilowatt-hour of photovoltaic power plant C is 0.46 yuan. Therefore, if the load of thermal power plant A is 100%, the dispatching plan obtained by the dispatching model can be: all thermal power plant A is called to meet the power demand; if the load of thermal power plant A is less than 55%, the dispatching plan obtained by the dispatching model can be: call photovoltaic power plant C to meet the power demand; if the load of thermal power plant A is less than 40%, the dispatching plan obtained by the dispatching model can be: call hydropower plant B to meet the power demand. Taking the case where the load of thermal power plant A is less than 40% as an example, if hydropower plant B cannot meet the power demand, the dispatching plan obtained by the dispatching model can be: hydropower plant B generates electricity at the maximum power generation, and the remaining unmet power demand is allocated to photovoltaic power plant C.

[0090] Optionally, the first weight M can be calculated before or after determining the target power plant type, thereby introducing the impact of factors such as unit aging on the initial cost per kilowatt-hour, that is, unit aging will lead to a decrease in power generation, and then an increase in the carbon emission cost per kilowatt-hour, and an increase in the initial cost per kilowatt-hour. As a result, the overall performance and economy of the generator sets of each power plant that can be scheduled for power generation or each power plant that meets the target power plant type can be more accurately evaluated. Wherein, M = K × A + P × S, K is the carbon emission cost per kilowatt-hour, A is the capacity cost per kilowatt-hour, P is the performance coefficient of the generator set, and S is the power generation cost per kilowatt-hour in the initial cost per kilowatt-hour. Wherein, the generator set performance parameter P can be set based on the percentage of the key parameters of the performance test deviating from the standard value, and the key parameters may include parameters such as full illumination power generation or net output.

[0091] In the first weight M, K×A can reflect the carbon footprint and economy of the equipment. The higher the initial investment and carbon footprint of the equipment, the greater the value of K×A; P×S reflects the performance status and overall economy of the generator set. For a generator set with good performance, the P value is high, the S value is low, and the P×S value is small. For a generator set with poor performance, the P value is low and the S value is high. If the decrease in the P value is less than the increase in the S value, the P×S value will increase. Specifically, in the case of aging of the unit, the decrease in P is likely to lead to an increase in the value of P×S, and then the increase in the first weight M can reflect the disadvantages of the aging unit in terms of economy and environmental protection; in the case of a decrease in the power generation of the unit, S may increase, resulting in an increase in P×S, and then the increase in the first weight M can reflect the disadvantages of the unit in terms of economy; in the case of poor emission reduction performance of the unit, the carbon emission cost per kilowatt-hour M increases, K×A will increase, and then the increase in the first weight M can reflect the disadvantages of the unit in terms of environmental protection.

[0092] In some embodiments, after determining the target power plant type, it is possible to calculate the first weight of each power plant that meets the target power plant type, thereby reducing the amount of calculation and improving the calculation speed.

[0093] Therefore, by calculating the first weight, the comprehensive power generation cost of the power plant can be obtained by comprehensively considering four factors: environmental protection factors, capacity cost, power generation cost and performance.

[0094] Optionally, a power generation scheduling plan may be obtained through a pre-trained scheduling model based on the first weight of each power plant, the emergency level of power demand of the power grid, the initial cost per kilowatt-hour of each power plant, and the stability parameter of each power plant.

[0095] Exemplarily, three emergency levels of power grid demand can be divided, wherein the first emergency level can indicate that the power grid urgently needs power, the second emergency level can indicate that the power grid needs power but is not urgent, and the third emergency level can indicate that the power grid does not need the power plant to provide additional power generation. If the emergency level of power grid demand is the first level, the power generation scheduling plan can be: call the power plant that can quickly provide the required power generation among the power plants that meet the target power plant type; if the emergency level of power grid demand is the second level, the power generation scheduling plan can be: call the power plant or a combination of power plants with the lowest initial kilowatt-hour cost among the power plants that meet the target power plant type; if the emergency level of power grid demand is the third level, the power generation scheduling plan can be: optimize the currently executed power generation scheduling plan according to the first weight, and replace the power plant with a higher first weight among the power plants participating in power generation with a power plant with a lower first weight among the power plants that meet the target power plant type.

