CN117277439B - Power grid dispatching method, device, equipment and storage medium - Google Patents

Power grid dispatching method, device, equipment and storage medium Download PDF

Info

Publication number
CN117277439B
CN117277439B CN202311246873.6A CN202311246873A CN117277439B CN 117277439 B CN117277439 B CN 117277439B CN 202311246873 A CN202311246873 A CN 202311246873A CN 117277439 B CN117277439 B CN 117277439B
Authority
CN
China
Prior art keywords
power
data
prediction
time point
generator set
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202311246873.6A
Other languages
Chinese (zh)
Other versions
CN117277439A (en
Inventor
夏伟
成勇
范晓云
钟博宇
虞文斌
李妙
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Contemporary Amperex Technology Co Ltd
Original Assignee
Contemporary Amperex Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Contemporary Amperex Technology Co Ltd filed Critical Contemporary Amperex Technology Co Ltd
Priority to CN202311246873.6A priority Critical patent/CN117277439B/en
Publication of CN117277439A publication Critical patent/CN117277439A/en
Application granted granted Critical
Publication of CN117277439B publication Critical patent/CN117277439B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Electricity, gas or water supply
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/003—Load forecast, e.g. methods or systems for forecasting future load demand
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/004—Generation forecast, e.g. methods or systems for forecasting future energy generation
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/04—Circuit arrangements for ac mains or ac distribution networks for connecting networks of the same frequency but supplied from different sources
    • H02J3/06—Controlling transfer of power between connected networks; Controlling sharing of load between connected networks
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/24—Arrangements for preventing or reducing oscillations of power in networks
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/28—Arrangements for balancing of the load in a network by storage of energy
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
    • H02J3/46—Controlling of the sharing of output between the generators, converters, or transformers
    • H02J3/466—Scheduling the operation of the generators, e.g. connecting or disconnecting generators to meet a given demand
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
    • H02J2203/10—Power transmission or distribution systems management focussing at grid-level, e.g. load flow analysis, node profile computation, meshed network optimisation, active network management or spinning reserve management
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
    • H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
    • H02J2300/20—The dispersed energy generation being of renewable origin
    • H02J2300/22—The renewable source being solar energy
    • H02J2300/24—The renewable source being solar energy of photovoltaic origin
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
    • H02J2300/20—The dispersed energy generation being of renewable origin
    • H02J2300/28—The renewable source being wind energy

Abstract

The application relates to a power grid dispatching method, a device, equipment and a storage medium, wherein the method comprises the following steps: the method comprises the steps of obtaining power load prediction data of a target area at a plurality of prediction time points, and obtaining power generation power prediction data of each wind-light generator set of the target area at the plurality of prediction time points. Further, grid scheduling is performed according to the power load prediction data of the plurality of prediction time points and the power generation power prediction data of the plurality of prediction time points, so that power generation power scheduling data of each power generation unit in the target area at each prediction time point is obtained. According to the embodiment of the application, the reference data of the power grid dispatching are more comprehensive, and the power grid dispatching of a plurality of prediction time points can be synchronously performed, so that the accuracy and the dispatching efficiency of the power grid dispatching are improved.

