CN115276099A - Wind power plant energy storage system flexible control method and device based on artificial intelligence technology - Google Patents
Wind power plant energy storage system flexible control method and device based on artificial intelligence technology Download PDFInfo
- Publication number
- CN115276099A CN115276099A CN202211030872.3A CN202211030872A CN115276099A CN 115276099 A CN115276099 A CN 115276099A CN 202211030872 A CN202211030872 A CN 202211030872A CN 115276099 A CN115276099 A CN 115276099A
- Authority
- CN
- China
- Prior art keywords
- energy storage
- power
- wind
- representing
- loss
- 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.)
- Pending
Links
- 238000004146 energy storage Methods 0.000 title claims abstract description 150
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 24
- 238000005516 engineering process Methods 0.000 title claims abstract description 24
- 238000005457 optimization Methods 0.000 claims abstract description 53
- 238000007599 discharging Methods 0.000 claims abstract description 43
- 238000011217 control strategy Methods 0.000 claims abstract description 22
- 230000005611 electricity Effects 0.000 claims description 54
- 230000006870 function Effects 0.000 claims description 37
- 238000011084 recovery Methods 0.000 claims description 34
- 238000005096 rolling process Methods 0.000 claims description 16
- 238000010276 construction Methods 0.000 claims description 14
- 230000008569 process Effects 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 4
- 239000000126 substance Substances 0.000 claims 1
- 238000010248 power generation Methods 0.000 description 5
- 201000004384 Alopecia Diseases 0.000 description 4
- 208000024963 hair loss Diseases 0.000 description 4
- 230000003676 hair loss Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 230000009467 reduction Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 241000283153 Cetacea Species 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000000739 chaotic effect Effects 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000011664 nicotinic acid Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000000087 stabilizing effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- 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
- H02J3/381—Dispersed generators
-
- 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
- H02J3/32—Arrangements for balancing of the load in a network by storage of energy using batteries with converting means
-
- 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
- H02J2300/28—The renewable source being wind energy
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The application provides a wind power plant energy storage system flexible control method based on an artificial intelligence technology, and relates to the technical field of energy storage control, wherein the method comprises the following steps: acquiring predicted daily data of a wind power plant; taking the spot income maximization as an objective function, and constructing an energy storage optimization decision model according to preset constraint conditions; solving the energy storage optimization decision model according to the prediction daily data to obtain a charge-discharge power sequence; and generating a control strategy according to the charging and discharging power sequence, and controlling the energy storage system according to the control strategy. The technical problems that MPC and robust control are mainly used, advancement is lacked, and market loss and income conditions caused by participation of a wind power plant in spot market trading are not considered in the prior art are solved.
Description
Technical Field
The application relates to the technical field of energy storage control, in particular to a method and a device for flexibly controlling an energy storage system of a wind power plant based on an artificial intelligence technology.
Background
In the scene of the spot market of electric power, the spot market requires that a wind power plant has market cashing capability, if deviation exists between a wind power plant market declaration curve (generally taking a short-term power prediction curve) and a wind power plant actual sending curve, settlement income can be directly influenced, and excessive deviation can also generate 'excess profit recovery' loss. Specifically, when the deviation between the output clear electricity amount and the actual electricity generation amount before a certain point of time exceeds a certain ratio (referred to as a "deviation recovery ratio" or an "excess profit recovery ratio" such as 40%), the electricity amount outside the ratio is correspondingly recovered by the market.
For a wind power plant with an energy storage system, the wind power plant has certain adjusting capacity, but how to flexibly control the energy storage system and further effectively control the actual power of the wind power plant so as to reduce the market assessment loss of the wind power plant and improve the market income becomes a problem to be solved urgently at present.
The existing energy storage control technology generally takes MPC and robust control as main parts, lacks advancement, and has the core aim of stabilizing wind power fluctuation without considering market loss and income conditions caused by participation of a wind power plant in spot market trading.
Disclosure of Invention
The present application is directed to solving, at least in part, one of the technical problems in the related art.
Therefore, the first purpose of the application is to provide a wind power plant energy storage system flexible control method based on an artificial intelligence technology, which solves the technical problems that the existing method generally takes MPC and robust control as main parts, lacks advancement and does not consider market loss and income caused by participation of a wind power plant in spot market trading, and achieves the economic goal of loss reduction and gain under the spot market scene of the wind power plant.
The second purpose of the application is to provide a wind power plant energy storage system flexible control device based on an artificial intelligence technology.
A third object of the present application is to propose a computer device.
In order to achieve the above object, an embodiment of the first aspect of the present application provides a method for flexibly controlling an energy storage system of a wind farm based on an artificial intelligence technology, including: acquiring predicted daily data of a wind power plant; taking the spot income maximization as an objective function, and constructing an energy storage optimization decision model according to preset constraint conditions; solving the energy storage optimization decision model according to the prediction daily data to obtain a charge and discharge power sequence; and generating a control strategy according to the charging and discharging power sequence, and controlling the energy storage system according to the control strategy.