[0096] Therefore, according to the different urgency of power demand in the power grid, a power generation scheduling plan can be quickly provided in an emergency by using a method with less computational effort, and a low-cost power generation scheduling plan can be provided in a non-emergency by using a method with more computational effort.

[0097] Optionally, the dispatch model may also consider the heat consumption requirement of the power grid when generating the power generation dispatch plan, so as to prevent the heat consumption of the thermal power plants involved in power generation from exceeding the heat consumption range allowed by the power grid.

[0098] Therefore, in the embodiment of the present application, first, the production factor data of each power plant in the power system is obtained; then, based on the production factor data, the initial cost per kilowatt-hour of each power plant is determined through a pre-established production factor model; then, based on the production factor data, the stability parameters of each power plant are determined; finally, according to the initial cost per kilowatt-hour and stability parameters of each power plant, a power generation scheduling plan is obtained through a pre-trained scheduling model. Therefore, for multiple power plants in the power system, the production factor data can be comprehensively considered, and from the two dimensions of initial cost per kilowatt-hour and stability, a low-cost power generation scheduling plan that can meet the stability requirements can be obtained to reduce the power generation cost.

[0099] In some other embodiments provided in the present application, after executing step S104, the following steps may also be performed: Figure 2 Steps shown:

[0100] S201: Based on the scheduling feasibility model, determine whether the power generation scheduling plan is feasible. If so, execute step S202; if not, execute step S205.

[0101] Specifically, the scheduling feasibility model can be obtained based on the scheduling history and scheduling failure rate of the virtual power plant. Through the scheduling feasibility model, the failure rate of executing the power generation scheduling plan under the current situation can be obtained. If the failure rate is higher than the preset threshold, the power generation scheduling plan can be considered infeasible. Among them, the virtual power plant (Virtual PowerPlant, VPP) is a system that integrates distributed energy resources such as thermal power plants, hydropower plants, photovoltaic power plants and wind power plants through advanced communication and control technologies, so that they can operate like traditional power plants.

[0102] S202: Execute the power generation scheduling plan.

[0103] Specifically, the power generation of each working power plant can be controlled through the real-time production factor data fed back by the working power plant, so that each working power plant generates electricity according to the power generation allocated in the power generation scheduling plan. In this way, the efficient operation of the power system can be achieved, ensuring the stability and economy of power supply. Through the feedback of real-time data, the scheduling model can also adjust the power generation plan of each power plant in time to cope with changes in grid load and various emergencies, thereby ensuring the safe and reliable operation of the entire power system.

[0104] Taking a hydropower plant as an example, based on real-time production factor data such as inflow and reservoir water level, when the inflow is too large, the control model obtained through deep learning on the power plant side can be used to control the flood discharge of the hydropower plant so that its power generation meets the power generation scheduling plan and the water level does not exceed the dam.

[0105] See Table 2, which is a table of daily water level and power generation conditions of a hydropower plant provided in an embodiment of the present application:

[0106] Table 2

[0107]

[0108] By collecting the data in Table 2, the relationship between the monthly average reservoir water level, the amount of water entering the reservoir, the amount of water leaving the reservoir, the amount of flood discharge, and the amount of water for power generation can be obtained. Specifically, see Table 3, which shows the monthly average water level and power generation of a hydropower plant provided in an embodiment of the present application:

[0109] Table 3

[0110]

[0111] When the water head is constant, the power generation is proportional to the amount of water used for power generation. For example, the data provided in Tables 2 and 3 can be used as training data for deep learning training to obtain a control model that can obtain the flood discharge amount based on the water level, water inflow (i.e., water inflow) and power generation. Thus, through the control model, the flood discharge amount can be obtained based on the current water level and the power generation in the power generation scheduling plan, so that the power generation of the hydropower plant can be matched with the power generation in the power generation scheduling plan by controlling the flood discharge amount.

[0112] Optionally, based on Table 3, the average monthly reservoir water level data for many years can also be analyzed, and according to the clustering characteristics of the quarterly water levels, a quarterly water level table as shown in Table 4 can be obtained, so as to comprehensively consider the utilization efficiency of water resources and reduce the waste of water resources in the process of determining the power generation scheduling plan.