Description

Power grid dispatching method, device, equipment and storage medium
Technical Field
The present disclosure relates to the field of power systems, and in particular, to a power grid dispatching method, device, apparatus, and storage medium.
Background
Considering the high storage cost of the power resources, power generation is usually performed on demand, namely, each generator set is controlled to generate power according to the power grid load.
In the related art, for each time point to be predicted, power grid dispatching is performed according to power grid load prediction data of the time point to be predicted. But the accuracy of grid scheduling in the related art is low.
Disclosure of Invention
In view of the above problems, the present application provides a power grid dispatching method, device, equipment and storage medium, which can solve the problem of lower accuracy of power grid dispatching in the related art.
In a first aspect, the present application provides a power grid dispatching method, including:
acquiring power load prediction data of a target area at a plurality of prediction time points;
acquiring power generation power prediction data of each wind-solar generator set in a target area at a plurality of prediction time points;
carrying out power grid dispatching according to the power load prediction data of the plurality of prediction time points and the power generation power prediction data of the plurality of prediction time points to obtain power generation power dispatching data of each power generation unit in the target area at each prediction time point; the power generation scheduling data of each generator set at each prediction time point is used for controlling the power generation state of each generator set at each prediction time point.
In the technical scheme of the embodiment of the application, compared with the power grid load prediction data in the power grid dispatching process in the related technology, the embodiment of the application further considers the power generation power prediction data of each wind-solar generator set in the target area at a plurality of prediction time points on the basis of the power load prediction data, and the reference data is more comprehensive, so that the accuracy of power grid dispatching is improved. In addition, compared with a single-step scheduling mode in the related art, in the embodiment of the application, by performing power grid scheduling according to the power load prediction data of the target area at a plurality of prediction time points and the power generation prediction data of each wind-light generator set of the target area at a plurality of prediction time points, the power grid scheduling of each generator set of the target area at a plurality of prediction time points can be synchronously realized, the power grid scheduling time can be saved, more valuable data references can be brought to a scheduling center, and therefore the scheduling efficiency of power grid scheduling is improved.
In some embodiments, performing power grid scheduling according to power load prediction data of a plurality of prediction time points and power generation prediction data of a plurality of prediction time points to obtain power generation scheduling data of each power generation unit of a target area at each prediction time point, including:
according to the power generation power prediction data of each wind-light generator set at a plurality of prediction time points, respectively determining first power constraint conditions of each wind-light generator set at the plurality of prediction time points;
constructing a power grid power flow constraint condition and a multi-objective function according to the power load prediction data of a plurality of prediction time points;
and carrying out optimization solving processing on the multi-objective function according to the first power constraint condition of each wind-solar generator set at a plurality of prediction time points, the second power constraint condition of other generator sets in the target area at a plurality of prediction time points and the power grid trend constraint condition to obtain the power generation power scheduling data of each generator set at each prediction time point.
According to the technical scheme, the method for optimizing and solving the multi-objective function according to the first power constraint condition of each wind-light generator set at a plurality of prediction time points, the second power constraint condition of other generator sets in a target area at a plurality of prediction time points and the power grid power flow constraint condition is achieved by determining the first power constraint condition according to the power generation power prediction data of each wind-light generator set at each prediction time point, constructing the power grid power flow constraint condition and the multi-objective function according to the power load prediction data of each prediction time point, and obtaining the power generation power scheduling data of each generator set which is closer to actual power generation at a plurality of prediction time points on the premise that the power grid reliably operates, so that the accuracy and reliability of power grid scheduling can be further improved.
In some embodiments, constructing a multi-objective function from power load prediction data for a plurality of prediction time points includes:
determining a power gain objective function of a target region at each prediction time point and a power deviation objective function of the target region between the power load and the generated power at each prediction time point according to the power load prediction data of the plurality of prediction time points;
and constructing a multi-objective function according to the power gain objective function of the target area at each prediction time point and the power deviation objective function of the target area at each prediction time point.
According to the technical scheme, a multi-objective function mode is constructed according to the power load prediction data of a plurality of prediction time points and the power gain objective function and the power deviation objective function determined by the power load of the target region at each prediction time point, so that a power grid dispatching scheme with maximized power gain and minimized power deviation can be conveniently realized, and the accuracy and rationality of power grid dispatching can be further improved.
In some embodiments, determining a power gain objective function for the target region at each predicted time point based on the power load prediction data for the plurality of predicted time points includes:
For each prediction time point, determining the power grid electricity selling income of the target area at the prediction time point according to the power load prediction data and the power grid electricity selling price at the prediction time point;
and determining an electric power gain objective function of the target region at the predicted time point according to the electric power selling income of the electric power network, the subsidy income of the target region at the predicted time point, the electricity purchasing cost and the pollution cost, so that an electric power dispatching scheme with the maximized electric power gain can be realized.
In some embodiments, determining a power deviation objective function between the power load and the generated power of the target region at each predicted point in time from the power load prediction data at a plurality of predicted points in time includes:
and for each prediction time point, determining a power deviation objective function of the target area at the prediction time point according to the power load prediction data of the prediction time point and the power generation power scheduling data of each generator set at the prediction time point so as to realize a power grid scheduling scheme with minimized power deviation.
In some embodiments, constructing the grid power flow constraint from the power load prediction data at a plurality of predicted time points includes:
for each prediction time point, determining a first power flow of the power load of the target area at the prediction time point to the power grid line according to the power load prediction data of the prediction time point and a power distribution coefficient of the preset power load to the power grid line;
Determining a second tide of each generator set to the power grid line at the predicted time point according to the power generation power scheduling data of each generator set at the predicted time point and the corresponding power transmission distribution coefficient;
and determining a power grid power flow constraint condition of the target region at a predicted time point according to the first power flow and the second power flow.
According to the technical scheme, the power grid power flow constraint condition of the target region at the predicted time point is determined according to the determined first power flow and second power flow, so that power generation power dispatching data under the premise of safe and stable operation of the power grid can be obtained when the multi-objective function is optimized and solved based on the power grid power flow constraint condition, and the reliability and stability of power grid dispatching can be further improved.
In some embodiments, determining a first power constraint condition of each wind-light generator set at a plurality of prediction time points according to the generated power prediction data of each wind-light generator set at a plurality of prediction time points respectively includes:
for each wind-light generating set at each prediction time point, taking the power generation prediction data of the wind-light generating set at the prediction time point as the maximum power upper limit of the wind-light generating set at the prediction time point;
And taking the preset power threshold value as the minimum power lower limit of the wind-solar generator set at the predicted time point.
In the technical scheme of the embodiment of the application, constraint conditions such as the maximum power upper limit of the wind-light generator set are dynamically updated by taking the power generation power prediction data of the wind-light generator set at the prediction time point as the maximum power upper limit of the wind-light generator set at the prediction time point, so that the power generation power scheduling data of the wind-light generator set obtained when the multi-objective function is optimized and solved based on the dynamic constraint conditions can be more close to the actual power generation power of the wind-light generator set, and the actual power grid scheduling requirement can be met.
In some embodiments, if the generator set comprises a thermal generator set, the second power constraints of the thermal generator set at each predicted point in time comprise: the power upper limit and the power lower limit of the power generation power scheduling data of the thermal generator set at the predicted time point and the power upper limit and the power lower limit of the power generation power change data of the thermal generator set in unit time are convenient for the power generation power scheduling data of the thermal generator set obtained when the multi-objective function is optimized and solved based on the second power constraint condition of the thermal generator set to be closer to the actual power generation power of the thermal generator set.
In some embodiments, if the generator set includes an energy storage set, the second power constraint of the energy storage set at each predicted point in time includes: the power upper limit and the lower limit of the power scheduling data of the energy storage unit at the prediction time point and the SOC upper limit and the lower limit of the SOC data of the energy storage unit at the prediction time point are convenient for the power scheduling data of the energy storage unit obtained when the multi-objective function is optimized and solved based on the second power constraint condition of the energy storage unit can be closer to the actual power of the energy storage unit.
In some embodiments, obtaining power load prediction data for a target region at a plurality of predicted time points includes:
and inputting the time sequence data related to the power load of the target area into a preset power load prediction model to obtain power load prediction data of the target area, which is output by the preset power load prediction model, at a plurality of prediction time points.
According to the technical scheme, the time sequence data related to the power load of the target area is input into the preset power load prediction model, so that the power load prediction data of the target area at a plurality of prediction time points can be obtained synchronously, and the prediction efficiency of the power load is high.
In some embodiments, the timing data includes at least two of: weather data of a target area, load data of the target area, electricity price data of the target area, policy data of the target area and economic index data of the target area; wherein the policy data is used to indicate an impact on the power demand.
In the technical scheme of the embodiment of the application, on the basis of weather data and load data, power load prediction is further performed by combining electricity price data, policy data, economic index data and the like. Therefore, the reference data for power load prediction in the embodiment of the application is more comprehensive, so that the accuracy of power load prediction is improved.
In some embodiments, obtaining power generation prediction data for each wind-solar power generator set in a target area at a plurality of prediction time points includes:
for each wind-light generator set, inputting time sequence data and non-time sequence data related to the power generated by the wind-light generator set into a preset power prediction model to obtain power generation prediction data of the wind-light generator set output by the preset power prediction model at a plurality of prediction time points.
According to the technical scheme, the power generation power prediction data of the wind-light generator set at a plurality of prediction time points can be obtained synchronously by inputting the time sequence data and the non-time sequence data related to the power generation power of the wind-light generator set into the preset power prediction model. Therefore, in the embodiment of the application, the reference data is more comprehensive by performing power prediction based on the time sequence data and the non-time sequence data related to the power generated by the wind-solar generator set, so that the accuracy of power prediction is improved, and the power prediction efficiency is higher.
In some embodiments, non-time series data related to wind turbine generator set generation power includes: status data of the wind-light generator set and/or constraint data of the wind-light generator set; the state data are used for indicating whether the wind-solar generator set operates or not; the constraint data is used for indicating the output power threshold range of the wind-solar generator set;
the time sequence data includes: weather data of the wind-light generator set and/or operation data of the wind-light generator set.
In the technical scheme of the embodiment of the application, on the basis of the time sequence data, the non-time sequence data such as constraint data and/or state data are further combined to conduct power prediction, and the reference data for power prediction are more comprehensive, so that the accuracy of power prediction is further improved.
In a second aspect, the present application provides a power grid dispatching apparatus, the apparatus comprising:
the first acquisition module is used for acquiring power load prediction data of the target area at a plurality of prediction time points;
the second acquisition module is used for acquiring the power generation power prediction data of each wind-solar generator set in the target area at a plurality of prediction time points;
the scheduling module is used for carrying out power grid scheduling according to the power load prediction data of the plurality of prediction time points and the power generation power prediction data of the plurality of prediction time points to obtain power generation power scheduling data of each power generation unit in the target area at each prediction time point; the power generation scheduling data of each generator set at each prediction time point is used for controlling the power generation state of each generator set at each prediction time point.
In a third aspect, the present application provides a computer device, including a memory and a processor, where the memory stores a computer program, and the processor implements the steps in the above-mentioned embodiments of the power grid scheduling method when executing the computer program.
In a fourth aspect, the present application provides a computer readable storage medium having a computer program stored thereon, which when executed by a processor, implements the steps of the above-described embodiments of a power grid scheduling method.
In a fifth aspect, the present application provides a computer program product comprising a computer program which, when executed by a processor, implements the steps of the above-described power grid scheduling method embodiments.
The foregoing description is only an overview of the technical solutions of the present application, and may be implemented according to the content of the specification in order to make the technical means of the present application more clearly understood, and in order to make the above-mentioned and other objects, features and advantages of the present application more clearly understood, the following detailed description of the present application will be given.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the application. Also, like reference numerals are used to designate like parts throughout the accompanying drawings. In the drawings:
Fig. 1 is a schematic structural diagram of a power grid provided in an embodiment of the present application;
fig. 2 is a flow chart of a power grid dispatching method according to some embodiments of the present application;
fig. 3 is a flow chart of a power grid dispatching method according to other embodiments of the present application;
FIG. 4 is a flowchart illustrating a method for constructing a multi-objective function according to some embodiments of the present disclosure;
fig. 5 is a flow chart of a method for constructing a power grid power flow constraint condition according to some embodiments of the present application;
fig. 6 is a schematic structural diagram of a power grid dispatching framework provided in some embodiments of the present application;
FIG. 7 is a schematic diagram of dynamic constraints provided by embodiments of the present application;
fig. 8 is a schematic structural diagram of a power grid dispatching device according to some embodiments of the present application;
fig. 9 is a schematic structural diagram of a power grid dispatching device according to other embodiments of the present disclosure;
fig. 10 is a schematic structural diagram of a computer device in some embodiments of the present application.
Detailed Description
Embodiments of the technical solutions of the present application will be described in detail below with reference to the accompanying drawings. The following examples are only for more clearly illustrating the technical solutions of the present application, and thus are only examples, and are not intended to limit the scope of protection of the present application.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the term "comprising" and any variations thereof in the description of the present application and claims and in the description of the figures above is intended to cover a non-exclusive inclusion.
In the description of the embodiments of the present application, the technical terms "first," "second," etc. are used merely to distinguish between different objects and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated, a particular order or a primary or secondary relationship. In the description of the embodiments of the present application, the meaning of "plurality" is two or more (including two) unless otherwise specifically defined.