According to the wind power plant energy storage system flexible control method based on the artificial intelligence technology, on the basis of comprehensively considering wind power plant wind power prediction data and deviation rules thereof, historical data of the wind power plant participating in spot market transaction, spot market disclosure data, spot price prediction data, energy storage system operation parameters, spot market assessment rules and transaction rules, an energy storage flexible control model is constructed through an operational optimization method, a real-time control charge-discharge power strategy is provided for the energy storage system, and finally the wind power plant achieves the economic goal of loss reduction gain in a spot market scene.
Optionally, in an embodiment of the present application, the forecast daily data of the wind farm includes a day-ahead output clear electricity amount, short-term wind power forecast data, a base electricity amount, a benchmarking electricity price, day-ahead electricity price forecast data, and real-time electricity price forecast data.
Optionally, in an embodiment of the present application, the method for building an energy storage optimization decision model according to a preset constraint condition with spot profit maximization as an objective function includes:
construction deviation recovery loss and excessive loss;
constructing an energy storage optimization decision model objective function by taking the spot profit maximization as a target according to the deviation recovery loss and the excess loss;
and constructing constraint conditions of an objective function of the energy storage optimization decision model.
Optionally, in one embodiment of the present application, the bias recovery loss is expressed as:
when the predicted power is greater than the wind-storage combined actual maximum output power and the benchmarking electricity price is greater than the real-time electricity price, the generated deviation recovery loss is expressed as:
wherein, J 1 Represents the deviation recovery loss, PI t Denotes predicted power, lambda denotes deviation recovery ratio, pg t Representing combined wind-storage output power, P3 t Representing base output, Q1 t Indicating the price of electricity on the post, Q2 t Representing real-time electricity price, delta t representing time interval of energy storage control, and wind storage combined actual maximum output power Pg t ×(1+λ)；
When the predicted power is less than the wind-storage combined actual minimum output power and the benchmarking electricity price is less than the real-time electricity price, the generated deviation recovery loss is expressed as:
wherein, J 1 Represents the deviation recovery loss, lambda represents the deviation recovery ratio, pg t Representing combined wind-storage output power, P1 t Representing predicted power, P3 t Denotes base contribution, Q2 t Representing real-time electricity prices, Q1 t The price of the electric power of the marker post is represented, delta t represents the time interval of energy storage control, and the actual minimum output power of the wind energy storage combination is Pg t ×(1-λ)；
The excess hair loss is expressed as:
when the predicted power is greater than the wind-storage combined output power and the benchmarking electrovalence is greater than the real-time electrovalence, the generated excess generation loss is expressed as:
wherein, J 2 Indicating excessive hair loss, pg t Representing combined wind-storage output power, P1 t Representing predicted power, Q1 t Indicating the price of the post, Q2 t Representing the real-time electricity prices, deltat representing the time interval of the energy storage control,
the energy storage optimization decision model objective function is expressed as:
wherein, delta (J) 1 +J 2 ) And the difference value of the loss before the energy storage intervention and the loss after the energy storage intervention is represented, U represents the charging and discharging times in the total data time quantity, and L represents the total time quantity corresponding to the data.
Optionally, in an embodiment of the present application, the constraint conditions of the objective function of the energy storage optimization decision model include a battery capacity limit constraint, a rated power constraint, a power-electricity equation constraint, a wind-storage combined output power equation constraint, and a charge-discharge power fluctuation constraint, wherein,
the battery capacity limit constraint is expressed as:
S t ∈[0，S]t＝1，2，...，T
wherein, S t Is the battery capacity at the T-th moment, S is the rated capacity of the energy storage battery, T is the total time of energy storage control,
the rated power constraint is expressed as:
P ESS，t ∈[-P，P]t＝1，2，...，T
wherein, P ESS，t The charging and discharging power of the battery at each moment, P is the rated power of the energy storage battery, T is the total time of energy storage control,
the power-to-charge equality constraint is expressed as:
u t ＝P ESS，t Δt t＝1，2，...，T
wherein u is t Is the charge and discharge capacity of the battery at the t moment ESS，t For each moment of the battery charge and discharge power, delta T is the time interval of energy storage control, T is the total time of energy storage control,
the wind-storage combined output power equality constraint is expressed as:
Pg t ＝P2 t -P ESS，t t＝1，2，...，T
wherein Pg t Representing combined wind-storage output power, P2 t Representing the actual power, P, of the wind farm ESS，t The battery charge-discharge power is measured at each moment, T is the total time of energy storage control,
the charge-discharge power fluctuation constraint is expressed as:
wherein, P ESS，t The charging and discharging power of the energy storage system at the T +1 th moment, beta is a fluctuation limiting coefficient, and T is the total time of energy storage control.