[0113] Table 4

[0114] month Water level m Median water level m January-March 250-–260 255 April-June 210-250 230 July-September 250-260 255 October-December 258-262 260

[0115] S203: Based on the real-time production factor data fed back by each working power plant participating in power generation in the power generation scheduling plan, the real-time electricity cost of each working power plant is determined through the production factor model.

[0116] Specifically, during the process of the working power plant executing the power generation instruction, the real-time production factor data can be fed back to the production factor model on the power grid side, and the production factor model can determine the real-time electricity cost of each working power plant based on the real-time production factor data.

[0117] S204: Determine whether there is a working power plant whose real-time kilowatt-hour cost increases by more than a preset threshold compared with the initial kilowatt-hour cost. If so, execute step S205; if not, execute step S203.

[0118] As an example, a threshold value of increase can be set in advance, for example, set to 5%. Thus, if the increase of the real-time kilowatt-hour cost compared to the initial kilowatt-hour cost exceeds 5%, it can be considered that the real-time kilowatt-hour cost has changed significantly compared to the initial kilowatt-hour cost, and there may be power plants with lower kilowatt-hour costs in the power system. It is necessary to execute step S205 to redetermine the power generation scheduling plan; if the increase of the real-time kilowatt-hour cost compared to the initial kilowatt-hour cost does not exceed 5%, it can be considered that the change of the real-time kilowatt-hour cost compared to the initial kilowatt-hour cost is small, and the current working power plant is most likely still the power plant with the lowest kilowatt-hour cost in the power system. There is no need to adjust the power generation scheduling plan, and step S203 can be executed to continue monitoring the real-time kilowatt-hour cost.

[0119] S205: Re-determine the power generation scheduling plan.

[0120] Specifically, the schemes of S101 to S104 may be re-executed to redetermine the power generation capacity scheduling scheme.

[0121] The power generation dispatching method of the power system provided in the present application can be used for a power system including a power grid and multiple power plants. Specifically, see Figure 3 , this figure is an interactive diagram of the power generation scheduling process of an electric power system provided in an embodiment of the present application, and the electric power system includes a photovoltaic power plant, a hydropower plant, a thermal power plant and a power grid.

[0122] On the photovoltaic power plant side, the stability parameters of the photovoltaic power plant can be calculated based on the obtained production factor data such as illuminance, and its power generation can be calculated through the production factor model, thereby determining the initial cost per kilowatt-hour of the photovoltaic power plant and the available power generation plan; on the hydropower plant side, the stability parameters of the hydropower plant can be calculated based on the obtained production factor data such as water inflow and daily water level, and the constraints between the inflow water volume, flood discharge volume and power generation water volume can be determined through the production factor model, and its power generation can be calculated, thereby determining the initial cost per kilowatt-hour of the hydropower plant and the available power generation plan; on the thermal power plant side, the stability parameters of the thermal power plant can be calculated based on the obtained production factor data such as fuel calorific value and heat consumption, and its power generation can be calculated through the production factor model, thereby determining the initial cost per kilowatt-hour of the thermal power plant and the available power generation plan; on the power grid side, the stability of the power grid can be calculated to determine the stability demand of the power grid, and based on the pre-trained scheduling model, on the premise of meeting the stability demand of the power grid, combined with the initial cost per kilowatt-hour and the available power generation plan of each power plant, the power generation scheduling plan is obtained from the strategy library in the scheduling model.

[0123] Each power plant can apply to the power grid for trading electricity and electricity prices based on the power generation scheduling plan issued by the power grid side; the power grid side collects the application data of each power plant, and based on the real-time production factor data of each power plant, determines the real-time cost per kilowatt-hour of each power plant through the production factor model; if there is a power plant whose real-time cost per kilowatt-hour increases by more than a preset threshold compared with the initial cost per kilowatt-hour, the power generation scheduling plan is re-determined, and a power generation scheduling instruction based on the new power generation scheduling plan is issued to each power plant, and each power plant operates its generator set in response to the power generation scheduling instruction.

[0124] See also Figure 4 , this figure is a schematic diagram of a power generation scheduling device for an electric power system provided in an embodiment of the present application, the device includes: an acquisition module 401, a cost determination module 402, a stability determination module 403 and a scheme output module 404.