Fig. 1 is a schematic structural diagram of a power grid provided in an embodiment of the present application, as shown in fig. 1, where the power grid may include, but is not limited to: source side 10, network side 11 and user side 12. Wherein the source side 10 is used for generating power to provide power resources; the network side 11 is used for transmitting the power resource of the source side 10 to the user side 12; the user side 12 is configured to use the power resources transmitted from the network side 11.
Illustratively, the source side 10 may include, but is not limited to, at least one of: wind power plants, photovoltaic power plants, energy storage power plants, thermal power plants. The mesh side 11 may include, but is not limited to: lifting transformer equipment, transformer substations and high-voltage transmission lines. The user side 12 may include, but is not limited to, business and residential users.
Considering the high storage cost of power resources, power generation is usually performed on demand, namely, a power grid dispatching center controls each generator set on a source side to perform power generation according to the power grid load on a user side, wherein the power grid dispatching center plays a role in the whole power grid operation and plays a role in guiding and supervising.
In the related art, for each time point to be predicted, a power grid dispatching center needs to conduct load prediction according to power grid historical load data to obtain power grid load prediction data of the predicted time point, and then controls the power generation state of each power generating set at the predicted time point according to the power grid load prediction data of the predicted time point.
Because wind power and photovoltaic resources (or simply wind-light resources) are transient and uncontrollable, the wind power and photovoltaic power generation system is different from the traditional power generation mode in that: the available power is greatly influenced by natural environment, and has great uncertainty, so that the power generation power prediction data of the wind-solar generator set should be considered in the power grid dispatching process. However, only the power grid load prediction data is considered in the power grid dispatching process in the related art, so that the accuracy of power grid dispatching in the related art is low.
In order to solve the problem of low accuracy of power grid dispatching in the related art, the embodiment of the application proposes that in the power grid dispatching process, power load prediction data of a target area and power generation dispatching data of each generator set can be comprehensively considered, and reference data of the power generation dispatching data are more comprehensive, so that the accuracy of power grid dispatching is improved.
In some embodiments, fig. 2 is a flow chart of a power grid dispatching method provided in some embodiments of the present application, where in the embodiments of the present application, a computer device in which the method is applied to a power grid dispatching center is illustrated as an example. As shown in fig. 2, the method of the embodiment of the present application may include the following steps:
step S201, power load prediction data of a target region at a plurality of prediction time points is acquired.
In this step, the computer device may acquire, at intervals of a preset time period, or in the case of receiving a scheduling instruction, power load prediction data (or referred to as power grid load prediction data) of the target area to be scheduled at a plurality of prediction time points, where the power load prediction data at any prediction time point may be used to indicate a power load (or referred to as power grid load) of the user side of the target area at the prediction time point.
In one possible implementation, the computer device may obtain power load prediction data of the target region at a plurality of prediction time points through a preset power load prediction model.
The preset power load prediction model in the embodiment of the present application may be used to indicate time sequence data related to a power load in any region, and a correspondence relationship between power load prediction data of multiple time length types corresponding to the region, where the number of prediction time points corresponding to different time length types is different.
Illustratively, the types of time lengths in embodiments of the present application may include, but are not limited to, at least two of: a long-term load prediction type, a medium-term load prediction type, a short-term load prediction type, and an extremely short-term load prediction type. It is to be understood that the number of prediction time points corresponding to the long-term load prediction type, the number of prediction time points corresponding to the medium-term load prediction type, the number of prediction time points corresponding to the short-term load prediction type, and the number of prediction time points corresponding to the extremely-short-term load prediction type become smaller in order.
The preset power load prediction model in the embodiment of the application may be a power load prediction model pre-trained by the computer device, or may be a power load prediction model pre-trained obtained by the computer device from other devices. The preset power load prediction model in embodiments of the present application may include, but is not limited to, a time series regression algorithm (time series regression algorithm, TSRA) model.
Alternatively, the computer device may input time series data related to the electric load of the target region into the preset power electric load prediction model, and obtain electric load prediction data of the target region output by the preset power electric load prediction model at a plurality of prediction time points.
In this embodiment of the present application, the computer device may input time series data related to a power load of a target area into a preset power load prediction model, extract a plurality of time series features of the time series data through the preset power load prediction model, and perform fusion processing on the plurality of time series features to output power load prediction data of the target area at a plurality of prediction time points.
Illustratively, the time series data related to the power load of the target region in the embodiments of the present application may include, but is not limited to, at least two of the following: weather data of a target area, load data of the target area, electricity price data of the target area, policy data of the target area and economic index data of the target area; wherein the policy data is used to indicate an impact on the power demand.
For example, weather data for the target region may be used to indicate weather information for the target region, wherein the weather data may include, but is not limited to, at least one of: weather conditions (such as heavy rain, sunny, cloudy, hail, etc.), air temperature, humidity, ultraviolet intensity, wind direction, wind speed, wind power.
For example, load data of the target region may be used to indicate electrical load information of the target region, wherein the load data may include, but is not limited to, electrical load demand (e.g., power values, etc.) and/or available crew data; the available genset data may include, but is not limited to, available gensets and/or output power of each genset.
For example, the electricity rate data of the target region may be used to indicate dynamic electricity rate information of the electric power of the target region.
For example, the policy data for the target region may be used to indicate the impact of the policy for the target region on power demand, which may include positive and negative impacts. Positive effects are manifested primarily as positive stimulation of power demand by policies; negative effects are mainly manifested by a negative stimulation of the power demand by policies. It should be appreciated that if any policy is a supporting policy or an investment policy for the power industry, the policy is a positive policy that will positively affect the power demand; if any policy is a punishment policy for the power industry, the policy is a negative policy, negatively affecting the power demand.
Therefore, the time sequence data related to the power load of the target area in the embodiment of the application can comprise policy data, so that the influence relation of the daily life policy trend on the power demand can be mined, and the accuracy of power load prediction can be improved.
For example, economic indicator data for the target zone may be used to indicate economic information for the target zone, wherein the economic indicator data may include, but is not limited to, GDP data and/or CPI data. For example, monthly GDP data, and/or monthly CPI data. Note that, the economic condition of the target area may actually reflect the power demand of the target area, and thus, the time series data related to the power load of the target area in the embodiment of the present application may include economic index data.
It can be seen that, in the embodiment of the present application, on the basis of the weather data and the load data, the power load prediction is further performed by combining the electricity price data, the policy data, the economic index data, and/or the like. Therefore, the reference data for power load prediction in the embodiment of the application is more comprehensive, so that the accuracy of power load prediction is improved.
In another possible implementation, a computer device may receive power load prediction data for a target region at a plurality of predicted time points transmitted by other devices.
Of course, the computer device may also obtain power load prediction data for the target region at a plurality of predicted time points in other manners.
Step S202, obtaining power generation power prediction data of each wind-solar generator set in a target area at a plurality of prediction time points.
In this step, the computer device may acquire, at intervals of a preset duration, or in the case of receiving a scheduling instruction, power generation prediction data of each wind-solar power generator set in a target area to be scheduled at a plurality of prediction time points, where the power generation prediction data of any prediction time point may be used to indicate power generation of a source side in the target area at the prediction time point.
In a possible implementation manner, the computer device may obtain, through a preset power prediction model, power generation prediction data of each wind-solar generator set in the target area at a plurality of prediction time points.
The preset power prediction model in the embodiment of the application can be used for indicating the corresponding relation between time sequence data and non-time sequence data of each wind-light generator set and the power generation power prediction data of each wind-light generator set at a plurality of prediction time points; the preset power prediction model may be a time series hybrid regression algorithm model (Time Series Mixture Regression algorithm, TSMRA).
The preset power prediction model in the embodiment of the application may be a power prediction model pre-trained by the computer device, or may be a power prediction model pre-trained by the computer device obtained from other devices.
Optionally, for each wind-light generator set, the computer device may input time sequence data and non-time sequence data related to the power generated by the wind-light generator set into a preset power prediction model, so as to obtain power generation prediction data of the wind-light generator set output by the preset power prediction model at a plurality of prediction time points.
In the embodiment of the application, for each wind-solar generator set, the computer equipment can input time sequence data and non-time sequence data related to the power generation power of the wind-solar generator set into a preset power prediction model, extract time sequence characteristics of the time sequence data and non-time sequence characteristics of the non-time sequence data through the preset power prediction model, and fuse the time sequence characteristics and the non-time sequence characteristics to output power generation prediction data of the wind-solar generator set at a plurality of prediction time points.
The non-time series data related to the generating power of the wind-light generating set in the embodiment of the application can be used for indicating the non-time series data related to the generating power of the wind-light generating set. Illustratively, non-time series data related to wind turbine generator set generating power in embodiments of the present application may include, but is not limited to: status data of the wind-light generator set and/or constraint data of the wind-light generator set.
For example, the status data of the wind turbine may be used to indicate whether the wind turbine is operating, e.g., whether the wind turbine is down, and/or whether the wind turbine is serviced, etc.
For example, constraint data of the wind turbine generator may be used to indicate an output power threshold range of the wind turbine generator, e.g., maximum output power, and/or minimum output power, etc.
The time sequence data related to the generating power of the wind-light generating set in the embodiment of the application can be used for indicating the time sequence data related to the generating power of the wind-light generating set. For example, the timing data related to the wind turbine generator system power may include, but is not limited to, weather data for the wind turbine generator system, and/or operational data for the wind turbine generator system.
For example, weather data of the wind-light generator set may be used to indicate weather data of an area to which the wind-light generator set belongs, wherein the weather data may include, but is not limited to, at least one of the following: weather conditions (such as heavy rain, sunny, cloudy, hail, etc.), air temperature, humidity, ultraviolet intensity, wind direction, wind speed, wind power. It should be appreciated that for a photovoltaic generator set, weather data in embodiments of the present application may include, but is not limited to, ultraviolet intensity; for wind turbine generators, weather data in embodiments of the present application may include, but is not limited to, wind direction, wind speed, wind power size.
For example, the operational data of the wind turbine may be used to indicate an output power of the wind turbine, wherein the output power may include, but is not limited to, active power and/or reactive power.
Compared with the mode of carrying out power prediction based on time sequence data such as weather data and operation data in the related art, the embodiment of the application further carries out power prediction by combining non-time sequence data such as constraint data and/or state data on the basis of the time sequence data, and reference data for power prediction is more comprehensive. Further, by utilizing the deep learning model to mine the association between constraint data and power generation prediction data, the power generation prediction data of the wind-light generator set is more close to the actual power generation of the wind-light generator set in actual operation, so that the accuracy of power prediction is improved.
In addition, constraint data of the wind-light generator set are further considered in the power prediction process, the deep learning model is used for excavating influence of the constraint data on the power prediction result by extracting constraint characteristics corresponding to the constraint data of the wind-light generator set, association between the constraint data and the power generation power prediction data is achieved, corresponding support can be provided for the power generation power prediction data to be closer to actual power generation power of the wind-light generator set in actual operation, and therefore the power generation power prediction data is closer to the actual power generation power.
In another possible implementation manner, the computer device may receive power generation prediction data of each wind-solar generator set in the target area, which is sent by other devices, at a plurality of prediction time points.
Of course, the computer device may also obtain the power generation prediction data of each wind-solar generator set in the target area at a plurality of prediction time points in other manners.
And step S203, carrying out power grid dispatching according to the power load prediction data of the plurality of prediction time points and the power generation power prediction data of the plurality of prediction time points to obtain power generation power dispatching data of each power generation unit in the target area at each prediction time point.
The types of the generator sets in the target area in the embodiment of the application may include, but are not limited to, at least one of the following: wind-light generating set, thermal generating set, energy storage set (or energy storage power station set); wind and/or solar power generation sets may include, but are not limited to, wind power generation sets and/or photovoltaic power generation sets.
The power generation scheduling data of each generating set at each predicted time point in the embodiment of the application may be used to control the power generation state of each generating set at each predicted time point, where the power generation state may include, but is not limited to, power generation.
In this step, the computer device may perform power grid scheduling according to the power load prediction data of the target area at a plurality of prediction time points and the power generation prediction data of each wind-light generator set of the target area at a plurality of prediction time points, so as to obtain power generation scheduling data of each generator set of the target area at each prediction time point, so as to control the power generation state of each generator set at each prediction time point according to the power generation scheduling data of each generator set at each prediction time point.
For example, the computer device may perform power grid scheduling according to the power load prediction data of the target area at a plurality of prediction time points and the power generation prediction data of each wind-light generator set of the target area at a plurality of prediction time points, so as to obtain power generation scheduling data of each generator set of the target area at each prediction time point. Further, the computer device may determine a power generation instruction of each power generation unit according to the power generation scheduling data of each power generation unit at each prediction time point, and send a corresponding power generation instruction to each power generation unit, where the power generation instruction of any power generation unit may be used to instruct the power generation scheduling data of the power generation unit at each prediction time point, so that the actual power generation of the power generation unit at each prediction time point may be close to the corresponding power generation scheduling data.
Considering that wind power and photovoltaic resources (or simply wind-light resources) are transient and uncontrollable, the power generation power prediction data of the wind-light generator set should be considered in the power grid dispatching process. Compared with the power grid load prediction data only considered in the power grid dispatching process in the related technology, the embodiment of the application further also considers the power generation power prediction data of each wind-solar generator set in the target area at a plurality of prediction time points, and the reference data is more comprehensive, so that a more suitable power grid dispatching scheme can be determined based on dynamic supply and demand balance of the source side and the user side of the power grid.