Optionally, in an embodiment of the application, solving the energy storage optimization decision model according to the data of the prediction day to obtain a charge and discharge power sequence includes:
constructing an actual constraint condition of an objective function of an energy storage optimization decision model based on the prediction daily data;
and (4) optimizing based on actual constraint conditions by taking the objective function as an optimization target to obtain an optimal charging and discharging sequence.
Alternatively, in one embodiment of the present application, further comprising:
in the flexible control process of wind power energy storage, a rolling optimization method is adopted, and a charging and discharging operation control strategy of advanced mode energy storage is executed in a forward rolling real-time manner;
wherein the scrolling is optimized as follows:
optimizing the charge-discharge strategies at all the moments in the period of the next moment;
adjusting the charge and discharge strategy at the next moment according to the charge and discharge strategy;
and when the adjusted charging and discharging strategy is executed at the next moment, optimizing the strategy at the future moment according to the latest actual data, thereby continuously optimizing and correcting the actual charging and discharging strategy in a rolling way.
In order to achieve the above object, a second aspect of the present invention provides a flexible control device for a wind farm energy storage system based on an artificial intelligence technology, which includes a data acquisition module, a model construction module, a model solution module, and a control module, wherein the data acquisition module, the model construction module, the model solution module, and the control module are included in the flexible control device
The data acquisition module is used for acquiring the predicted day data of the wind power plant;
the model construction module is used for constructing an energy storage optimization decision model according to preset constraint conditions by taking the spot income maximization as a target function;
the model solving module is used for solving the energy storage optimization decision model according to the prediction day data to obtain a charging and discharging power sequence;
and the control module is used for generating a control strategy according to the charging and discharging power sequence and controlling the energy storage system according to the control strategy.
Optionally, in an embodiment of the present application, the model building module is specifically configured to:
construction deviation recovery loss and excessive loss;
constructing an energy storage optimization decision model objective function by taking the spot profit maximization as a target according to the deviation recovery loss and the excess delivery loss;
and constructing constraint conditions of an objective function of the energy storage optimization decision model.
To achieve the above object, a third embodiment of the present invention provides a computer device, including: a processor; a memory for storing the processor-executable instructions; when the processor executes the executable instructions in the memory, the method for flexibly controlling the wind power plant energy storage system based on the artificial intelligence technology is realized.
Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.
Drawings
The above and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 is a schematic flow chart of a method for flexibly controlling a wind farm energy storage system based on an artificial intelligence technology according to a first embodiment of the present application;
FIG. 2 is a flowchart of an IWOA algorithm according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of a flexible control device of a wind farm energy storage system based on an artificial intelligence technology according to an embodiment of the present application.
Detailed Description
Reference will now be made in detail to the embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the drawings are exemplary and intended to be used for explaining the present application and should not be construed as limiting the present application.
The method and the device for flexibly controlling the energy storage system of the wind power plant based on the artificial intelligence technology are described below with reference to the accompanying drawings.
Fig. 1 is a schematic flow chart of a method for flexibly controlling a wind farm energy storage system based on an artificial intelligence technology according to an embodiment of the present application.
As shown in FIG. 1, the method for flexibly controlling the energy storage system of the wind farm based on the artificial intelligence technology comprises the following steps:
103, solving the energy storage optimization decision model according to the data on the prediction day to obtain a charge-discharge power sequence;
and 104, generating a control strategy according to the charging and discharging power sequence, and controlling the energy storage system according to the control strategy.
According to the method for flexibly controlling the energy storage system of the wind power plant based on the artificial intelligence technology, on the basis of comprehensively considering wind power plant wind power prediction data and deviation rules thereof, historical data of the wind power plant participating in spot market transaction, spot market disclosure data, spot price prediction data, energy storage system operation parameters, spot market examination rules and transaction rules, an energy storage flexible control model is constructed through an operation optimization method, a real-time control charge-discharge power strategy is provided for the energy storage system, and finally the economic goal of loss reduction gain of the wind power plant in a spot market scene is achieved.