[0125] The acquisition module 401 is used to acquire the production factor data of each power plant in the power system; the production factor data includes at least one of illuminance, heat consumption, fuel consumption, water flow, water level and wind speed;

[0126] The cost determination module 402 is used to determine the initial cost per kilowatt-hour of each power plant based on the production factor data and through a pre-established production factor model; the initial cost per kilowatt-hour includes the power generation cost per kilowatt-hour and the carbon emission cost per kilowatt-hour;

[0127] The stability determination module 403 is used to determine the stability parameters of each power plant based on the production factor data; the stability parameters include frequency, system inertia and voltage;

[0128] The plan output module 404 is used to obtain a power generation scheduling plan according to the initial cost per kilowatt-hour of each power plant and the stability parameters of each power plant through a pre-trained scheduling model.

[0129] Therefore, for multiple power plants in the power system, the production factor data can be comprehensively considered, starting from the two dimensions of initial cost per kilowatt-hour and stability, to obtain a low-cost power generation scheduling plan that can meet the stability requirements and reduce the power generation cost.

[0130] Optionally, the cost determination module 402 is specifically used to: obtain a production vector value based on production factor data; the production vector includes: a SOLAR vector established based on illuminance, month, reactive power, power plant efficiency, spare capacity, and monthly power generation; a COALPOWER vector established based on heat consumption, fuel consumption, fuel price, load rate, month, rotation capacity, and monthly power generation; a HYDRO POWER vector established based on water head, water inflow, water abandonment rate, rotation capacity, and monthly power generation; and a WIND POWER vector established based on wind speed, wind time, wind abandonment rate, and monthly power generation; based on the production vector value, the initial cost per kilowatt-hour of each power plant is determined separately through a pre-established production factor model.

[0131] Optionally, the cost determination module 402 includes a kilowatt-hour power generation cost determination unit and an initial kilowatt-hour power generation cost calculation unit, wherein the kilowatt-hour power generation cost determination unit is used to determine the kilowatt-hour power generation cost of each power plant based on production factor data and a pre-established production factor model; the initial kilowatt-hour power generation cost calculation unit is used to calculate the sum of the kilowatt-hour power generation cost and the kilowatt-hour carbon emission cost of each power plant to obtain the initial kilowatt-hour power generation cost of each power plant; the kilowatt-hour carbon emission cost is obtained based on the full life cycle carbon footprint of each power plant; the full life cycle carbon footprint includes the total carbon emissions generated by the production of power generation equipment and the total carbon emissions in the power generation process.

[0132] Optionally, the unit for determining the power generation cost per kilowatt-hour is specifically used to: determine the power generation of each power plant in the target time period based on the production factor data through a pre-established production factor model; determine the power generation cost per kilowatt-hour of each power plant based on the power generation of each power plant and the power generation cost data of each power plant through the production factor model.

[0133] Optionally, in another power system power generation dispatching device provided in an embodiment of the present application, it also includes a weight calculation module, which is used to calculate the capacity cost per kilowatt-hour of each power plant based on the power generation of each power plant in the target period and the capacity cost of each power plant; calculate the first weight according to the initial cost per kilowatt-hour of each power plant, the capacity cost per kilowatt-hour and the performance coefficient of the generator set; the first weight is: the sum of the product of the carbon emission cost per kilowatt-hour and the capacity cost per kilowatt-hour and the product of the performance coefficient of the generator set and the power generation cost per kilowatt-hour; the plan output module 404 is specifically used to: based on the first weight of each power plant, the emergency level of power demand of the power grid, the initial cost per kilowatt-hour of each power plant and the stability parameters of each power plant, obtain the power generation scheduling plan through a pre-trained scheduling model.

[0134] Optionally, the plan output module 404 is specifically used to: determine the target power plant type that meets the grid stability requirements based on the grid stability requirements and the stability parameters of each power plant; the target power plant type is selected from at least one of thermal power, hydropower, photovoltaic power and wind power; based on the initial kilowatt-hour cost of each power plant that meets the target power plant type, obtain the power generation scheduling plan through a pre-trained scheduling model; the power generation scheduling plan has the lowest initial kilowatt-hour cost.