In the power grid dispatching method, the power load prediction data of the target area at a plurality of prediction time points are obtained, and the power generation power prediction data of each wind-solar generator set of the target area at a plurality of prediction time points are obtained. Further, grid scheduling is performed according to the power load prediction data of the plurality of prediction time points and the power generation power prediction data of the plurality of prediction time points, so that power generation power scheduling data of each power generation unit in the target area at each prediction time point is obtained. Therefore, compared with the power grid load prediction data only considered in the power grid dispatching process in the related technology, the embodiment of the application further considers the power generation power prediction data of each wind-solar generator set in the target area at a plurality of prediction time points on the basis of the power load prediction data, and the reference data is more comprehensive, so that the accuracy of power grid dispatching is improved. In addition, compared with a single-step scheduling mode (i.e. scheduling of only one prediction time point in each power grid scheduling) in the related art, in the embodiment of the present application, the mode of performing power grid scheduling according to the power load prediction data of the target area at a plurality of prediction time points and the power generation power prediction data of each wind-light generator set of the target area at a plurality of prediction time points can realize synchronous power grid scheduling of each generator set of the target area at a plurality of prediction time points, so that not only can power grid scheduling time be saved, but also more valuable data references can be brought to a scheduling center, thereby being beneficial to improving the scheduling efficiency of power grid scheduling.
In some embodiments, fig. 3 is a schematic flow chart of a power grid scheduling method according to other embodiments of the present application, and on the basis of the foregoing embodiments, in the embodiments of the present application, relevant contents of "performing power grid scheduling according to power load prediction data at a plurality of prediction time points and power generation prediction data at a plurality of prediction time points to obtain power generation scheduling data of each generator set in a target area at each prediction time point" in the foregoing step S203 are described. As shown in fig. 3, the step S203 may include the steps of:
step S2031, determining first power constraint conditions of each wind-light generator set at a plurality of prediction time points according to the power generation prediction data of each wind-light generator set at a plurality of prediction time points.
Because wind power and photovoltaic resources are transient and uncontrollable, they differ from the traditional power generation modes in that: the available power is greatly influenced by natural environment, and has great uncertainty, so constraint conditions such as the maximum power upper limit (or called the available maximum power generation power) of the wind-light unit need to be considered in the power grid dispatching process, wherein the constraint conditions such as the maximum power upper limit and the like change along with time due to dynamic change of the environment along with time.
In the step, for each wind-light generator set in a target area, the computer equipment can respectively determine the first power constraint conditions of the wind-light generator set at a plurality of prediction time points according to the power generation prediction data of the wind-light generator set at a plurality of prediction time points, so that constraint conditions such as the maximum power upper limit of the wind-light generator set are dynamically updated according to the power generation prediction data of the wind-light generator set, and the like, so that the power generation scheduling data obtained when the multi-objective function is optimized and solved based on the dynamic constraint conditions can be more close to the actual power generation of the generator set. For example, in the case of insufficient illumination intensity, the generated power of the photovoltaic generator set may not reach the theoretical upper output limit.
It should be appreciated that the first power constraint of any wind turbine generator set in embodiments of the present application is a dynamic constraint.
Optionally, for each wind-light generator set at each prediction time point, the computer device may use the power generation predicted data of the wind-light generator set at the prediction time point as the maximum power upper limit of the wind-light generator set at the prediction time point, and use the preset power threshold as the minimum power lower limit of the wind-light generator set at the prediction time point; the first power constraint condition of the wind-light generator set at the prediction time point may include, but is not limited to, a maximum power upper limit of the wind-light generator set at the prediction time point and a minimum power lower limit of the wind-light generator set at the prediction time point.
For example, if the wind-solar generator set is the ith photovoltaic generator set in the target area, the first power constraint condition of the ith photovoltaic generator set at the predicted time point t may be expressed as the following formula (1):
formula (1)
Wherein P is pv，i，min Representing the minimum power of the ith photovoltaic generator set at the predicted time point tLower limit, P pv，i，t Generating power scheduling data representing the ith photovoltaic generator set at a predicted time point t, P pv，i，max Representing the maximum power upper limit of the ith photovoltaic generator set at a predicted time point t; t may be at least one of: t1, t2, … …, tn, n are integers greater than 2.
Of course, the first power constraint of the ith photovoltaic generator set at the predicted time point t may also be expressed as other variations of the above formula (1) or an equivalent formula.
Still another exemplary scenario, if the wind-solar generator set is the jth wind generator set in the target area, the first power constraint condition of the jth wind generator set at the predicted time point t may be expressed as the following formula (2):
formula (2)
Wherein P is w，j，min Represents the minimum power lower limit, P, of the jth wind generating set at the predicted time point t w，j，t Generating power scheduling data representing the j-th wind generating set at a predicted time point t, P w，j，max Representing the maximum power upper limit of the jth wind generating set at the predicted time point t.
Of course, the first power constraint of the jth wind turbine at the predicted time point t may also be expressed as other variations of the above formula (2) or as an equivalent formula.
Therefore, in the embodiment of the application, constraint conditions such as the maximum power upper limit of the wind-light generator set are dynamically updated by taking the power generation power prediction data of the wind-light generator set at the prediction time point as the maximum power upper limit of the wind-light generator set at the prediction time point, so that power generation scheduling data obtained when the multi-objective function is optimized and solved based on the dynamic constraint conditions can be more close to the actual power generation power of the generator set, the problem that the scheduling data of the wind-light generator set and the actual power generation power have contradiction in the related art can be solved, and the actual power grid scheduling requirement can be met.
Step S2032, constructing a grid power flow constraint condition and a multi-objective function according to the power load prediction data of the plurality of prediction time points.
In the actual operation of the power grid, reliable and stable operation of the power grid also needs to be considered, so that the trend constraint of the power grid needs to be considered. In the step, for each prediction time point, the computer equipment can construct a power grid power flow constraint condition of the target region at the prediction time point according to the power load prediction data of the target region at the prediction time point, and the power grid power flow constraint condition is used as a constraint condition in the subsequent optimization solving process of the multi-objective function, so that the running stability of the power grid is improved.
On the other hand, for each prediction time point, the computer device can construct a multi-objective function of the target region at the prediction time point according to the power load prediction data of the target region at the prediction time point, so that the multi-objective function can be subjected to optimization solving processing to obtain the power generation power scheduling data of each generator set at the prediction time point.
Illustratively, the multiple objective functions in embodiments of the present application may include, but are not limited to, a power gain objective function and a power deviation objective function; the power gain objective function is used for indicating economic benefits of power grid operation; the power deviation objective function is used to indicate a power deviation between the electrical load of the electrical grid and the generating power of the generator set.
Step S2033, performing optimization solving processing on the multi-objective function according to the first power constraint condition of each wind-solar generator set at a plurality of prediction time points, the second power constraint condition of other generator sets in the target area at a plurality of prediction time points, and the power flow constraint condition of the power grid, so as to obtain the power generation power scheduling data of each generator set at each prediction time point.
Other generator sets in the target area in the embodiments of the present application may refer to other generator sets in the target area except for the wind-light generator set. It should be appreciated that where the target area includes other types of gensets in addition to the wind and solar gensets, other gensets in embodiments of the present application may include, but are not limited to: at least one thermal power plant and/or at least one energy storage plant; in the case that the generating sets included in the target area are all wind-light generating sets, relevant contents about other generating sets in the embodiments of the present application may be omitted.
In one possible implementation, if the generator set in the target area includes a thermal generator set, that is, the other generator sets in the target area include thermal generator sets, the second power constraint of the thermal generator set at each predicted time point may include, but is not limited to: the power upper limit and the lower limit of the power generation power scheduling data of the thermal generator set at the predicted time point and the power upper limit and the lower limit of the power generation power change data of the thermal generator set in unit time.
Illustratively, the second power constraint condition of the first thermal generator set at the predicted time point t may be expressed as the following formula (3):
formula (3)
Wherein P is f，l，min Represents the minimum power lower limit, P, of the first thermal generator set at the predicted time point t f，l，t Generating power schedule data representing the first thermal generator set at a predicted time point t, P f，l，max Representing the maximum power upper limit of the first thermal generator set at a predicted time point t; p (P) f，l，t+1 Generating power scheduling data representing the predicted time point t+1 of the first thermal generator set, P f，l，r Representing the power upper limit, P, to which the power generation power schedule data of the first thermal generator set increased in unit time belongs f，l，d Representing the power upper limit to which the generated power schedule data of the first thermal generator set decreases in a unit time.
Of course, the second power constraint condition of the first thermal generator set at the predicted time point t may also be expressed as other variations of the above formula (3) or an equivalent formula.
In another possible implementation, if the generator set includes an energy storage set, that is, the other generator sets in the target area include an energy storage set, the second power constraint of the energy storage set at each predicted time point may include, but is not limited to: the power upper limit and the lower limit of the power generation power scheduling data of the energy storage unit at the prediction time point and the SOC upper limit and the lower limit of the SOC data of the energy storage unit at the prediction time point.
For example, the second power constraint condition of the kth energy storage unit at the predicted time point t may be expressed as the following formula (4):
formula (4)
Wherein P is s，k，min Represents the minimum power lower limit, P, of the kth energy storage unit at the predicted time point t s，k，t Generating power scheduling data representing the kth energy storage unit at a predicted time point t, P s，k，max Representing the maximum power upper limit of the kth energy storage unit at a predicted time point t; SOC (State of Charge) k，t SOC data representing the k-th energy storage unit at a predicted time point t, and SOC k，min Representing the SOC lower limit and SOC of the kth energy storage unit at the predicted time point t k，max Representing the upper SOC limit of the kth energy storage unit at the predicted time point t.
Of course, the second power constraint of the kth energy storage unit at the predicted time point t may also be expressed as other variations of the above formula (4) or as an equivalent formula.
In this step, for each predicted time point, the computer device may perform an optimization solution process on the multiple objective functions according to the first power constraint condition of each wind-solar generator set at the predicted time point, the second power constraint condition of other generator sets in the target area at the predicted time point, and the power flow constraint condition of the power grid, to obtain power generation power scheduling data of each generator set at the predicted time point.
For example, the computer device may perform an optimization solution process on the multi-objective function by using a sequential meta-heuristic algorithm (Sequence MetaHeuristic Algorithm, SMA) to obtain power generation scheduling data of each generator set at the predicted time point, where the SMA may include, but is not limited to, a sequential particle swarm optimization algorithm (particle swarm optimization, PSO) or a genetic algorithm (genetic algorithm, GA) and other operational algorithms.
Of course, the computer device may also perform the optimization solving process on the multi-objective function by using other algorithms for optimizing the long-time sequence solving.
In summary, in the embodiment of the application, by determining the first power constraint condition according to the power generation power prediction data of each wind-light generator set at each prediction time point, constructing the power grid power flow constraint condition and the multi-objective function according to the power load prediction data of each prediction time point, and performing optimization solving processing on the multi-objective function according to the first power constraint condition of each wind-light generator set at a plurality of prediction time points, the second power constraint condition of other generator sets in a target area at a plurality of prediction time points and the power grid power flow constraint condition, the power generation power scheduling data of each generator set closer to the actual power generation power at a plurality of prediction time points can be obtained on the premise of reliable operation of the power grid, and therefore the accuracy and reliability of power grid scheduling can be further improved.
In some embodiments, fig. 4 is a schematic flow chart of a multi-objective function construction method according to some embodiments of the present application, and on the basis of the foregoing embodiments, in the embodiments of the present application, the relevant content of "constructing a multi-objective function according to power load prediction data at a plurality of prediction time points" in the foregoing step S2032 is described. As shown in fig. 4, the step S2032 may include the steps of:
Step S2032A, determining a power gain objective function at each prediction time point for the target region and a power deviation objective function between the power load and the generated power at each prediction time point for the target region from the power load prediction data at a plurality of prediction time points.
In this step, the computer device may determine the power gain objective function of the target region at each prediction time point from the power load prediction data at the plurality of prediction time points, and determine the power deviation objective function between the power load and the generated power of the target region at each prediction time point from the power load prediction data at the plurality of prediction time points.
The following embodiments of the present application describe the content of "determining a power gain objective function at each prediction time point in a target region from power load prediction data at a plurality of prediction time points".
Optionally, for each predicted time point, the computer device may determine, according to the power load prediction data and the power grid selling price at the predicted time point, power grid selling income of the target area at the predicted time point; further, the computer device may determine an objective function of the power gain of the target area at the predicted time point based on the power grid selling income, the subsidy income of the target area at the predicted time point, the electricity purchasing cost, and the pollution cost.
The subsidy income of the target area at each predicted time point in the embodiment of the application can be calculated according to the power generation scheduling data of each generator set of the target area at the predicted time point and the subsidy price corresponding to each generator set.
For each predicted time point, the computer apparatus may determine the subsidy income of the target region at the predicted time point according to the power generation scheduling data of each power generation unit of the target region at the predicted time point and the subsidy price corresponding to each power generation unit, as illustrated in the following formula (5).
Formula (5)
Wherein B is grid,income,t Subsidy income of the target area at the predicted time point t;representing a unit time; m is M w Representing the number of wind generating sets contained in the target area; s is S w,j Representing the subsidy price of the jth wind generating set; m is M f Representing the number of thermal generator sets contained in the target area; s is S f,l Representing the subsidy price of the first thermal generator set; m is M s Representative target area packageThe number of the energy storage units; s is S s,k Representing the subsidy price of the kth energy storage unit; m is M pv Representing the number of photovoltaic generator sets contained in the target area; s is S pv,i Representing the subsidy price of the ith photovoltaic generator set.
Of course, the computer device may determine the subsidy income of the target area at the predicted time point according to the power generation scheduling data of each generator set of the target area at the predicted time point and the subsidy price corresponding to each generator set by using other variations or equivalent formulas of the above formula (5).
The electricity purchasing cost of the target area at each predicted time point in the embodiment of the present application may be calculated according to the power generation scheduling data of each generator set of the target area at the predicted time point and the unit electricity selling price corresponding to each generator set.
For each predicted time point, the computer device may determine the electricity purchasing cost of the target area at the predicted time point according to the power generation scheduling data of each generator set of the target area at the predicted time point and the unit electricity selling price corresponding to each generator set by using the following formula (6).
Formula (6)