Optionally, in an embodiment of the present application, the forecast day (also referred to as D day, wind farm control day) data of the wind farm, including 6 types of the day-ahead clear electricity quantity, the ultra-short term wind power forecast data, the base electricity quantity, the benchmarking electricity price, the day-ahead electricity price forecast data, and the real-time electricity price forecast data, are used together as boundary data of the energy storage flexible control decision, specifically:
1) The fresh electric quantity before the day: it is generally released at 20 pm on the previous day (D-1 day);
2) Ultra-short term wind power prediction data: on the basis of original ultra-short-term wind power prediction data from a wind power prediction system, corrected ultra-short-term power prediction data are obtained by using a power prediction lifting system and serve as one of core boundaries of an energy storage flexible control strategy;
3) Cardinal number of electric quantities: it is generally released at 20 pm on the previous day (D-1 day);
4) Post price of electricity: the price of the current post in Shanxi province is 332 yuan/MWH;
5) Day-ahead electricity price prediction data: the load rate sectional type day-ahead electricity price prediction algorithm is adopted to predict the day-ahead electricity price, the accuracy of the day-ahead electricity price prediction in a high price section and a low price section is improved by predicting the day-ahead electricity price through the load rate data characteristics, the problem of integral deviation of the prediction result caused by nonlinear regression is effectively avoided, and the prediction result of the day-ahead electricity price of 96 points is finally obtained and is used as one of the core boundaries of the energy storage flexible control strategy;
6) Real-time electricity price prediction data: the real-time price prediction is carried out by adopting a rolling type real-time price prediction algorithm, and the price difference between the current price and the real-time electricity price is used as important characteristic data of the real-time electricity price prediction, so that the prediction accuracy of the real-time electricity price is greatly improved, the prediction result of the 96-point real-time electricity price is finally obtained, and more accurate and reliable boundary conditions are provided for the energy storage flexible control strategy algorithm.
Optionally, in an embodiment of the present application, the building an energy storage optimization decision model according to a preset constraint condition with spot revenue maximization as an objective function includes:
in the electric power spot-purchase trading market, the difference between the actual power generation amount and the day-ahead output clear power amount can cause wind power loss, and the wind power loss comprises deviation recovery loss and excess loss;
based on deviation recovery loss and excessive loss, an energy storage optimization decision model objective function is established by taking unit charge-discharge profit maximization as a target after an energy storage system is intervened;
and constructing a constraint condition of the energy storage optimization decision model objective function.
Optionally, in one embodiment of the present application, the bias recovery loss is expressed as:
when P1 is present t ＞Pg t X (1 + lambda) and Q 1 ＞Q 2 The deviation generated during the process is recovered and lost J 1 The settlement formula is as follows: :
wherein, J 1 Represents the bias recovery loss, P1 t The predicted power is represented, corrected ultra-short-term power prediction data is obtained from a power prediction and promotion system, lambda represents deviation recovery ratio, and Pg t Representing combined wind-storage output power, P3 t Denotes the base contribution, Q1 t Electric indicating postValence, Q2 t Representing real-time electricity price from a price prediction system based on a rolling type real-time price prediction algorithm, wherein delta t represents an energy storage control time interval, and the actual maximum output power of the wind energy storage combination is Pg t ×(1+λ)；
When P1 is present t <Pg t X (1-. Lambda.) and Q 2 ＞Q 1 The deviation generated during the process is recovered and lost J 1 Expressed as:
wherein, J 1 Represents the bias recovery loss, P1 t Denotes predicted power, lambda denotes deviation recovery ratio, pg t Representing combined wind-storage output power, P3 t Representing base output, Q1 t Indicating the price of electricity on the post, Q2 t Representing real-time electricity price, delta t representing time interval of energy storage control, and actual minimum output power of wind storage combination Pg t ×(1-λ)；
The excess hair loss is expressed as:
when P1 is present t <Pg t And Q 1 ＞Q 2 Time-to-time, excessive loss J 2 Expressed as:
wherein, J 2 Indicating excess hair loss, pg t Representing combined wind-storage output power, P1 t Representing predicted power, Q1 t Indicating the price of electricity on the post, Q2 t Representing the real-time electricity prices, at represents the time interval of the energy storage control,
the energy storage optimization decision model objective function is expressed as:
wherein, Δ (J) 1 +J 2 ) Representing loss before and intervention of stored energyAnd the subsequent loss difference, U represents the charging and discharging times in the total number of data moments, L represents the total number of data corresponding moments, and the time is every 15 minutes.