[0135] Optionally, in another power system power generation scheduling device provided in an embodiment of the present application, it also includes: a feasibility determination module, which is used to determine the feasibility of the power generation scheduling plan based on the scheduling feasibility model; the scheduling feasibility model is obtained through virtual power plant scheduling history and scheduling failure rate training; if the power generation scheduling plan is feasible, the power generation scheduling plan is executed; if the power generation scheduling plan is not feasible, the power generation scheduling plan is re-determined.

[0136] Optionally, in another power generation scheduling device of an electric power system provided in an embodiment of the present application, it also includes: a cost control module, which is used to determine the real-time kilowatt-hour cost of each working power plant through a production factor model based on the real-time production factor data fed back by each working power plant participating in power generation in the power generation scheduling plan; if there is a working power plant whose real-time kilowatt-hour cost increases by more than a preset threshold compared to the initial kilowatt-hour cost, the power generation scheduling plan is re-determined.

[0137] Optionally, in another power system power generation dispatching device provided in an embodiment of the present application, it also includes: a power generation control module, which is used for each working power plant participating in power generation in the power generation dispatching plan to control the power generation of each working power plant according to real-time production factor data, so that the power generation of each working power plant fits the power generation in the power generation dispatching plan.

[0138] See also Figure 5 , this figure is a structural diagram of a power generation dispatching device of an electric power system provided in an embodiment of the present application, and the device includes: a memory 501 and a processor 502.

[0139] Memory 501: used to store program codes and transmit the program codes to the processor.

[0140] Processor 502: used to execute the steps of the power generation scheduling method of the above power system according to the instructions in the program code.

[0141] In addition, the present application also provides a computer-readable storage medium, which stores computer instructions. When the computer instructions are executed on the power generation dispatching equipment of the power system, the power generation dispatching equipment of the power system executes the steps of the above-mentioned power generation dispatching method of the power system.

[0142] It should be noted that each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device and system embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments. The device and system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components indicated as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0143] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A power generation dispatching method for a power system, characterized in that: The method comprises: Acquire production factor data of each power plant in the power system; the production factor data includes at least one of illuminance, heat consumption, fuel consumption, water flow, water level and wind speed; Based on the production factor data, the initial electricity cost of each power plant is determined through a pre-established production factor model; the initial electricity cost includes electricity generation cost and electricity carbon emission cost; Based on the production factor data, stability parameters of each power plant are determined respectively; the stability parameters include frequency, system inertia and voltage; According to the initial LCOE of each power plant and the stability parameters of each power plant, a power generation scheduling plan is obtained through a pre-trained scheduling model.

2. The method according to claim 1, characterized in that: Based on the production factor data, the initial electricity cost of each power plant is determined through a pre-established production factor model, including: Based on the production factor data, a production vector value is obtained; the production vector includes: a SOLAR vector established based on illuminance, month, reactive power, power plant efficiency, spare capacity, and monthly power generation; a COAL POWER vector established based on heat consumption, fuel consumption, fuel price, load rate, month, rotation capacity, and monthly power generation; a HYDRO POWER vector established based on water head, water inflow, water abandonment rate, rotation capacity, and monthly power generation; and a WIND POWER vector established based on wind speed, wind time, wind abandonment rate, and monthly power generation; Based on the production vector value, the initial cost per kilowatt-hour of each power plant is determined through a pre-established production factor model.

3. The method according to claim 1, characterized in that Based on the production factor data, the initial electricity cost of each power plant is determined through a pre-established production factor model, including: Based on the production factor data, the power generation cost per kilowatt-hour of each power plant is determined through a pre-established production factor model; The sum of the power generation cost per kilowatt-hour and the carbon emission cost per kilowatt-hour of each power plant is calculated to obtain the initial power generation cost per kilowatt-hour of each power plant; the carbon emission cost per kilowatt-hour is obtained based on the full life cycle carbon footprint of each power plant; the full life cycle carbon footprint includes the total carbon emissions generated by the production of power generation equipment and the total carbon emissions in the power generation process.

4. The method according to claim 3, characterized in that Based on the production factor data, the power generation cost per kilowatt-hour of each power plant is determined through a pre-established production factor model, including: Based on the production factor data, the power generation of each power plant in the target period is determined by using a pre-established production factor model; Based on the power generation of each power plant and the power generation cost data of each power plant, the power generation cost per kilowatt-hour of each power plant is determined respectively through the production factor model.