Wherein C is grid,buy,t Representing electricity purchasing cost of a target area at a predicted time point t; c (C) w,j The electricity selling price of the unit of the jth wind generating unit is represented; c (C) f,l The unit electricity selling price of the first thermal generator unit is represented; c (C) s,k The unit electricity selling price of the kth energy storage unit is represented; c (C) pv,i Representing the unit electricity selling price of the ith photovoltaic generator unit.
Of course, the computer device may determine the electricity purchasing cost of the target area at the predicted time point according to the power scheduling data of each generator set of the target area at the predicted time point and the unit electricity selling price corresponding to each generator set by using other variations of the above formula (6) or an equivalent formula.
The pollution cost of the target area at each predicted time point in the embodiment of the present application may be calculated according to the power generation scheduling data of each thermal generator set of the target area at the predicted time point.
For each predicted time point, the computer apparatus may determine the pollution cost of the target region at the predicted time point by the following formula (7) from the power generation scheduling data of each thermal generator set of the target region at the predicted time point.
Formula (7)
Wherein C is po,t Representing pollution cost of a target area at a predicted time point t;representing the pollution cost of each degree of electricity of the thermal generator set.
Of course, the computer device can also determine the pollution cost of the target area at the predicted time point through other variants of the above formula (7) or equivalent formulas according to the power generation scheduling data of each thermal generator set of the target area at the predicted time point.
For each predicted point in time, the computer device may determine the grid electricity sales revenue for the target region at that predicted point in time from the predicted data of the power load and the grid electricity sales price for that predicted point in time, as illustrated by equation (8) below.
Formula (8)
Wherein I is grid,income,t Power grid electricity selling income, P, representing target area at predicted time point t load,t Power load prediction data, p, representing the target region at a predicted time point t grid,t Representing the electricity selling price of the power grid at the predicted time point t.
Of course, the computer device may also determine the electricity selling income of the electric network in the target area at the predicted time point according to the electricity load predicted data and the electricity selling price of the electric network at the predicted time point by using other variants or equivalent formulas of the above formula (8).
Further, the computer device may determine the power gain objective function of the target region at the predicted time point according to the power selling income of the power grid, the subsidy income of the target region at the predicted time point, the electricity purchasing cost and the pollution cost by the following formula (9).
Formula (9)
Wherein f profi,t Representing the power gain objective function of the target region at the predicted time point t.
Of course, the computer device may also determine the electric power gain objective function of the target area at the predicted time point according to the electric power selling income of the electric network, the subsidy income of the target area at the predicted time point, the electricity purchasing cost and the pollution cost, and other variants or equivalent formulas of the above formula (9).
Of course, the computer device may also determine the power gain objective function of the target region at each predicted time point in other manners based on the power load prediction data at the plurality of predicted time points.
The following embodiments of the present application describe the content of the "determining a power deviation objective function between a power load and a generated power at each prediction time point in a target region from power load prediction data at a plurality of prediction time points".
For each predicted time point, the computer device may determine a power deviation objective function of the target region at the predicted time point according to the power load prediction data of the predicted time point and the generated power scheduling data of each generator set at the predicted time point.
Illustratively, the computer apparatus may determine the power deviation objective function of the target region at the predicted time point by the following formula (10) based on the power load prediction data at the predicted time point and the generated power schedule data of each generator set at the predicted time point.
Formula (10)
Wherein,representing a power deviation objective function of a target region at a predicted time point t; />Representing the efficiency of the network loss.
Of course, the computer device may also determine the power deviation objective function of the target area at the predicted time point according to the power load predicted data of the predicted time point and the power scheduling data of each generator set at the predicted time point through other variants or equivalent formulas of the above formula (10).
Of course, the computer device may also determine the power deviation objective function between the power load and the generated power at each predicted time point of the target region by other means, based on the power load prediction data at a plurality of predicted time points.
Step S2032B, constructing a multi-objective function according to the power gain objective function of the target area at each prediction time point and the power deviation objective function of the target area at each prediction time point.
In this step, for each predicted time point, the computer device may construct a multi-objective function of the target area at the predicted time point with the objective of maximizing the corresponding power gain and minimizing the corresponding power deviation according to the power gain objective function of the target area at the predicted time point and the power deviation objective function of the target area at the predicted time point.
Illustratively, the computer apparatus may construct a multi-objective function of the target region at the predicted time point by the following formula (11) based on the power gain objective function of the target region at the predicted time point and the power deviation objective function of the target region at the predicted time point.
Formula (11)
Wherein f op,t Representing a multi-objective function of the target region at a predicted time point t; Represents a power penalty factor, wherein ∈>May be [0,1 ]]A first predetermined value of (a); />Represents a gain penalty factor, wherein->May be [0,1 ]]Is a second preset value of (a).
It will be appreciated that the above power deviation objective functionThe closer to 0, the better, i.e., the target region can be made to maintain dynamic balance between the generated power at the predicted time point t and the power load prediction data. The electric power gain objective function f profi,t The larger the better, i.e. the higher the revenue of the grid operation. The coefficient of the first term in the above formula (11) is squared mainly to make it possible to preferentially balance the supply and demand of the grid and secondly to optimize the economic return.
Of course, the computer device may also construct a multi-objective function of the target region at the predicted time point according to the power gain objective function of the target region at the predicted time point and the power deviation objective function of the target region at the predicted time point by other variations of the above formula (11) or an equivalent formula.
In summary, in the embodiment of the present application, the power gain objective function of the target region at each prediction time point and the power deviation objective function between the power load and the generated power of the target region at each prediction time point are determined by the power load prediction data at a plurality of prediction time points. Further, a multi-objective function mode is constructed according to the power gain objective function of the target area at each prediction time point and the power deviation objective function of the target area at each prediction time point, so that a power grid dispatching scheme with maximized power gain and minimized power deviation can be realized, and the accuracy and the rationality of power grid dispatching can be further improved.
In some embodiments, fig. 5 is a flowchart of a method for constructing a power grid load constraint condition according to some embodiments of the present application, and on the basis of the foregoing embodiments, in the embodiments of the present application, the relevant content of "constructing a power grid load constraint condition according to power load prediction data at a plurality of prediction time points" in the foregoing step S2032 is described. As shown in fig. 5, the step S2032 may include the steps of:
step S2032C, for each predicted time point, determining a first power flow of the power load of the target area at the predicted time point to the power grid line according to the power load prediction data of the predicted time point and the power distribution coefficient of the preset power load to the power grid line.
In this step, for each predicted time point, the computer device determines a first power flow of the power load of the target region to the power grid line at the predicted time point according to the power load prediction data of the target region at the predicted time point and a preset power distribution coefficient of the power load to the power grid line.
The computer device may determine the first power flow of the power load of the target region to the grid line at the predicted time point by the following formula (12) based on the power load prediction data of the target region at the predicted time point and the preset power distribution coefficient of the power load to the grid line.
Formula (12)
Wherein Y is l,load,t A first power flow of the power load to the power grid line r at a predicted time point t representing the target region;representing a preset power distribution coefficient of the power load to the grid line r.
Of course, the computer device may also determine the first power flow of the power load of the target area at the predicted time point to the power grid line according to the predicted data of the power load of the target area at the predicted time point and the preset power distribution coefficient of the power load to the power grid line through other variants or equivalent formulas of the above formula (12).
Step S2032D, determining a second power flow of each generator set to the power grid line at the predicted time point according to the power generation power scheduling data of each generator set at the predicted time point and the corresponding power transmission distribution coefficient.
In this step, for each predicted time point, the computer device determines, according to the power generation power scheduling data of each generator set at the predicted time point and the corresponding power transmission distribution coefficient (or referred to as the power transmission distribution coefficient), a second power flow of each generator set to the power grid line at the predicted time point.
The computer device may determine the second power flow of each generator set to the grid line at the predicted point in time by the following equation (13) based on the generated power schedule data and the corresponding power transmission distribution coefficient of each generator set at the predicted point in time.
Formula (13)
Wherein Y is l,p,t Representing the second tide of each generator set to the power grid line r at the predicted time point t;representing the power transmission distribution coefficient of the first thermal generator set to the power grid line r; />Representing the power transmission distribution coefficient of the jth wind generating set to the power grid line r; />Representing the power transmission distribution coefficient of the kth energy storage unit to the power grid line r; />Representing the power transmission distribution coefficient of the ith photovoltaic generator set to the power grid line r. />
Of course, the computer device may also determine the second power flow of each generator set to the grid line at the predicted time point according to the power scheduling data of each generator set at the predicted time point and the corresponding power transmission distribution coefficient, and other variations of the above formula (13) or an equivalent formula.
Step S2032E, determining a power grid power flow constraint condition of the target area at the predicted time point according to the first power flow and the second power flow.
In this step, for each predicted time point, the computer device may determine a power grid power flow constraint condition of the target area at the predicted time point according to a first power flow of the power load of the target area at the predicted time point to the power grid line and a second power flow of each generator set at the predicted time point to the power grid line.
The computer device may determine the grid power flow constraint condition of the target region at the predicted time point by the following equation (14) based on the first power flow of the power load of the target region to the grid line at the predicted time point and the second power flow of each generator set to the grid line at the predicted time point.
Formula (14)
Wherein Y is r,max Representing a preset upper tide limit of the grid line r.
Of course, the computer device may determine the power flow constraint condition of the power grid of the target area at the predicted time point according to the first power flow of the power load of the target area at the predicted time point and the second power flow of each generator set at the predicted time point.
In summary, in the embodiment of the present application, for each predicted time point, a first power flow of the power load of the target area at the predicted time point to the power grid line is determined by using the power load prediction data of the predicted time point and a preset power distribution coefficient of the power load to the power grid line. Further, according to the power generation power scheduling data of each generator set at the predicted time point and the corresponding power transmission distribution coefficient, determining a second tide of each generator set to the power grid line at the predicted time point. Further, according to the first power flow and the second power flow, the power grid power flow constraint condition of the target area at the predicted time point is determined, so that power generation power dispatching data under the premise of safe and stable operation of the power grid can be obtained when the multi-objective function is optimized and solved based on the power grid power flow constraint condition, and further reliability and stability of power grid dispatching can be improved.
In some embodiments, fig. 6 is a schematic structural diagram of a power grid dispatching framework provided in some embodiments of the present application, and on the basis of the foregoing embodiments, the embodiments of the present application describe an overall flow of the power grid dispatching method. As shown in fig. 6, the power grid dispatching method of the embodiment of the present application may include: the system comprises a power load prediction part, a power generation power prediction part of a wind-light generator set and a power grid dispatching part.
1. Power load prediction part
1) The computer device may obtain raw time series data related to the power load of the target region from each data source, wherein the raw time series data may be divided into offline raw time series data and real-time raw time series data; the raw timing data may include, but is not limited to: raw weather data, raw load data, raw electricity price data, raw policy data, and raw economic index data.
Illustratively, the policy data includes: policy data that has a positive impact on the increase in power demand and/or policy data that has a negative impact on the increase in power demand.
2) The computer device performs data processing on the raw time series data related to the power load of the target area to obtain time series data related to the power load of the target area, wherein the data processing can include, but is not limited to, data cleaning processing, data preprocessing and first characteristic engineering processing. The real-time data may not be subjected to the data cleaning process.
Illustratively, the data cleansing process may include, but is not limited to, at least one of: the method comprises the steps of repeating data deleting processing, missing data filling processing, abnormal data deleting processing, abnormal data correcting processing and redundant data deleting processing. The data preprocessing may include, but is not limited to, at least one of: data filtering processing, data filling processing, data splicing processing and data format conversion processing. The first specialty engineering process may include, but is not limited to, a feature encoding process, and/or a data feature stitching process.
In the first special engineering processing process of the original time sequence data after the data preprocessing, on one hand, the computer equipment can input the policy data and the economic index data in the original time sequence data after the data preprocessing into the feature classification encoder to perform feature encoding processing to obtain the first time sequence data. Wherein the feature classification encoder may include, but is not limited to, xgboost+lr tree models. After the xgboost+lr tree model is trained, the last layer of the xgboost+lr tree model needs to be removed, and a part above the coding layer is left, so that the coding layer outputs binary codes corresponding to the policy data and the economic index data.
On the other hand, the computer device may perform feature encoding processing on other raw time series data except for the policy data and the economic index data in the raw time series data after the data preprocessing to obtain second time series data, where the feature encoding processing may include, but is not limited to, at least one of the following: hash processing, continuous characteristic discretization processing and coding processing.
Further, the computer device may perform data feature stitching processing on the first time sequence data and the second time sequence data to obtain time sequence data related to the power load of the target area. Wherein, the time sequence data related to the power load of the target area is divided into offline time sequence data and real-time sequence data.
It should be appreciated that the computer device may perform power load prediction model training with a portion of the offline time series data as a training sample set and power load prediction model testing with another portion of the offline time series data as a test sample set.
Further, in the case that the preset power load prediction model is trained using the offline time series data, the computer device may input the real-time series data into the preset power load prediction model to obtain power load prediction data of the target region at a plurality of prediction time points.
2. Generating power prediction part of wind-light generator set
1) The computer equipment can acquire original time sequence data and original non-time sequence data which correspond to each wind-solar generator set of the target area from each data source, wherein the original time sequence data can be divided into offline original time sequence data and real-time original time sequence data, and the original non-time sequence data can be divided into offline original non-time sequence data and real-time original non-time sequence data. As shown in fig. 6, the computer device may obtain the original time series data 1 and the original non-time series data 2 of each wind generating set, and the original time series data 3 and the original non-time series data 4 of each photovoltaic generating set.
Illustratively, the raw timing data may include raw weather data and raw operational data; the raw non-temporal data may include raw state data and raw constraint data. It should be noted that, the original non-time series data may be used as a constraint condition.