Optionally, in an embodiment of the present application, in combination with physical constraints of the energy storage system and actual wind power generation scenarios, the artificial intelligence flexible control strategy method needs to consider constraints such as a battery capacity limit constraint, a rated power constraint, a power-electricity equation constraint, a battery charging and discharging power fluctuation constraint, and the like, wherein,
1) Battery capacity limit constraints
Assuming that S is the rated capacity of the energy storage battery and the initial time capacity of the battery is S 0 The battery capacity at the t-th time is S t And at each moment, the remaining available capacity of the battery does not exceed the maximum capacity of the battery and is not lower than the minimum remaining available capacity of the battery:
S t ∈[0，S]t＝1，2，...，T
wherein S is t Is the battery capacity at the T-th moment, S is the rated capacity of the energy storage battery, T is the total time of energy storage control,
2) Power rating constraint
Suppose P is the rated power of the energy storage battery and the capacity of the battery at the t +1 time is S t+1 ＝S t +u t The battery capacity at each time fluctuates within the maximum and minimum capacity of the battery as a battery capacity limit constraint, i.e., the battery charge-discharge power P at each time ESS，t Size is constrained by power Chi Eding:
P ESS，t ∈[-P，P]t＝1，2，...，T
wherein, P ESS，t The charging and discharging power of the battery at each moment, P is the rated power of the energy storage battery, T is the total time of energy storage control,
3) Power-to-power equality constraint
Suppose the time interval of the energy storage control is Δ t, and the charge/discharge capacity of the battery at the t-th time is u t U during charging t Is positive, u at discharge t Is negative, and the charge and discharge capacity of the battery is the same as that of the batteryThe equation for the discharge power is constrained as follows:
u t ＝P ESS，t Δt t＝1，2，...，T
wherein u is t Is the charge and discharge capacity of the battery at the t moment ESS，t For the charging and discharging power of the battery at each moment, delta T is the time interval of energy storage control, T is the total time of energy storage control,
4) Wind-storage combined output power equality constraint
The wind-storage combined output power is equal to the real power of the wind power plant minus the charging and discharging power of the energy storage system:
Pg t ＝P2 t -P ESS，t t＝1，2，...，T
wherein Pg t Representing combined wind-storage output power, P2 t Representing wind farm actual power, P ESS，t For each moment of time, the battery charge and discharge power, T is the total time of energy storage control,
when the charging and discharging power of the energy storage system is negative, energy storage discharging is represented; when the charging and discharging power of the energy storage system is positive, energy storage charging is represented. The charging of the energy storage system indicates that redundant power generation of the wind power plant is stored and utilized, and the actual power generation of the wind power plant is reduced; the energy storage system discharges to release part of battery electric quantity, so that the actual generating capacity of the wind power plant is increased.
5) Charge-discharge power fluctuation constraint
Meanwhile, in order to ensure stable operation, the power at the t moment and the power at the t +1 moment must meet the fluctuation requirement and serve as the battery charging and discharging power fluctuation constraint:
|P ESS，t+1 -P ESS，t |≤β|P ESS，t |t＝1，2，...，T-1
wherein, P ESS，t The charging and discharging power of the energy storage system at the T +1 th moment, beta is a fluctuation limiting coefficient, and T is the total time of energy storage control.
Optionally, in an embodiment of the present application, solving the energy storage optimization decision model according to the data on the prediction day to obtain a charge-discharge power sequence includes:
after the objective function and the constraint equation are determined, according to historical power generation data of a wind power plant, an advanced bionic intelligent optimization algorithm is adopted, in the process of flexible wind power energy storage control, the unit charging and discharging income is maximized to be the objective function, constraint conditions such as battery capacity limit constraint, rated power constraint, power and electric quantity equality constraint, battery charging and discharging power fluctuation constraint and the like are considered, and finally, an improved whale algorithm (improved cabin optimization algorithm, IWOA, a flow chart shown in figure 2) is adopted to calculate the charging and discharging sequence with the optimal economy of the energy storage system.
1) And the generation of the initial population is completed by utilizing the better traversal uniformity of the cubic chaotic mapping.
2) In order to enhance the diversity of the population and the global search capability of the algorithm, a chaos variation strategy is applied to the optimal candidate solution in the population by utilizing a regression model, namely Logistoc chaos mapping.
3) In order to better balance the local search and global search capabilities of the algorithm, a fixed search value A is set c When A is not less than A c Global searches are performed when, otherwise, local searches are performed. The method is characterized in that the optimization search is guided by the cooperation and competition of individuals in the differential evolution algorithm, the spiral motion and the linear motion are respectively carried out, and the updating mode is shown in the following formula.
Wherein t represents the number of iterations; x t Is the position vector of the current solution; b is a logarithmic spiral constant; l is [ -1,1]A random number in between;
solving a random candidate solution i in the current population;
representing a current optimal solution position vector; a and C are weight coefficients, are related to the current iteration number and are defined as follows:
optionally, in an embodiment of the present application, the method further includes:
and (3) taking 6 types of data boundaries including the current clear electricity quantity, the ultra-short term wind power prediction data, the base electricity quantity, the benchmarking electricity price, the current electricity price prediction data and the real-time electricity price prediction data in a future period into consideration, calling an energy storage optimization decision model to obtain a charging and discharging sequence curve with optimal economy, and issuing a next charging and discharging power instruction in the sequence to an energy storage system for execution. When energy storage optimization decision is made, in a period of time in the future, if the real-time electricity price prediction at some moment is higher, the energy storage system tends to be charged in advance so as to earn more benefits; if the real-time electricity price prediction is low at some time, the energy storage system tends to discharge ahead of time to recover some of the losses.
In the flexible control process of wind power energy storage, a rolling optimization method is adopted, and a charging and discharging operation control strategy of advanced mode energy storage is executed in a forward rolling real-time manner. The pre-arrangement of each stage and the next stage in the comparison period are organically connected, the charging and discharging strategies at all the moments in the period of the next moment are optimized in a rolling mode, but only the charging and discharging strategy at the next moment is actually adjusted, the strategy at the future moment is optimized by the latest actual data at the next moment, and the actual charging and discharging strategies are continuously corrected in a rolling mode.