5. The method according to claim 4, characterized in that Before obtaining the power generation scheduling plan based on the initial KWh cost of each power plant and the stability parameters of each power plant through a pre-trained scheduling model, the method further includes: Calculate the kilowatt-hour capacity cost of each power plant based on the power generation of each power plant in the target period and the capacity cost of each power plant; Calculate a first weight according to the initial kilowatt-hour cost, kilowatt-hour capacity cost and generator set performance coefficient of each power plant; the first weight is the sum of the product of the kilowatt-hour carbon emission cost and the kilowatt-hour capacity cost and the product of the generator set performance coefficient and the kilowatt-hour power generation cost; The power generation scheduling scheme is obtained according to the initial kilowatt-hour cost of each power plant and the stability parameters of each power plant through a pre-trained scheduling model, including: Based on the first weight of each power plant, the emergency level of power demand of the power grid, the initial cost per kilowatt-hour of each power plant, and the stability parameters of each power plant, a power generation scheduling plan is obtained through a pre-trained scheduling model.

6. The method according to claim 1, characterized in that The power generation scheduling scheme is obtained according to the initial kilowatt-hour cost of each power plant and the stability parameters of each power plant through a pre-trained scheduling model, including: According to the grid stability requirement and the stability parameters of each power plant, determining the target power plant type that meets the grid stability requirement; the target power plant type is selected from at least one of thermal power, hydropower, photovoltaic power and wind power; Based on the initial kilowatt-hour costs of each power plant that meets the target power plant type, a power generation scheduling plan is obtained through a pre-trained scheduling model; the power generation scheduling plan is a scheduling plan with the lowest initial kilowatt-hour cost.

7. The method according to claim 1, characterized in that After obtaining the power generation scheduling plan according to the initial KWh cost of each power plant and the stability parameters of each power plant through the pre-trained scheduling model, the method further includes: Based on a scheduling feasibility model, determining the feasibility of the power generation scheduling plan; the scheduling feasibility model is obtained by training the virtual power plant scheduling history and scheduling failure rate; If the power generation scheduling plan is feasible, the power generation scheduling plan is executed; if the power generation scheduling plan is not feasible, the power generation scheduling plan is re-determined.

8. The method according to claim 7, characterized in that After executing the power generation scheduling plan, the method further includes: Based on the real-time production factor data fed back by each working power plant participating in power generation in the power generation scheduling plan, the real-time electricity cost of each working power plant is determined through the production factor model; If there is a working power plant whose real-time kilowatt-hour cost increases beyond the preset threshold compared with the initial kilowatt-hour cost, the power generation scheduling plan will be re-determined.

9. The method according to claim 7, characterized in that: After executing the power generation scheduling plan, the method further includes: Each working power plant participating in power generation in the power generation scheduling scheme controls the power generation of each working power plant according to real-time production factor data, so that the power generation of each working power plant fits the power generation in the power generation scheduling scheme.

10. A power generation dispatching device for a power system, characterized in that: The device comprises: an acquisition module, a cost determination module, a stability determination module and a solution output module; The acquisition module is used to acquire production factor data of each power plant in the power system; the production factor data includes at least one of illuminance, heat consumption, fuel consumption, water flow, water level and wind speed; The cost determination module is used to determine the initial electricity cost per kilowatt-hour of each power plant based on the production factor data and through a pre-established production factor model; the initial electricity cost per kilowatt-hour includes the electricity generation cost per kilowatt-hour and the carbon emission cost per kilowatt-hour; The stability determination module is used to determine the stability parameters of each power plant based on the production factor data; the stability parameters include frequency, system inertia and voltage; The scheme output module is used to obtain a power generation scheduling scheme according to the initial cost per kilowatt-hour of each power plant and the stability parameters of each power plant through a pre-trained scheduling model.

11. A power generation dispatching device for a power system, characterized in that: The device comprises: a memory and a processor; The memory is used to store program codes and transmit the program codes to the processor; The processor is used to execute the steps of the power generation scheduling method of the power system according to any one of claims 1-9 according to the program code.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program. When the computer program runs on a power generation dispatching device of a power system, the power generation dispatching device of the power system executes the steps of a power generation dispatching method of a power system as described in any one of claims 1-9.

Images