2) The method comprises the steps that data processing is conducted on original time sequence data and original non-time sequence data corresponding to all wind-light generator sets in a target area through computer equipment, and time sequence data and non-time sequence data corresponding to all wind-light generator sets in the target area are obtained, wherein the time sequence data can be divided into offline time sequence data and real-time sequence data, and the non-time sequence data can be divided into offline non-time sequence data and real-time non-time sequence data.
Illustratively, the data processing may include, but is not limited to, a data cleansing process, a data preprocessing, and a second feature engineering process. The real-time data may not be subjected to the data cleaning process.
Illustratively, the second feature engineering process may include, but is not limited to, at least one of: hash processing, continuous feature discretization processing, coding processing, one_hot coding and data feature splicing processing.
It should be noted that, in the process of performing the second feature engineering processing on the original time sequence data after the data preprocessing by the computer device, an Embedding encoding processing may be performed to obtain time sequence data; and the computer equipment can perform one_hot coding in the process of performing second characteristic engineering processing on the original non-time sequence data after the data preprocessing to obtain the non-time sequence data.
Further, the computer device can perform data characteristic splicing processing on the time sequence data and the non-time sequence data to obtain corresponding long sequence data. Wherein the long sequence data can be divided into offline sequence data and real-time sequence data.
Further, under the condition that the offline sequence data is used for training the preset power prediction model, the computer equipment can input the real-time sequence data into the preset power prediction model to obtain the power generation power prediction data of each wind-solar generator set at a plurality of prediction time points.
3. Grid dispatching part
1) For each wind-light generator set in a target area at any prediction time point t, the computer equipment can take the power generation power prediction data of the wind-light generator set at the prediction time point t as the maximum power upper limit of the wind-light generator set at the prediction time point t so as to obtain a first power constraint condition of the wind-light generator set at the prediction time point t.
For any predicted time point t, the computer device may construct a power grid power flow constraint condition and a multi-objective function of the target region at the predicted time point t according to the power load prediction data of the target region at the predicted time point t.
Further, for any prediction time point t, the computer device may perform optimization solving processing on the multiple objective functions according to the first power constraint condition of each wind-solar generator set at the prediction time point t, the second power constraint condition of each thermal generator set at the prediction time point t, the second power constraint condition of each energy storage set at the prediction time point t, and the power grid power flow constraint condition of the target area at the prediction time point t, so as to obtain power generation power scheduling data of each generator set at the prediction time point t.
In an embodiment of the present application, the computer device may perform optimization solving processing on the multiple objective functions by using a sequential meta-heuristic SMA to obtain power generation scheduling data of each generating set at a predicted time point t, where the power generation scheduling data of each generating set at the predicted time point t may respectively satisfy a corresponding constraint condition.
In the embodiment of the application, the sequential meta-heuristic algorithm SMA is used to perform optimization solving processing on the multiple objective functions, so that the power generation scheduling data of each generator set in the target area at a plurality of future prediction time points can be obtained synchronously.
For ease of understanding, the following embodiments of the present application illustrate grid scheduling of 96 predicted time points in the future by using a sequential meta-heuristic SMA including PSO, where a computer device may schedule every 15 minutes. It should be appreciated that the PSO algorithm in the embodiments of the present application may perform grid scheduling on a time Sequence, and thus may be referred to as a Sequence (Sequence) PSO algorithm.
The PSO algorithm referred to in the embodiments of the present application may include, but is not limited to, the following steps:
1) All particles are initialized, i.e. the velocity and position of all particles are assigned values.
2) And evaluating each particle to obtain global optimum, and judging whether an end condition is met.
3) If the end condition is not satisfied, the speed and position of each particle are updated and the fitness function value of each particle is evaluated. Further, updating the historical optimal position of each particle and the global optimal position of the group, returning to the step of judging whether the end condition is met or not, and continuing to execute until the end condition is met, and outputting the global optimal position of the group.
It should be noted that, in the embodiment of the present application, the target region is used to predict the multiple objective functions f at the time point t op,t As fitness function value, and is changed from original R when randomly initializing particles M*N Space is converted into R Q*M*N The method comprises the steps of carrying out a first treatment on the surface of the Wherein, Q represents the time sequence length (or the number of predicted time points) that needs to be scheduled once, M is the scale of the particle swarm, and N is the number of all the generator sets in the power grid.
Fig. 7 is a schematic diagram of the dynamic constraint condition provided by the embodiment of the present application, as shown in fig. 7, because the wind-light generator set is greatly affected by the external environment, the power constraint condition corresponding to the wind-light generator set should be dynamically changed. Therefore, compared with the fixed constraint conditions of 96 predicted time points in the related technology, in the embodiment of the application, the power generation power scheduling data of each generating set, which is more close to the actual power generation power at 96 predicted time points in the future, can be obtained by converting the fixed constraint conditions into the dynamic constraint conditions to perform optimization solving processing.
In summary, in the embodiment of the present application, by performing the optimization solving process on the multiple objective functions according to the dynamic first power constraint condition of each wind-solar generator set at the multiple prediction time points, the second power constraint condition of other generator sets in the target area at the multiple prediction time points, and the grid trend constraint condition, a power grid reliable operation is assumed, and a corresponding power grid scheduling scheme is made with dynamic maximization of power gain, minimization of pollution cost, and minimization of power deviation, so that power generation power scheduling data of each generator set closer to actual power generation at the multiple prediction time points can be obtained. Therefore, the power grid dispatching method in the embodiment of the application is high in accuracy and reliability and dispatching efficiency.
It should be understood that, although the steps in the flowcharts related to the above embodiments are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides a power grid dispatching device for realizing the power grid dispatching method. The implementation of the solution provided by the device is similar to the implementation described in the above method, so the specific limitation in the embodiments of the power grid dispatching device or devices provided below may be referred to the limitation of the power grid dispatching method hereinabove, and will not be repeated here.
In some embodiments, fig. 8 is a schematic structural diagram of a power grid dispatching device provided in some embodiments of the present application, where the power grid dispatching device provided in the embodiments of the present application may be applied to a computer device. As shown in fig. 8, the power grid dispatching apparatus of the embodiment of the present application may include: a first acquisition module 801, a second acquisition module 802, and a scheduling module 803.
Wherein, the first obtaining module 801 is configured to obtain power load prediction data of a target area at a plurality of prediction time points;
a second obtaining module 802, configured to obtain power generation prediction data of each wind-solar generator set in a target area at a plurality of prediction time points;
the scheduling module 803 is configured to perform power grid scheduling according to the power load prediction data of the plurality of prediction time points and the power generation prediction data of the plurality of prediction time points, so as to obtain power generation scheduling data of each power generation unit in the target area at each prediction time point; the power generation scheduling data of each generator set at each prediction time point is used for controlling the power generation state of each generator set at each prediction time point.
In some embodiments, fig. 9 is a schematic structural diagram of a power grid dispatching device according to other embodiments of the present application, and on the basis of the above embodiments, the embodiments of the present application describe relevant contents of the dispatching module 803. As shown in fig. 9, the scheduling module 803 includes:
The determining unit 8031 is configured to determine, according to the power generation prediction data of each wind-light generator set at multiple prediction time points, a first power constraint condition of each wind-light generator set at multiple prediction time points;
a construction unit 8032, configured to construct a grid power flow constraint condition and a multi-objective function according to power load prediction data of a plurality of prediction time points;
the processing unit 8033 is configured to perform an optimization solution process on the multiple objective functions according to a first power constraint condition of each wind-solar generator set at multiple prediction time points, a second power constraint condition of other generator sets in the target area at multiple prediction time points, and a power grid trend constraint condition, so as to obtain power generation power scheduling data of each generator set at each prediction time point.
In some embodiments, the building unit 8032 is specifically configured to:
determining a power gain objective function of a target region at each prediction time point and a power deviation objective function of the target region between the power load and the generated power at each prediction time point according to the power load prediction data of the plurality of prediction time points;
and constructing a multi-objective function according to the power gain objective function of the target area at each prediction time point and the power deviation objective function of the target area at each prediction time point.
In some embodiments, the building unit 8032 is specifically configured to:
for each prediction time point, determining the power grid electricity selling income of the target area at the prediction time point according to the power load prediction data and the power grid electricity selling price at the prediction time point;
and determining an electric power gain objective function of the target region at the predicted time point according to the electric power selling income of the electric network, the subsidy income of the target region at the predicted time point, the electricity purchasing cost and the pollution cost.
In some embodiments, the building unit 8032 is specifically configured to:
and for each prediction time point, determining a power deviation objective function of the target area at the prediction time point according to the power load prediction data of the prediction time point and the power generation power scheduling data of each generator set at the prediction time point.
In some embodiments, the building unit 8032 is specifically configured to:
for each prediction time point, determining a first power flow of the power load of the target area at the prediction time point to the power grid line according to the power load prediction data of the prediction time point and a power distribution coefficient of the preset power load to the power grid line;
determining a second tide of each generator set to the power grid line at the predicted time point according to the power generation power scheduling data of each generator set at the predicted time point and the corresponding power transmission distribution coefficient;
And determining a power grid power flow constraint condition of the target region at a predicted time point according to the first power flow and the second power flow.
In some embodiments, the determining unit 8031 is specifically configured to:
for each wind-light generating set at each prediction time point, taking the power generation prediction data of the wind-light generating set at the prediction time point as the maximum power upper limit of the wind-light generating set at the prediction time point;
and taking the preset power threshold value as the minimum power lower limit of the wind-solar generator set at the predicted time point.
In some embodiments, if the generator set comprises a thermal generator set, the second power constraints of the thermal generator set at each predicted point in time comprise: the power upper limit and the lower limit of the power generation power scheduling data of the thermal generator set at the predicted time point and the power upper limit and the lower limit of the power generation power change data of the thermal generator set in unit time.
In some embodiments, if the generator set includes an energy storage set, the second power constraint of the energy storage set at each predicted point in time includes: the power upper limit and the lower limit of the power generation power scheduling data of the energy storage unit at the prediction time point and the SOC upper limit and the lower limit of the SOC data of the energy storage unit at the prediction time point.
In some embodiments, the first obtaining module 801 is specifically configured to:
and inputting the time sequence data related to the power load of the target area into a preset power load prediction model to obtain power load prediction data of the target area, which is output by the preset power load prediction model, at a plurality of prediction time points.
In some embodiments, the timing data includes at least two of: weather data of a target area, load data of the target area, electricity price data of the target area, policy data of the target area and economic index data of the target area; wherein the policy data is used to indicate an impact on the power demand.
In some embodiments, the second acquisition module 802 is specifically configured to:
for each wind-light generator set, inputting time sequence data and non-time sequence data related to the power generated by the wind-light generator set into a preset power prediction model to obtain power generation prediction data of the wind-light generator set output by the preset power prediction model at a plurality of prediction time points.
In some embodiments, non-time series data related to wind turbine generator set generation power includes: status data of the wind-light generator set and/or constraint data of the wind-light generator set; the state data are used for indicating whether the wind-solar generator set operates or not; the constraint data is used for indicating the output power threshold range of the wind-solar generator set;
The time sequence data includes: weather data of the wind-light generator set and/or operation data of the wind-light generator set.
The power grid dispatching device provided by the embodiment of the application can be used for executing the technical scheme about the computer equipment in the embodiment of the power grid dispatching method, and the implementation principle and the technical effect are similar, and are not repeated here.
The respective modules in the above-described image processing apparatus may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In some embodiments, fig. 10 is a schematic structural diagram of a computer device in some embodiments of the present application, and as shown in fig. 10, the computer device provided in the embodiments of the present application may include a processor, a memory, an input/output interface, a communication interface, a display unit, and an input device. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for conducting wired or wireless communication with an external device, and the wireless communication can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, the technical scheme in the embodiment of the power grid dispatching method is realized, and the implementation principle and the technical effect are similar, so that the description is omitted herein. The display unit of the computer device is used for forming a visual picture, and can be a display screen, a projection device or a virtual reality imaging device. The display screen may be a liquid crystal display screen or an electronic ink display screen. The input device of the computer equipment can be a touch layer covered on a display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those skilled in the art that the structure shown in fig. 10 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In some embodiments, a computer device is further provided, including a memory and a processor, where the memory stores a computer program, and the processor implements the technical solution in the power grid scheduling method embodiment described in the application when executing the computer program, and the implementation principle and the technical effect are similar, and are not repeated herein.
In some embodiments, a computer readable storage medium is further provided, on which a computer program is stored, where the computer program when executed by a processor implements the technical solution in the foregoing power grid scheduling method embodiment of the present application, and the implementation principle and technical effect are similar, and are not repeated herein.
In some embodiments, a computer program product is also provided, where the computer program is implemented by a processor to implement a technical solution in the foregoing power grid scheduling method embodiment of the present application, and the implementation principle and technical effects are similar, and are not repeated herein.
Those skilled in the art will appreciate that implementing all or part of the above-described methods may be accomplished by way of a computer program, which may be stored on a non-transitory computer readable storage medium and which, when executed, may comprise the steps of the above-described embodiments of the methods. Any reference to memory, feature database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as Static Random access memory (Static Random access memory AccessMemory, SRAM) or dynamic Random access memory (Dynamic Random Access Memory, DRAM), and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing based feature data processing logic units, etc., without being limited thereto.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the embodiments, and are intended to be included within the scope of the claims and description. In particular, the technical features mentioned in the respective embodiments may be combined in any manner as long as there is no structural conflict. The present application is not limited to the specific embodiments disclosed herein, but encompasses all technical solutions falling within the scope of the claims.