Assuming that the energy storage optimization decision model is f, the charge-discharge strategy in the time window L at the t-th moment can be represented as:
P ESS，t～t+L ＝f(P1 t ，P1 t+1 ，...，P1 t+L ，
P2 t ，P2 t+1 ，...，P2 t+L ，
P3 t ，P3 t+1 ，...，P3 t+L ，
Q1 t ，Q1 t+1 ，...，，Q1 t+L ，
Q2 t ，Q2 t+1 ，...，Q2 t+L )
in the flexible control process of wind power energy storage, a rolling optimization method is adopted, and a charging and discharging operation control strategy of advanced mode energy storage is executed in a forward rolling real-time manner. The pre-arrangement of each stage and the next period in the comparison period are organically connected, the charging and discharging strategies at all the moments in the period of the next moment are optimized in a rolling mode, only the charging and discharging strategy at the next moment is actually adjusted, the strategy at the future moment is optimized by the latest actual data at the next moment, and the actual charging and discharging strategies are continuously corrected in a rolling mode.
In order to realize the embodiment, the application further provides a wind power plant energy storage system flexible control device based on the artificial intelligence technology.
Fig. 3 is a schematic structural diagram of a flexible control device of a wind farm energy storage system based on an artificial intelligence technology according to an embodiment of the present application.
As shown in FIG. 3, the flexible control device for the energy storage system of the wind farm based on the artificial intelligence technology comprises a data acquisition module, a model construction module, a model solving module and a control module, wherein the data acquisition module, the model construction module, the model solving module and the control module are arranged in the flexible control device
The data acquisition module is used for acquiring the predicted day data of the wind power plant;
the model construction module is used for constructing an energy storage optimization decision model according to preset constraint conditions by taking the spot income maximization as a target function;
the model solving module is used for solving the energy storage optimization decision model according to the prediction day data to obtain a charge-discharge power sequence;
and the control module is used for generating a control strategy according to the charging and discharging power sequence and controlling the energy storage system according to the control strategy.
Optionally, in an embodiment of the present application, the model building module is specifically configured to:
construction deviation recovery loss and excessive loss;
constructing an energy storage optimization decision model objective function by taking the spot profit maximization as a target according to the deviation recovery loss and the excess delivery loss;
and constructing constraint conditions of an objective function of the energy storage optimization decision model.
It should be noted that the explanation of the embodiment of the method for flexibly controlling the energy storage system of the wind farm based on the artificial intelligence technology is also applicable to the device for flexibly controlling the energy storage system of the wind farm based on the artificial intelligence technology of the embodiment, and is not repeated herein.
In order to implement the foregoing embodiments, the present invention further provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the method described in the foregoing embodiments is implemented.
In the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Moreover, various embodiments or examples and features of various embodiments or examples described in this specification can be combined and combined by one skilled in the art without being mutually inconsistent.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present application, "plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing steps of a custom logic function or process, and alternate implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present application.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present application may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc. Although embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application, and that variations, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.
Claims (10)
1. A wind power plant energy storage system flexible control method based on an artificial intelligence technology is characterized by comprising the following steps:
acquiring predicted daily data of a wind power plant;
taking the spot income maximization as an objective function, and constructing an energy storage optimization decision model according to preset constraint conditions;
solving the energy storage optimization decision model according to the prediction daily data to obtain a charge-discharge power sequence;
and generating a control strategy according to the charging and discharging power sequence, and controlling the energy storage system according to the control strategy.
2. The method of claim 1, wherein the predicted daily data for the wind farm includes a day ahead amount of clear power, short term wind power prediction data, base number amount of power, benchmarking power rates, day ahead power rate prediction data, real time power rate prediction data.
3. The method of claim 1, wherein the building of the energy storage optimization decision model according to the preset constraint condition with the spot revenue maximization as an objective function comprises:
construction deviation recovery loss and excessive loss;
constructing an energy storage optimization decision model objective function by taking the spot profit maximization as a target according to the deviation recovery loss and the excess loss;
and constructing a constraint condition of the energy storage optimization decision model objective function.
4. The method of claim 3, wherein the bias recovery loss is expressed as:
when the predicted power is greater than the wind-storage combined actual maximum output power and the benchmarking electricity price is greater than the real-time electricity price, the generated deviation recovery loss is expressed as:
wherein, J 1 Represents the bias recovery loss, P1 t Denotes the predicted power, lambda denotes the deviation recovery ratio, pg t Representing combined wind-storage output power, P3 t Representing base output, Q1 t Indicating the price of electricity on the post, Q2 t Representing the real-time electricity price, delta t representing the time interval of energy storage control, and the wind storage combined actual maximum output power being
When the predicted power is less than the wind-storage combined actual minimum output power and the benchmarking electricity price is less than the real-time electricity price, the generated deviation recovery loss is expressed as:
wherein, J 1 Denotes the deviation recovery loss, lambda denotes the deviation recovery ratio, pg t Representing combined wind-storage output power, P1 t Representing predicted power, P3 t Representing base output, Q2 t Representing real-time electricity prices, Q1 t Representing the price of the electric pole, delta t representing the time interval of energy storage control, and the wind storage combined actual minimum output power being
The excess loss is expressed as:
when the predicted power is greater than the wind-storage combined output power and the benchmarking electrovalence is greater than the real-time electrovalence, the generated excess generation loss is expressed as:
wherein, J 2 The loss of the excessive hair is shown,
representing combined wind-storage output power, P1 t Representing predicted power, Q1 t Indicating the price of electricity on the post, Q2 t Representing the real-time electricity prices, at represents the time interval of the energy storage control,
the energy storage optimization decision model objective function is expressed as:
wherein, delta (J) 1 +J 2 ) The difference value between the loss before the intervention of the energy storage and the loss after the intervention of the energy storage is represented, U represents the charging and discharging times in the total number of data moments, and L represents the total number of the moments corresponding to the data.
5. The method of claim 3, wherein the constraints of the energy storage optimization decision model objective function include a battery capacity limit constraint, a rated power constraint, a power-to-electricity equality constraint, a wind-storage combined output power equality constraint, a charge-discharge power volatility constraint, wherein,
the battery capacity limit constraint is expressed as:
S t ∈[0，S] t＝1，2，...，T
wherein S is t Is the battery capacity at the T-th moment, S is the rated capacity of the energy storage battery, T is the total time of energy storage control,
the rated power constraint is expressed as:
P ESS，t ∈[-P，P] t＝1，2，...，T
wherein, P ESS，t The charging and discharging power of the battery at each moment, P is the rated power of the energy storage battery, T is the total time of energy storage control,
the power-to-electricity equality constraint is expressed as:
u t ＝P ESS，t Δt t＝1，2，...，T
wherein u is t Is the charge and discharge capacity of the battery at the t moment, P ESS，t For each moment of the battery charge and discharge power, delta T is the time interval of energy storage control, T is the total time of energy storage control,
the wind-storage combined output power equality constraint is expressed as:
wherein the content of the first and second substances,
representing combined wind-storage output power, P2 t Representing the actual power, P, of the wind farm ESS，t For each moment of time, the battery charge and discharge power, T is the total time of energy storage control,
the charge-discharge power fluctuation constraint is expressed as:
|P ESS，t+1 -P ESS，t |≤β|P ESS，t |t＝1，2，...，T-1
wherein, P ESS，t The charging and discharging power of the energy storage system at the T +1 th moment, beta is a fluctuation limiting coefficient, and T is the total time of energy storage control.
6. The method of claim 2 or 3, wherein solving the energy storage optimization decision model according to the daily prediction data to obtain a charge-discharge power sequence comprises:
constructing an actual constraint condition of the energy storage optimization decision model objective function based on the prediction daily data;
and optimizing based on the actual constraint condition by taking the objective function as an optimization target to obtain an optimal charging and discharging sequence.
7. The method of claim 1, further comprising:
in the flexible control process of wind power energy storage, a rolling optimization method is adopted, and a charging and discharging operation control strategy of advanced mode energy storage is executed in a forward rolling real-time manner;
wherein the scrolling is optimized as:
optimizing the charge-discharge strategies at all the moments in the period of the next moment;
adjusting the charge and discharge strategy at the next moment according to the charge and discharge strategy;
and when the adjusted charging and discharging strategy is executed at the next moment, optimizing the strategy at the future moment according to the latest actual data, thereby continuously optimizing and correcting the actual charging and discharging strategy in a rolling way.
8. The device for flexibly controlling the energy storage system of the wind power plant based on the artificial intelligence technology is characterized by comprising a data acquisition module, a model construction module, a model solving module and a control module, wherein the data acquisition module, the model construction module, the model solving module and the control module are arranged in the wind power plant
The data acquisition module is used for acquiring the predicted day data of the wind power plant;
the model construction module is used for constructing an energy storage optimization decision model according to preset constraint conditions by taking the spot income maximization as a target function;
the model solving module is used for solving the energy storage optimization decision model according to the prediction day data to obtain a charge-discharge power sequence;
and the control module is used for generating a control strategy according to the charging and discharging power sequence and controlling the energy storage system according to the control strategy.
9. The apparatus of claim 8, wherein the model building module is specifically configured to:
construction deviation recovery loss and excessive loss;
constructing an energy storage optimization decision model objective function by taking the spot profit maximization as a target according to the deviation recovery loss and the excess loss;
and constructing a constraint condition of the energy storage optimization decision model objective function.
10. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method of any one of claims 1-7 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211030872.3A CN115276099A (en) | 2022-08-26 | 2022-08-26 | Wind power plant energy storage system flexible control method and device based on artificial intelligence technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211030872.3A CN115276099A (en) | 2022-08-26 | 2022-08-26 | Wind power plant energy storage system flexible control method and device based on artificial intelligence technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115276099A true CN115276099A (en) | 2022-11-01 |
Family
ID=83755369
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211030872.3A Pending CN115276099A (en) | 2022-08-26 | 2022-08-26 | Wind power plant energy storage system flexible control method and device based on artificial intelligence technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115276099A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112531751A (en) * | 2020-12-04 | 2021-03-19 | 西安峰频能源科技有限公司 | Method for establishing flexible control wind power energy storage strategy model |
| CN112653142A (en) * | 2020-12-18 | 2021-04-13 | 武汉大学 | Wind power prediction method and system for optimizing depth transform network |
| CN114188987A (en) * | 2021-12-03 | 2022-03-15 | 国网新疆电力有限公司电力科学研究院 | Shared energy storage optimal configuration method of large-scale renewable energy source sending end system |
| CN114493222A (en) * | 2022-01-18 | 2022-05-13 | 中广核风电有限公司 | Wind power plant energy storage power station multi-market participation strategy considering output prediction and price |
-
2022
- 2022-08-26 CN CN202211030872.3A patent/CN115276099A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112531751A (en) * | 2020-12-04 | 2021-03-19 | 西安峰频能源科技有限公司 | Method for establishing flexible control wind power energy storage strategy model |
| CN112653142A (en) * | 2020-12-18 | 2021-04-13 | 武汉大学 | Wind power prediction method and system for optimizing depth transform network |
| CN114188987A (en) * | 2021-12-03 | 2022-03-15 | 国网新疆电力有限公司电力科学研究院 | Shared energy storage optimal configuration method of large-scale renewable energy source sending end system |
| CN114493222A (en) * | 2022-01-18 | 2022-05-13 | 中广核风电有限公司 | Wind power plant energy storage power station multi-market participation strategy considering output prediction and price |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2017000853A1 (en) | Active power distribution network multi-time scale coordinated optimization scheduling method and storage medium | |
| CN110165698B (en) | Wind power plant smooth grid-connection method for realizing prospective error asset conversion | |
| CN115102202B (en) | Energy storage control method based on rolling type real-time electricity price prediction | |
| CN112001528A (en) | Optimal bidding method and system for wind storage combined participation in energy-frequency modulation market | |
| CN115511634A (en) | New energy day-ahead transaction decision-making method and device for electricity market based on settlement income | |
| CN112785435A (en) | Model for assisting unit to quote in spot transaction declaration | |
| CN111476647A (en) | Energy storage aggregator bidding method based on worst condition risk value | |
| CN115276099A (en) | Wind power plant energy storage system flexible control method and device based on artificial intelligence technology | |
| CN112531751B (en) | Method for establishing flexible control wind power energy storage strategy model | |
| CN108631368B (en) | Energy storage configuration method considering wind storage system joint scheduling under energy storage operation loss | |
| CN113437757B (en) | Electric quantity decomposition method of wind-storage combined system based on prospect theory | |
| CN115117886A (en) | Energy storage control method and device for wind power plant and storage medium | |
| CN115912420A (en) | Wind power collection area energy storage optimization configuration method considering cycle life and operation strategy | |
| CN115693741A (en) | Energy storage optimization method for distributed photovoltaic and energy storage system and electronic equipment | |
| CN113935182A (en) | Quantitative battery life attenuation prediction method based on mixed integer programming model | |
| CN113555887A (en) | Power grid energy control method and device, electronic equipment and storage medium | |
| CN117728465A (en) | Energy storage power station operation control method and device considering battery life cycle | |
| CN115378006A (en) | Multi-target wind storage flexible control method and device in spot-cargo scene | |
| CN115310708A (en) | Method and device for selecting wind power plant energy storage power prediction time window of ant colony algorithm | |
| CN115663921B (en) | Method and system for determining regulation and control plan of wind-solar storage and charging micro-grid | |
| Bakhtvar et al. | Dispatching of the Hybrid Renewable Energy Systems | |
| CN114336591B (en) | Comprehensive optimization configuration method for hybrid energy storage of wind farm | |
| CN114709854A (en) | Charge state adjusting method and device for jointly participating in frequency modulation through energy storage and thermal power | |
| CN117394404A (en) | Wind power plant energy storage capacity configuration method considering carbon benefit and auxiliary frequency modulation | |
| CN117013582A (en) | Wind-storage combined system charge-discharge optimization decision-making method based on rolling optimization |
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 |