Claims (14)

1. A method for grid dispatching, the method comprising:
acquiring power load prediction data of a target area at a plurality of prediction time points;
acquiring power generation power prediction data of each wind-solar generator set in the target area at a plurality of prediction time points;
For each wind-light generator set at each prediction time point, taking the power generation power prediction data of the wind-light generator set at the prediction time point as the maximum power upper limit of the wind-light generator set in a first power constraint condition of the prediction time point, and taking a preset power threshold value as the minimum power lower limit of the wind-light generator set in the first power constraint condition of the prediction time point;
constructing a power grid power flow constraint condition and a multi-objective function according to the power load prediction data of the plurality of prediction time points; wherein the multiple objective functions include a power gain objective function and a power deviation objective function; wherein the power gain objective function is used for indicating economic benefits of grid operation; the power deviation objective function is used for indicating the power deviation between the power load of the power grid and the power generated by the generator set;
according to the first power constraint conditions of all the wind-solar generator sets at the plurality of prediction time points, the second power constraint conditions of other generator sets in the target area at the plurality of prediction time points and the power grid trend constraint conditions, carrying out optimization solving processing on the multi-objective function to obtain power generation power scheduling data of all the generator sets in the target area at the plurality of prediction time points; the power generation scheduling data of each generator set at each predicted time point is used for controlling the power generation state of each generator set at each predicted time point.
2. The method of claim 1, wherein constructing a multi-objective function from the power load prediction data for the plurality of predicted time points comprises:
determining a power gain objective function of the target region at each predicted time point and a power deviation objective function of the target region between the power load and the generated power at each predicted time point according to the power load prediction data of the plurality of predicted time points;
and constructing the multi-objective function according to the power gain objective function of the target area at each predicted time point and the power deviation objective function of the target area at each predicted time point.
3. The method of claim 2, wherein said determining a power gain objective function for said target region at each of said predicted time points based on power load prediction data for said plurality of predicted time points comprises:
for each predicted time point, determining the power grid electricity selling income of the target area at the predicted time point according to the power load predicted data and the power grid electricity selling price of the predicted time point;
and determining an electric power gain objective function of the target area at the predicted time point according to the electric power selling income of the electric network, the subsidy income of the target area at the predicted time point, the electricity purchasing cost and the pollution cost.
4. The method of claim 2, wherein determining a power deviation objective function between the power load and the generated power of the target region at each of the predicted time points from the power load prediction data at the plurality of predicted time points comprises:
and for each predicted time point, determining a power deviation objective function of the target area at the predicted time point according to the power load predicted data of the predicted time point and the power generation power scheduling data of each generator set at the predicted time point.
5. The method of claim 1, wherein constructing a grid power flow constraint from the power load prediction data for the plurality of predicted time points comprises:
for each predicted time point, determining a first power flow of the power load of the target area at the predicted time point to the power grid line according to the power load predicted data of the predicted time point and a power distribution coefficient of the power load to the power grid line;
determining a second tide of each generator set to the power grid line at the predicted time point according to the power generation power scheduling data of each generator set at the predicted time point and the corresponding power transmission distribution coefficient;
And determining a power grid power flow constraint condition of the target region at the predicted time point according to the first power flow and the second power flow.
6. The method of any of claims 1-5, wherein if the generator set comprises a thermal generator set, the second power constraint of the thermal generator set at each of the predicted time points comprises: and the thermal generator set has an upper power limit and a lower power limit to which the power generation scheduling data of the thermal generator set at the predicted time point belong and has an upper power limit and a lower power limit to which the power generation change data of the thermal generator set in unit time belong.
7. The method of any one of claims 1-5, wherein if the generator set comprises an energy storage set, the second power constraint of the energy storage set at each of the predicted time points comprises: and the power upper limit and the lower limit of the power generation power scheduling data of the energy storage unit at the prediction time point and the SOC upper limit and the lower limit of the SOC data of the energy storage unit at the prediction time point.
8. The method of any one of claims 1-5, wherein the obtaining power load prediction data for the target region at a plurality of prediction time points comprises:
And inputting time sequence data related to the power load of the target area into a preset power load prediction model to obtain power load prediction data of the target area, which is output by the preset power load prediction model, at a plurality of prediction time points.
9. The method of claim 8, wherein the timing data comprises at least two of: weather data of the target area, load data of the target area, electricity price data of the target area, policy data of the target area and economic index data of the target area; wherein the policy data is used to indicate an impact on power demand.
10. The method according to any one of claims 1-5, wherein said obtaining power generation prediction data for each wind-solar power generator set in the target area at the plurality of predicted time points comprises:
for each wind-light generator set, inputting time sequence data and non-time sequence data related to the power generated by the wind-light generator set into a preset power prediction model to obtain power generation prediction data of the wind-light generator set, which is output by the preset power prediction model, at a plurality of prediction time points.
11. The method of claim 10, wherein the non-time series data related to the wind turbine generator set generation power comprises: the state data of the wind-light generator set and/or the constraint data of the wind-light generator set; the state data are used for indicating whether the wind-solar generator set operates or not; the constraint data is used for indicating the output power threshold range of the wind-solar generator set;
the time sequence data comprises: weather data of the wind-light generator set and/or operation data of the wind-light generator set.
12. A power grid dispatching apparatus, the apparatus comprising:
the first acquisition module is used for acquiring power load prediction data of the target area at a plurality of prediction time points;
the second acquisition module is used for acquiring the power generation prediction data of each wind-solar generator set in the target area at the plurality of prediction time points;
a scheduling module, configured to:
for each wind-light generator set at each prediction time point, taking the power generation power prediction data of the wind-light generator set at the prediction time point as the maximum power upper limit of the wind-light generator set in a first power constraint condition of the prediction time point, and taking a preset power threshold value as the minimum power lower limit of the wind-light generator set in the first power constraint condition of the prediction time point;
Constructing a power grid power flow constraint condition and a multi-objective function according to the power load prediction data of the plurality of prediction time points; wherein the multiple objective functions include a power gain objective function and a power deviation objective function; wherein the power gain objective function is used for indicating economic benefits of grid operation; the power deviation objective function is used for indicating the power deviation between the power load of the power grid and the power generated by the generator set;
according to the first power constraint conditions of all the wind-solar generator sets at the plurality of prediction time points, the second power constraint conditions of other generator sets in the target area at the plurality of prediction time points and the power grid trend constraint conditions, carrying out optimization solving processing on the multi-objective function to obtain power generation power scheduling data of all the generator sets in the target area at the plurality of prediction time points; the power generation scheduling data of each generator set at each predicted time point is used for controlling the power generation state of each generator set at each predicted time point.
13. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the method of any of claims 1-11 when executing the computer program.
14. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the method of any of claims 1-11.
CN202311246873.6A 2023-09-26 2023-09-26 Power grid dispatching method, device, equipment and storage medium Active CN117277439B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311246873.6A CN117277439B (en) 2023-09-26 2023-09-26 Power grid dispatching method, device, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311246873.6A CN117277439B (en) 2023-09-26 2023-09-26 Power grid dispatching method, device, equipment and storage medium

Publications (2)

Publication Number Publication Date
CN117277439A CN117277439A (en) 2023-12-22
CN117277439B true CN117277439B (en) 2024-03-29

Family

ID=89215585

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311246873.6A Active CN117277439B (en) 2023-09-26 2023-09-26 Power grid dispatching method, device, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN117277439B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2013102932A2 (en) * 2011-12-23 2013-07-11 Mzaya Private Limited System and method facilitating forecasting, optimization and visualization of energy data for an industry
CN115347621A (en) * 2022-08-22 2022-11-15 北京百度网讯科技有限公司 Scheduling method and device of combined power generation system, electronic equipment and medium
CN115600793A (en) * 2022-09-09 2023-01-13 国网浙江省电力有限公司嘉兴供电公司（Cn） Cooperative control method and system for source network load and storage integrated park
CN115714420A (en) * 2022-11-14 2023-02-24 中国华能集团清洁能源技术研究院有限公司 Combined power station operation optimization method and system based on high-precision wind and light output prediction

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2013102932A2 (en) * 2011-12-23 2013-07-11 Mzaya Private Limited System and method facilitating forecasting, optimization and visualization of energy data for an industry
CN115347621A (en) * 2022-08-22 2022-11-15 北京百度网讯科技有限公司 Scheduling method and device of combined power generation system, electronic equipment and medium
CN115600793A (en) * 2022-09-09 2023-01-13 国网浙江省电力有限公司嘉兴供电公司（Cn） Cooperative control method and system for source network load and storage integrated park
CN115714420A (en) * 2022-11-14 2023-02-24 中国华能集团清洁能源技术研究院有限公司 Combined power station operation optimization method and system based on high-precision wind and light output prediction

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
刘星月 ; 喻娜 ; 罗正华 ; .基于粒子群算法的微电网动态经济调度.成都大学学报(自然科学版).2016,(第04期),全文. *
基于粒子群算法的微电网动态经济调度;刘星月;喻娜;罗正华;;成都大学学报(自然科学版)(第04期);全文 *

Also Published As

Publication number Publication date
CN117277439A (en) 2023-12-22

Similar Documents

Publication Publication Date Title
Liu et al. Optimal power peak shaving using hydropower to complement wind and solar power uncertainty
Yan et al. Operation and design optimization of microgrids with renewables
Taggart et al. The future of renewables linked by a transnational Asian grid
Wu et al. A robust wind power optimization method for look-ahead power dispatch
Xu et al. Carbon emission reduction and reliable power supply equilibrium based daily scheduling towards hydro-thermal-wind generation system: A perspective from China
Zheng et al. Bio-inspired optimization of sustainable energy systems: a review
Javad Kasaei et al. Optimal operational scheduling of renewable energy sources using teaching–learning based optimization algorithm by virtual power plant
Cheng et al. Stochastic short-term scheduling of a wind-solar-hydro complementary system considering both the day-ahead market bidding and bilateral contracts decomposition
CN106684915A (en) Wind-hydrogen coupling power generation system optimization method and device thereof
Kharrich et al. Design of hybrid microgrid PV/Wind/Diesel/Battery system: case study for rabat and baghdad
Aliari et al. Planning for integration of wind power capacity in power generation using stochastic optimization
Huang et al. Joint generation and reserve scheduling of wind‐solar‐pumped storage power systems under multiple uncertainties
Petrichenko et al. Modelling the Future of the Baltic Energy Systems: A Green Scenario
Jin et al. A Wasserstein metric-based distributionally robust optimization approach for reliable-economic equilibrium operation of hydro-wind-solar energy systems
CN105678415A (en) Method for predicting net load of distributed power supply power distribution network
Soares et al. Hydro-dominated short-term hydrothermal scheduling via a hybrid simulation-optimisation approach: a case study
Michael et al. Economic scheduling of virtual power plant in day-ahead and real-time markets considering uncertainties in electrical parameters
Aghajani et al. Optimal energy storage sizing and offering strategy for the presence of wind power plant with energy storage in the electricity market
Abedi et al. Risk-constrained unit commitment of power system incorporating PV and wind farms
CN117277439B (en) Power grid dispatching method, device, equipment and storage medium
CN109494794B (en) Regional distributed energy storage optimization scheduling method and device
Salman et al. Optimal Power Systems Planning for IEEE-14 Bus Test System Application
Chudy et al. Mitigation of CO 2 emissions by optimizing energy storage capacity
Alkano et al. Distributed MPC for Power-to-Gas facilities embedded in the energy grids
Verrascina Energy transition of the Sardinia region through energy system modelling with the Calliope framework

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant