CN114156951B - Control optimization method and device of source network load storage system - Google Patents

Control optimization method and device of source network load storage system Download PDF

Info

Publication number
CN114156951B
CN114156951B CN202210123395.9A CN202210123395A CN114156951B CN 114156951 B CN114156951 B CN 114156951B CN 202210123395 A CN202210123395 A CN 202210123395A CN 114156951 B CN114156951 B CN 114156951B
Authority
CN
China
Prior art keywords
power generation
load
day
controlled
optimization
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
CN202210123395.9A
Other languages
Chinese (zh)
Other versions
CN114156951A (en
Inventor
乔匡华
邢至珏
景晨英
邢敬创
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.)
Xi'an Si'an Yunchuang Technology Co ltd
Original Assignee
Xi'an Si'an Yunchuang 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 Xi'an Si'an Yunchuang Technology Co ltd filed Critical Xi'an Si'an Yunchuang Technology Co ltd
Priority to CN202210123395.9A priority Critical patent/CN114156951B/en
Publication of CN114156951A publication Critical patent/CN114156951A/en
Application granted granted Critical
Publication of CN114156951B publication Critical patent/CN114156951B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • H02J3/46—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
    • H02J15/00—Systems for storing electric 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
    • H02J3/12—Circuit arrangements for ac mains or ac distribution networks for adjusting voltage in ac networks by changing a characteristic of the network load
    • H02J3/14—Circuit arrangements for ac mains or ac distribution networks for adjusting voltage in ac networks by changing a characteristic of the network load by switching loads on to, or off from, network, e.g. progressively balanced loading
    • H02J3/144—Demand-response operation of the power transmission or distribution network
    • 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
    • H02J2300/22—The renewable source being solar energy
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
    • Y02B70/00—Technologies for an efficient end-user side electric power management and consumption
    • Y02B70/30—Systems integrating technologies related to power network operation and communication or information technologies for improving the carbon footprint of the management of residential or tertiary loads, i.e. smart grids as climate change mitigation technology in the buildings sector, including also the last stages of power distribution and the control, monitoring or operating management systems at local level
    • Y02B70/3225—Demand response systems, e.g. load shedding, peak shaving
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S20/00—Management or operation of end-user stationary applications or the last stages of power distribution; Controlling, monitoring or operating thereof
    • Y04S20/20—End-user application control systems
    • Y04S20/222—Demand response systems, e.g. load shedding, peak shaving

Landscapes

  • Engineering & Computer Science (AREA)
  • Power Engineering (AREA)
  • Supply And Distribution Of Alternating Current (AREA)

Abstract

The invention discloses a control optimization method and a control optimization device for a source network load storage system, which are used for acquiring a weather state and a first temperature of an optimization day to be controlled and predicting an electrical load of the optimization day to be controlled by combining the weather state, the first temperature and a historical electrical load; acquiring the date, the illumination intensity and the second temperature of the optimization day to be controlled, and predicting the photovoltaic power generation amount of the optimization day to be controlled according to the date, the illumination intensity and the second temperature; calculating a non-absorption compensation time period of the optimization day to be controlled according to the power load and the photovoltaic power generation amount of the optimization day to be controlled and the predicted waste heat power generation amount of the waste heat storage power generation system; in the non-absorption compensation time period, constructing an objective function by taking the minimization of the running cost of the source network charge storage system as a target and solving to obtain the waste heat generating capacity, the charge-discharge state of the energy storage battery and the power consumption of the flexible load in the non-absorption compensation time period; the invention can optimize the scheduling problem of the power system, improve the economic benefit and avoid energy waste.

Description

Control optimization method and device of source network load storage system
Technical Field
The invention belongs to the technical field of optimization methods of electric energy storage systems, and particularly relates to a control optimization method and device of a source network load storage system.
Background
The source network charge storage system is a special form of an electric energy storage system, and the coordinated utilization of the system resources is an important means for promoting the efficient operation of a regional electric heating comprehensive energy system. With the development of renewable energy power generation, direct current transmission, electric energy storage and other technologies, flexible loads such as new energy power generation and electric vehicles and chargeable and dischargeable energy storage devices are continuously incorporated into a power grid, so that the traditional power distribution network architecture is changed greatly. Due to the large instability of the new source network load storage, great challenges are brought to the power distribution network scheduling, and particularly, extra power loss of the scheduling is difficult to control.
At present, related researches on optimal scheduling of a power distribution network are few, and especially, a method for optimal scheduling of a power distribution network containing renewable energy power generation needs to be further researched. Meanwhile, due to the fact that the operation condition is variable and the system structure is complex, the common control method usually has the problems, such as energy waste caused by insufficient utilization of generated energy and the like.
Disclosure of Invention
The invention aims to provide a control optimization method and device for a source network load storage system, which can optimize the scheduling problem of a power system, improve the economic benefit and avoid energy waste by using means of establishing various optimization models, establishing objective functions and the like.
The invention adopts the following technical scheme: a control optimization method for a source network charge-storage system is disclosed, wherein a power supply system in the source network charge-storage system comprises a photovoltaic power generation system, a waste heat storage power generation system and an energy storage battery system, and the source network charge-storage system comprises a flexible load; the control optimization method specifically comprises the following steps:
acquiring a weather state and a first temperature of an optimized day to be controlled, and predicting the electrical load of the optimized day to be controlled by combining the weather state, the first temperature and the historical electrical load;
acquiring the date, the illumination intensity and the second temperature of the optimization day to be controlled, and predicting the photovoltaic power generation amount of the optimization day to be controlled according to the date, the illumination intensity and the second temperature;
calculating a non-absorption compensation time period of the optimization day to be controlled according to the power load and the photovoltaic power generation amount of the optimization day to be controlled and the predicted waste heat power generation amount of the waste heat storage power generation system;
and in the non-absorption compensation time period, constructing an objective function by taking the minimization of the operating cost of the source network charge storage system as a target and solving to obtain the waste heat generating capacity, the charge-discharge state of the energy storage battery and the power consumption of the flexible load in the non-absorption compensation time period.
Further, the objective function is:
Figure 442303DEST_PATH_IMAGE001
，
wherein the content of the first and second substances,
Figure 890602DEST_PATH_IMAGE002
for the operating cost of the source network load-store system,
Figure 952230DEST_PATH_IMAGE003
in order to not absorb the compensation period of time,
Figure 878597DEST_PATH_IMAGE004
for the time within the non-absorption compensation period,
Figure 958549DEST_PATH_IMAGE005
，
Figure 312170DEST_PATH_IMAGE006
is composed oftThe cost of photovoltaic power generation at the time of day,
Figure 844782DEST_PATH_IMAGE007
is composed oftThe waste heat is stored for generating electricity at any moment,
Figure 309262DEST_PATH_IMAGE008
is composed oftThe cost of the energy stored at the moment,
Figure 257102DEST_PATH_IMAGE009
is composed oftThe network loss cost of the source network load storage system at the moment,
Figure 516045DEST_PATH_IMAGE010
is composed oftMoment flexible load compensation cost;
the constraint conditions of the objective function comprise power balance constraint, energy storage system constraint, waste heat storage power generation system constraint and electricity price constraint.
Further, predicting the electrical load of the optimal day to be controlled in combination with the weather state, the first temperature and the historical electrical load comprises:
and predicting the power load of the optimization day to be controlled by adopting a BP neural network model by taking the weather state, the first temperature and the historical power load as input information.
Further, predicting the electrical load of the optimal day to be controlled by combining the weather state, the first temperature and the historical electrical load further comprises:
sampling a weather state, a first temperature and a historical electric load to obtain a plurality of sampling point data sets;
inputting a plurality of sampling point data sets into a BP neural network model, and acquiring power load information of a plurality of time points output by the BP neural network model;
and combining the power load information of a plurality of time points to obtain the power load of the optimization day to be controlled.
Further, predicting the photovoltaic power generation amount of the optimal day to be controlled according to the date, the illumination intensity and the second temperature comprises the following steps:
determining the season of the optimization day to be controlled according to the date;
selecting a corresponding photovoltaic power generation prediction model according to the season;
and predicting the photovoltaic power generation amount of the day to be controlled and optimized by using the illumination intensity and the second temperature as input information through a photovoltaic power generation model.
Further, the photovoltaic power generation prediction model is constructed based on a support vector machine regression algorithm.
Further, calculating the non-consumption compensation time period of the optimization day to be controlled comprises:
calculating the total power generation according to the photovoltaic power generation and the predicted residual heat power generation;
calculating a difference value by taking the total power generation amount as a decrement and the power load as a decrement;
and selecting the time period with the difference value less than or equal to zero as the non-absorption compensation time period.
Further, solving the objective function by adopting a particle swarm algorithm.
The other technical scheme of the invention is as follows: a control optimization device of a source network charge storage system is disclosed, wherein a power supply system in the source network charge storage system comprises a photovoltaic power generation system, a waste heat storage power generation system and an energy storage battery system, and the source network charge storage system comprises a flexible load; the control optimization device comprises:
the acquisition module is used for acquiring the weather state and the first temperature of the optimization day to be controlled and predicting the power load of the optimization day to be controlled by combining the weather state, the first temperature and the historical power load;
the prediction module is used for acquiring the date, the illumination intensity and the second temperature of the optimization day to be controlled and predicting the photovoltaic power generation amount of the optimization day to be controlled according to the date, the illumination intensity and the second temperature;
the calculation module is used for calculating the non-absorption compensation time period of the optimization day to be controlled according to the power load and the photovoltaic power generation amount of the optimization day to be controlled and the predicted waste heat power generation amount of the waste heat storage power generation system;
and the control optimization module is used for constructing an objective function and solving the objective function by taking the minimization of the operating cost of the source network charge storage system as a target in the non-absorption compensation time period to obtain the waste heat generating capacity, the charge and discharge state of the energy storage battery and the power consumption of the flexible load in the non-absorption compensation time period.
The other technical scheme of the invention is as follows: the control optimization device of the source network load storage system comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, and when the processor executes the computer program, the control optimization method of the source network load storage system is realized.
The other technical scheme of the invention is as follows: a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the method for controlling and optimizing a source-network load storage system is implemented.
The other technical scheme of the invention is as follows: a computer program product, when the computer program product runs on a terminal device, causes the terminal device to execute a control optimization method of a source-network load-store system as described above.
The invention has the beneficial effects that: according to the method, the power load and the total generated energy are predicted according to the weather state, the temperature and the date, the prediction precision can be improved, the compensation time period to be not consumed is calculated, the optimization time period can be accurately determined, the calculated amount is reduced, the objective function is established and solved by minimizing the operation cost of the source network load storage system in the compensation time period to be not consumed, a more accurate control method of the source network load storage system can be obtained, the energy waste is reduced, and the economic benefit is improved.
Drawings
Fig. 1 is a flowchart of a control optimization method for a source-network load-storage system according to an embodiment of the present invention;
FIG. 2 is a diagram illustrating a total load prediction curve according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a typical daily prediction curve for photovoltaic power generation in an embodiment of the present invention;
FIG. 4 is a schematic diagram of a typical daily prediction curve of the heat-storage power generation;
FIG. 5 is a schematic diagram of a compensation curve for the embodiment of the present invention;
FIG. 6 is a schematic diagram of the compensation of peak shaving power generation by heat accumulation of waste heat in the embodiment of the present invention;
FIG. 7 is a schematic diagram of absorption-free compensation in peak shaving power generation with heat accumulation by waste heat in the embodiment of the present invention;
FIG. 8 is a flowchart illustrating the solving steps of the particle swarm algorithm in the embodiment of the present invention;
fig. 9 is a schematic structural diagram of a control optimization apparatus of a source-grid load-storage system according to an embodiment of the present invention.
Detailed Description
The present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.
The fluctuation and randomness of the output power of the photovoltaic power generation system in the source network load storage system also cause the problem of consumption of photovoltaic power generation, so that the problem of optimal scheduling of the power distribution network is more complicated. Further research is needed for solving the problems of absorption compensation of renewable energy sources of photovoltaic power generation and waste heat storage power generation, operation plan of energy storage batteries and scheduling optimization of flexible loads.
With the development of the technology and the construction of the ubiquitous power internet of things, the real-time information acquisition and analysis of the source network load storage can be realized, and a chance is provided for real-time data-driven source network load storage cooperative scheduling.
In the source network load storage system, the source end can comprise a micro gas power generation, a photovoltaic power generation, a water and electricity, a waste heat storage power generation and the like. In the embodiment of the invention, the included renewable energy sources are a photovoltaic power generation system and a waste heat storage power generation system. The network terminal is mainly a low-voltage side centralized reactive power compensation device of a distribution transformer, and comprises a discrete compensation device represented by a capacitor and a continuous compensation device represented by SVG (static var compensator). The load end is mainly flexible load, such as an electric automobile, interruptible load and the like. The storage end is an energy storage device, and the embodiment of the invention relates to an energy storage battery system.
The coordination between the source network and the power storage is essentially interactive influence and coordination of active power and reactive power, so that the load fluctuation of the power distribution network is stabilized, the running loss of the power grid is reduced, the utilization space of equipment resources is released, and the purposes of optimal configuration of the equipment, optimal utilization of the resources and optimal benefit are achieved.
The embodiment of the invention discloses a control optimization method of a source network load storage system, which comprises the following steps as shown in figure 1: step S110, acquiring a weather state and a first temperature of an optimized day to be controlled, and predicting the electrical load of the optimized day to be controlled by combining the weather state, the first temperature and the historical electrical load; s120, acquiring the date, the illumination intensity and the second temperature of the optimization day to be controlled, and predicting the photovoltaic power generation amount of the optimization day to be controlled according to the date, the illumination intensity and the second temperature; step S130, calculating a non-absorption compensation time period of the optimization day to be controlled according to the power load and the photovoltaic power generation amount of the optimization day to be controlled and the predicted waste heat power generation amount of the waste heat storage power generation system; and S140, constructing an objective function by taking the minimization of the running cost of the source network charge storage system as a target and solving the objective function in the non-absorption compensation time period to obtain the waste heat generating capacity, the charge and discharge state of the energy storage battery and the power consumption of the flexible load in the non-absorption compensation time period.
According to the method, the power load and the total generated energy are predicted according to the weather state, the temperature and the date, the prediction precision can be improved, the compensation time period to be not consumed is calculated, the optimization time period can be accurately determined, the calculated amount is reduced, the objective function is established and solved by minimizing the operation cost of the source network load storage system in the compensation time period to be not consumed, a more accurate control method of the source network load storage system can be obtained, the energy waste is reduced, and the economic benefit is improved.
Specifically, in step S110, the weather state of the to-be-controlled optimization day may be a sunny day, a cloudy day, a rainy day, a snowy day, a windy day, a haze day, a hail day, a sandstorm day, or the like, and each type of weather state may be classified into a light type, a heavy type, or the like, which may be determined according to the conventional technical knowledge of those skilled in the art. The acquisition mode can be manually input, or acquired by a weather forecast service provider through network query, and in the process of acquiring the weather state, weighting fusion and the like can be performed in various modes so as to acquire a more accurate weather state. For the first temperature, the obtaining mode can refer to the mode of the weather state.
The historical power consumption records may be the power consumption records of the system under the same weather condition and temperature, the power consumption records under different weather conditions and temperatures in the system, or data input through other systems or manually.
In one embodiment, the weather state, the first temperature and the historical electric load are used as input information, and the BP neural network model is adopted to predict the electric load of the optimization day to be controlled. In the prediction process by adopting the BP neural network algorithm, discretization can be carried out on input data, namely the weather state, the first temperature and the historical power load are sampled to obtain a plurality of sampling point data sets; and inputting the plurality of sampling point data sets into a BP neural network model, acquiring the electric load information of a plurality of time points output by the BP neural network model, and finally combining the electric load information of the plurality of time points to obtain the electric load of the optimization day to be controlled.
In the process of predicting by the BP neural network model, in the embodiment, the predicted data is converted into a curve mode, so that the predicted data is more convenient for practical application.
In the embodiment of the invention, a BP neural network model is established, the BP neural network model consists of an input layer, a hidden layer and an output layer, and the number of nodes of the input layer is determined by historical load, temperature and weather conditions. In this embodiment, 96 sampling points are taken every day (i.e., one sampling point is taken every 15 minutes), and there are 288 input nodes. The number of nodes in the hidden layer can be adjusted according to the accuracy of the actual model, and the number of nodes is 50 in this embodiment. The number of nodes in the output layer is determined by the load data to be output, and in this embodiment, is 96 output nodes.
Furthermore, the BP neural network model in this embodiment may be equivalent to the following formula:
Figure 801533DEST_PATH_IMAGE011
（1）
in the formula (I), the compound is shown in the specification,
Figure 804124DEST_PATH_IMAGE012
is an output layer ofkThe load of the individual nodes is such that,kis an ordinal number of the node of the output layer,
Figure 858667DEST_PATH_IMAGE013
as a hidden layer
Figure 304823DEST_PATH_IMAGE014
From node to output layerkThe weight between the individual nodes is given to,
Figure 812028DEST_PATH_IMAGE015
as an input layer
Figure 618310DEST_PATH_IMAGE016
From node to hidden layer
Figure 527360DEST_PATH_IMAGE014
The weight between the individual nodes is given to,
Figure 128106DEST_PATH_IMAGE017
as a hidden layer
Figure 404497DEST_PATH_IMAGE014
The threshold value of the node is set to be,
Figure 748891DEST_PATH_IMAGE018
as an output layerkThe threshold value of each of the nodes is,mto make a concession thatThe number of the nodes of the layer is,nin order to input the number of nodes of the layer,
Figure 512448DEST_PATH_IMAGE019
for the activation function of the hidden layer,
Figure 815253DEST_PATH_IMAGE020
is the activation function of the output layer.
When the BP neural network model is trained, firstly, the model is selectedaAnd training the BP neural network by using the training samples, and extracting the training samples by using historical data. The BP neural network model adopts S-shaped transfer function
Figure 31471DEST_PATH_IMAGE021
By passing back the error function
Figure 445135DEST_PATH_IMAGE022
Continuously adjusting weight and threshold of BP neural network model to make error function
Figure 813930DEST_PATH_IMAGE023
A minimum value (i.e., a threshold) is reached, wherein,
Figure 22058DEST_PATH_IMAGE024
in order to be able to output the desired output,
Figure 991151DEST_PATH_IMAGE025
and (4) storing the weight and the threshold of the BP neural network model at the moment for the actual calculation output of the network, so as to obtain the trained BP neural network model.
And finally, predicting by using a trained BP neural network model, and taking the historical load, the first temperature and the weather state as influence factors (namely input data) so as to obtain 96 predicted load data, wherein at the moment, because the time among the data is only 15 minutes and the time interval is relatively small, two adjacent data can be directly connected by a straight line when a day-ahead load curve is formed, and finally the day-ahead load curve shown in FIG. 2 is formed.
In other embodiments, if the time interval between two adjacent data is long, such as 1 hour, the output data may be processed again by using other fitting methods, so as to form a more accurate day-ahead load curve.
In the embodiment of the invention, the photovoltaic power generation prediction model is constructed based on a support vector machine regression algorithm. The idea of support vector machine regression algorithm is to pass through a non-linear function
Figure 677347DEST_PATH_IMAGE026
Mapping a dataset to a high-dimensional feature space
Figure 415496DEST_PATH_IMAGE027
And linear regression is carried out in the space, and the original nonlinear problem is skillfully converted into the linear problem in the high-dimensional space, so that the effect of linear regression in the original space is obtained. The specific functional form can be expressed as:
Figure 60104DEST_PATH_IMAGE028
（2）
wherein the content of the first and second substances,
Figure 4576DEST_PATH_IMAGE029
as a weight vector, the weight vector is,
Figure 760042DEST_PATH_IMAGE030
in order to be a constant of the offset amount,
Figure 87118DEST_PATH_IMAGE031
is as followsiThe amount of input to the individual nodes is,
Figure 637048DEST_PATH_IMAGE031
including in particular the intensity of the illumination and the second temperature. As a possible scenario, the first temperature and the second temperature in the embodiment of the present invention should be the same to ensure that the later calculation results in a more accurate prediction curve. If the first temperature and the second temperature are obtained through different ways, the value is obtainedAlternatively, the two may be processed to take an average, or may be weighted.
Thus, a linear regression in a high-dimensional feature space corresponds to a non-linear regression in a low-dimensional space, and a high-dimensional space is avoided
Figure 580734DEST_PATH_IMAGE029
And
Figure 874312DEST_PATH_IMAGE026
the dot product of (2). In formula (2)
Figure 337785DEST_PATH_IMAGE029
And with
Figure 793037DEST_PATH_IMAGE030
Can be estimated by minimizing equation (3).
Figure 958439DEST_PATH_IMAGE032
（3）
In the formula: item 1
Figure 55708DEST_PATH_IMAGE033
Representing a function
Figure 622956DEST_PATH_IMAGE034
The complexity of (2); item 2 represents empirical risk, where
Figure 265421DEST_PATH_IMAGE036
Is an insensitive loss function, the purpose of which is to be able to represent the decision function with sparse points,
Figure 918119DEST_PATH_IMAGE038
is the maximum error that the regression will allow,
Figure 819079DEST_PATH_IMAGE039
the number and generalization capability of the control support vectors are larger, the support vectors are smaller,Cis a normal number of the blood vessel which is,representing the degree of compromise between the complexity of the function class and the average loss on the training set. By utilizing a dual principle and simultaneously introducing a Lagrange function and a kernel function, converting the minimization formula (3) into an optimization problem, and solving the offset according to the Kuhn-Tucker theorem
Figure 975254DEST_PATH_IMAGE040
。
Specifically, during photovoltaic power generation amount prediction, the season of the day to be controlled and optimized is determined according to the date, the corresponding photovoltaic power generation prediction model is selected according to the season, the illumination intensity and the second temperature are used as input information, and the photovoltaic power generation amount of the day to be controlled and optimized is predicted through the photovoltaic power generation model.
The output power of the photovoltaic system is mainly influenced by the position of the area, the illumination intensity and the second temperature are obtained through the position information, the illumination intensity and the temperature are used as input quantities of a power generation model, and the output power of the photovoltaic power generation system is obtained through calculation of the model.
In the process of training the power generation prediction models of the photovoltaic power generation system, different weather in spring, summer, autumn and winter is classified, samples with the same weather type are clustered, each clustered sample is trained to form different photovoltaic power generation prediction models supporting vector machine regression algorithms, and then training models in four seasons are synthesized to obtain a photovoltaic system prediction model set in the whole year.
More specifically, when the photovoltaic power generation is in different seasons, the same temperature and illumination intensity may also cause different power generation amounts, so that the corresponding season is selected according to the date, then the corresponding prediction model is found according to the weather forecast information of the prediction day, and finally the output of the photovoltaic power generation is predicted by using the trained regression model of the support vector machine, as a specific implementation manner, as shown in fig. 3, the model is a typical day curve of the predicted output of the photovoltaic power generation.
In the embodiment of the invention, the prediction of the waste heat power generation amount is also carried out by adopting a BP neural network model. The BP neural network model consists of an input layer, a hidden layer and an output layer, the number of nodes of the input layer is determined by historical power generation and historical load, and 192 input nodes are provided by selecting 96 sampling points every day; the number of nodes of the hidden layer can be adjusted according to the accuracy of the actual model, and the number of the selected nodes is 30 in the embodiment; the number of nodes in the output layer is determined by the output load data, and is selected to be 96 output nodes in the present embodiment.
The model can be represented by the following formula:
Figure 303467DEST_PATH_IMAGE041
（4）
wherein the content of the first and second substances,
Figure 177882DEST_PATH_IMAGE042
is an output layer ofkThe amount of power generation of the individual nodes,kis the node ordinal number of the output layer,
Figure 633265DEST_PATH_IMAGE043
as a hidden layer
Figure 909526DEST_PATH_IMAGE014
From node to output layerkThe weight between the individual nodes is given to,
Figure 143061DEST_PATH_IMAGE044
as an input layer
Figure 770352DEST_PATH_IMAGE016
From node to hidden layer
Figure 747535DEST_PATH_IMAGE014
The weight between the individual nodes is given to,
Figure 891684DEST_PATH_IMAGE045
as a hidden layer
Figure 561700DEST_PATH_IMAGE014
The threshold value of the node is set to be,
Figure 410707DEST_PATH_IMAGE046
as an output layerkThe threshold value of each of the nodes is,min order to imply the number of layer nodes,nin order to input the number of nodes of the layer,
Figure 926002DEST_PATH_IMAGE047
an activation function for the hidden layer;
Figure 442434DEST_PATH_IMAGE048
is the activation function of the output layer.
When the BP neural network model is trained, historical power generation and historical load are used as training samples, and an S-shaped transfer function is selected for the network
Figure 17772DEST_PATH_IMAGE021
By passing back the error function
Figure 104808DEST_PATH_IMAGE022
Continuously adjusting network weight and threshold to make error function
Figure 689373DEST_PATH_IMAGE049
When the minimum value is reached, the network weight and the threshold value at the moment are stored, and the network weight and the threshold value are calculated, so that 96 predicted power generation power data are obtained, namely the prediction of the waste heat storage and power generation amount curve of the day is completed, wherein,
Figure 794732DEST_PATH_IMAGE024
in order to be able to output the desired output,
Figure 540971DEST_PATH_IMAGE025
is the actual computational output of the network.
And after the predicted waste heat power generation amount is obtained, generating a day-ahead waste heat storage power generation curve according to the predicted waste heat power generation amount. In one embodiment, a typical daily profile of waste heat storage power generation is shown in fig. 4.
In conclusion, a photovoltaic power generation prediction curve and a waste heat storage power generation prediction curve are obtained, and the total power generation amount is calculated according to the photovoltaic power generation amount and the predicted waste heat power generation amount; calculating a difference value by taking the total power generation amount as a decrement and the electric load as a decrement; and finally, selecting a time period with the difference value less than or equal to zero as a non-absorption compensation time period.
Specifically, when the total power generation amount is greater than the total load amount, the consumption compensation of the renewable energy source needs to be performed for the consumption compensation time period.
When the total power generation is less than or equal to the total load, the consumption compensation of the renewable energy is not needed, and the time period is a non-consumption compensation time period. The absorptive capacity of renewable energy sources can be expressed as:
Figure 364571DEST_PATH_IMAGE050
（5）
wherein the content of the first and second substances,
Figure 487247DEST_PATH_IMAGE051
the consumption rate of renewable energy sources;
Figure 197846DEST_PATH_IMAGE049
the total power generation amount is obtained;
Figure 380565DEST_PATH_IMAGE052
for the generated electric power to be absorbed by the load,
Figure 691461DEST_PATH_IMAGE053
the generated electric energy is consumed by the energy storage system.
As shown in fig. 5, the portion of the curve smaller than 0 is a time curve (i.e., a consumption compensation time period) requiring consumption compensation, and during the time period, the flexible load is firstly started, and then the energy storage battery is charged, so as to ensure that the redundant power generation amount can be completely consumed.
In other time periods, namely non-absorption compensation time periods, optimization adjustment is needed, the time and the power generation amount of waste heat storage power generation are adjusted, and meanwhile, the energy storage battery is charged and discharged according to the change condition of the load. Specifically, in the embodiment of the present invention, a particle swarm algorithm is adopted to solve the objective function. The waste heat storage power generation time and the power generation amount are adjusted in the power generation margin space (i.e., within the adjustable power generation range), and as shown in fig. 6, a waste heat storage peak shaving power generation absorption compensation diagram is shown.
The waste heat storage power generation time and the power generation amount are adjusted in the power generation margin space, and as shown in fig. 7, a waste heat storage peak shaving power generation non-consumption compensation diagram is shown. And (3) starting the flexible load in a planned manner, adjusting the time and the power generation amount of the waste heat storage power generation, simultaneously charging and discharging the energy storage battery according to the change condition of the load, solving the model by adopting an improved particle swarm optimization algorithm, and calculating an operation optimization scheduling plan in the whole day, namely the waste heat storage power generation amount, the charge-discharge state of the energy storage battery and the size of the flexible load corresponding to each moment of 96 sampling time points.
The network side is mainly performed by means of controllable DC/DC converters, wherein converters connected to different voltage classes participate in the optimization interaction by controlling the output voltage or power. And in a certain voltage margin range, voltage regulation is carried out on a constant voltage node in the system through a converter, the network loss can be reduced by increasing the voltage of the node, and the system is optimally scheduled. The DC/DC converter performs corresponding voltage and power limitation on the transmission system, avoiding overrun, and the constraint can be expressed as:
Figure 352249DEST_PATH_IMAGE054
（6）
Figure 432201DEST_PATH_IMAGE055
（7）
wherein the content of the first and second substances,
Figure 785822DEST_PATH_IMAGE056
and
Figure 334746DEST_PATH_IMAGE057
the upper limit and the lower limit of the voltage of the DC/DC converter are respectively set;
Figure 799225DEST_PATH_IMAGE058
and
Figure 468104DEST_PATH_IMAGE059
the upper limit and the lower limit of the capacity of the DC/DC converter are respectively.
Flexible loads are classified by type into transferable loads and interruptible loads. The transferable load time is nimble, and the work demand can be accomplished in a certain time, and measures such as accessible peak avoidance production shift the power consumption demand to electric wire netting load low ebb time section, for example electric automobile trades power station and partial resident load etc.. According to the protocol signed after the power supply and utilization parties negotiate in advance, the interruptible load interrupts the short-time power supply to the preset load without influencing normal work and life in order to meet the optimized operation of the power grid under the condition of insufficient power supply during the peak period of power utilization of the power grid. Such as large industrial users and irrigation equipment.
The energy storage system has the dual properties of a power supply and a load, and when the total generated energy is greater than the total load requirement, redundant renewable energy is consumed to store power, so that the utilization rate of the renewable energy is improved; and when the total generated energy is insufficient, the power balance can be maintained, and the stored electric quantity is released to supply power for the system. And through reasonable guide and flexible load of dispatch, make flexible load avoid the power consumption peak period, at the excessive power consumption trough period operation of photovoltaic power generation, increased the burden reserve capacity for the system equivalently. The flexible load can be interrupted in the peak period of power utilization, the load demand is reduced, namely, the positive reserve capacity is increased for the system, the system meets the power balance requirement, and the influence of the uncertainty of photovoltaic power generation on the operation of the system is reduced.
In the embodiment of the invention, the objective function is that the operation cost is the lowest, and the cost mainly comprises the photovoltaic power generation cost
Figure 258206DEST_PATH_IMAGE060
Waste heat storage power generation cost
Figure 278114DEST_PATH_IMAGE061
Energy storage cost
Figure 280705DEST_PATH_IMAGE062
Loss of network cost
Figure 913130DEST_PATH_IMAGE063
Flexible load compensation cost
Figure 608553DEST_PATH_IMAGE064
Is of the formula
Figure 850179DEST_PATH_IMAGE065
（8）
Wherein the content of the first and second substances,
Figure 922040DEST_PATH_IMAGE002
for the operating cost of the source network load storage system,
Figure 831090DEST_PATH_IMAGE003
in order to not absorb the compensation period of time,
Figure 448147DEST_PATH_IMAGE004
for the time within the non-absorption compensation period,
Figure 442648DEST_PATH_IMAGE005
，
Figure 787042DEST_PATH_IMAGE006
is composed oftThe cost of photovoltaic power generation at the time of day,
Figure 816178DEST_PATH_IMAGE007
is composed oftThe waste heat is stored for generating electricity at any moment,
Figure 587825DEST_PATH_IMAGE008
is composed oftThe cost of the energy stored at the moment,
Figure 69622DEST_PATH_IMAGE009
is composed oftThe network loss cost of the source network load storage system at the moment,
Figure 234018DEST_PATH_IMAGE010
is composed oftThe time flexible load compensates for the cost. The constraint conditions of the objective function comprise power balance constraint, energy storage system constraint, waste heat storage power generation system constraint and electricity price constraint. The constraints are specifically as follows:
a) and power balance constraint:
Figure 852081DEST_PATH_IMAGE066
（9）
wherein the content of the first and second substances,
Figure 60208DEST_PATH_IMAGE067
in order to generate the power by the photovoltaic power generation,
Figure 29301DEST_PATH_IMAGE068
in order to preheat the heat-storage power generation power,
Figure 715498DEST_PATH_IMAGE069
for the charging and discharging power of the energy storage system,
Figure 453647DEST_PATH_IMAGE070
in order to be the power of the load,
Figure 583408DEST_PATH_IMAGE071
in order to obtain the power loss of the network,
Figure 774218DEST_PATH_IMAGE072
flexible load power.
b) And (4) energy storage system constraint:
the charging and discharging depth affects the service life of the storage battery in the energy storage system, and the overshoot and the overdischarge can cause the loss of the service life of the storage battery, so the state of charge of the storage battery is requiredSOC, constraint:
Figure 264105DEST_PATH_IMAGE073
（10）
wherein the content of the first and second substances,
Figure 122339DEST_PATH_IMAGE074
is composed oftTime energy storage systemiThe charging power of the battery pack is set,
Figure 672269DEST_PATH_IMAGE075
is composed oftTime energy storage system iThe maximum charging power of the battery pack,
Figure 350375DEST_PATH_IMAGE076
is composed oftTime energy storage systemiThe power of the discharge of (a) is,
Figure 391756DEST_PATH_IMAGE077
is composed oftTime energy storage system i(serial number of energy storage modules in the energy storage system),
Figure 838918DEST_PATH_IMAGE078
is the minimum value of the state of charge of the energy storage system,
Figure 825329DEST_PATH_IMAGE079
the maximum value of the state of charge of the energy storage system.
c) And (3) restraining the waste heat storage power generation system:
Figure 990731DEST_PATH_IMAGE080
（11）
wherein the content of the first and second substances,
Figure 822421DEST_PATH_IMAGE081
is the minimum generating capacity of the waste heat storage generating system,
Figure 124089DEST_PATH_IMAGE082
the maximum power generation capacity of the waste heat storage power generation system.
d) And (4) electricity price constraint:
according to different peak-to-valley electricity prices, the waste heat storage peak-shaving power generation, the energy storage system charge and discharge and the flexible load adjustment are all adjusted according to respective priority orders:
waste heat storage peak shaving power generation: peak > flat > valley;
charging an energy storage battery: valley time > usual time > peak time;
discharging the energy storage battery: peak > flat > valley;
flexible load: valley > flat > peak.
According to the constraint conditions, the model is solved by adopting an improved particle swarm optimization algorithm, as shown in fig. 8, a running optimization scheduling plan in a non-absorption compensation time period is obtained by adopting the specific solving steps of the improved particle swarm optimization algorithm, namely, the residual heat storage power generation amount, the energy storage battery charge-discharge state and the flexible load size corresponding to each moment in the time points needing absorption compensation are removed from 96 sampling time points.
The specific steps of solving the model by the improved particle swarm optimization algorithm are as follows:
a) randomly initializing the position (the position of the particle includes the generated energy of the waste heat storage system, the charge-discharge state of the energy storage battery system and the magnitude of the flexible load) and the speed of the particle in the population, wherein the particle includes 96 sampling time points to remove the generated energy of the waste heat storage system, the charge-discharge state of the energy storage battery and the magnitude of the flexible load corresponding to each time corresponding to the time point needing absorption compensation.
b) Calculating the fitness of the particles, wherein the fitness at the moment is the operation cost of the system, then storing the positions and the fitness of the particles, and storing the positions and the fitness of the particles with the optimal fitness in all the current particles, wherein the fitness function is as follows:
Figure 32133DEST_PATH_IMAGE083
（12）
c) the velocity and position of the particles are updated with an improved shrinkage factor:
Figure 684831DEST_PATH_IMAGE084
（13）
wherein
Figure 54633DEST_PATH_IMAGE085
、
Figure 741966DEST_PATH_IMAGE086
In order to learn the factors, the learning device is provided with a plurality of learning devices,
Figure 804600DEST_PATH_IMAGE087
、
Figure 944594DEST_PATH_IMAGE088
is a random number between 0 and 1,
Figure 134398DEST_PATH_IMAGE089
、
Figure 410659DEST_PATH_IMAGE090
is as followsiA particle is arranged in
Figure 909773DEST_PATH_IMAGE014
The velocity and position of the dimensional space are,
Figure 271485DEST_PATH_IMAGE091
for the best position to be searched for at present,
Figure 248668DEST_PATH_IMAGE092
the best position currently searched for the entire population.
The contraction factor can effectively control and restrict the flight speed of the particles compared with the inertia weight coefficient w, and meanwhile, the local searching capability of the algorithm is enhanced.
d) For each particle, it is compared to its previous optimal position and, if better, it is taken as the current optimal position.
e) And comparing all the current particles, and updating the individual with the optimal fitness.
f) And if the required precision or iteration times is reached, stopping searching, outputting results, wherein the results at the moment are the current waste heat storage and power generation amount of the optimal particles, the charge and discharge state of the energy storage battery and the size of the flexible load, and otherwise, returning to the step b. Through the steps, the optimal control optimization strategy can be calculated.
In addition, taking the waste heat storage system in this embodiment as a sintering waste heat power generation system as an example, the sintering waste heat power generation system can be adjusted according to the following method.
When the sintering equipment normally operates, the resource amount of the sintering flue gas waste heat is stable. From this it can be concluded that the steam production of the waste heat boiler fluctuates around a certain value, assuming: a) the average value of the steam generated by the waste heat boiler in normal operation is unchanged, and the waste heat boilers are mutually independent; b) the steam quantity generated by the boiler follows normal distribution
Figure 645014DEST_PATH_IMAGE093
(ii) a c) The average steam amount does not change with time. In order to ensure the normal operation of the steam turbine generator unit, the total steam quantity generated by the waste heat boiler should meet the minimum steam quantity required by the generator unit, and the probability of meeting the continuous operation of the generator unit is greater than
Figure 800183DEST_PATH_IMAGE094
. Setting probability values
Figure 914770DEST_PATH_IMAGE095
By solving for conditions satisfied
Figure 430065DEST_PATH_IMAGE096
Determines the operating state of the boiler, expressed as a vector
Figure 680917DEST_PATH_IMAGE097
. The mathematical expression is:
Figure 521834DEST_PATH_IMAGE098
（14）
wherein, the first and the second end of the pipe are connected with each other,
Figure 858138DEST_PATH_IMAGE099
represents the maximum amount of steam when the generator set is running,
Figure 196365DEST_PATH_IMAGE100
the rated steam amount is set as the minimum steam amount
Figure 301724DEST_PATH_IMAGE101
. The minimum value of the steam flow is more than 50% of the maximum value, and the power generation can be operated within the range of the bearable fluctuation of the steam turbine.
Figure 47964DEST_PATH_IMAGE102
The working efficiency of the generator set is represented, which is called as the working state coefficient of the generator set,
Figure 871563DEST_PATH_IMAGE103
、
Figure 994240DEST_PATH_IMAGE104
representing the upper and lower bounds of the state coefficient. Then the state coefficient
Figure 970417DEST_PATH_IMAGE105
When is coming into contact with
Figure 887558DEST_PATH_IMAGE106
The steam amount satisfies the rated value, and the power generation state is considered to be optimal. Solving the inequality can obtain the operation scheme of the waste heat boiler.
In summary, in the embodiment of the present invention, a power system source-grid-load-storage coordination optimization model is established, a renewable energy power generation output model is established, and photovoltaic power generation and waste heat storage power generation are predicted; the daily operation plan of the energy storage system and the dispatching plan of the flexible load under the peak-valley electricity price are obtained through the optimization model, the reliability and the economy of the power distribution network system can be improved through reasonable configuration of the energy storage system, the power electronic device is used for quickly adjusting the capacity, an effective way for solving photovoltaic output fluctuation is formed, and peak clipping and valley filling are carried out in cooperation with photovoltaic; under the condition of meeting the constraint of planning cost, the minimization of system operation cost and the minimization of pollution emission are realized; the photovoltaic consumption level is effectively improved, the grid loss rate and the voltage deviation are reduced, the new energy power generation is balanced, and the safe and reliable operation of the power distribution network is realized.
The invention also discloses a control optimization device of the source network charge storage system, a power supply system in the source network charge storage system comprises a photovoltaic power generation system, a waste heat storage power generation system and an energy storage battery system, and the source network charge storage system comprises a flexible load. As shown in fig. 9, the control optimization apparatus includes: the obtaining module 210 is configured to obtain a weather state and a first temperature of an optimized day to be controlled, and predict an electrical load of the optimized day to be controlled by combining the weather state, the first temperature and a historical electrical load; the prediction module 220 is used for acquiring the date, the illumination intensity and the second temperature of the optimization day to be controlled, and predicting the photovoltaic power generation amount of the optimization day to be controlled according to the date, the illumination intensity and the second temperature; the calculating module 230 is used for calculating the non-absorption compensation time period of the optimization day to be controlled according to the power load and the photovoltaic power generation amount of the optimization day to be controlled and the predicted waste heat power generation amount of the waste heat storage power generation system; and the control optimization module 240 is configured to construct an objective function and solve the objective function by using the minimization of the operation cost of the source network charge storage system as a target in the non-absorption compensation time period to obtain the waste heat power generation amount, the charge and discharge state of the energy storage battery and the power consumption of the flexible load in the non-absorption compensation time period.
It should be noted that, for the information interaction, execution process, and other contents between the modules of the apparatus, the specific functions and technical effects of the embodiments of the method are based on the same concept, and thus reference may be made to the section of the embodiments of the method specifically, and details are not described here.
It will be clear to those skilled in the art that, for convenience and simplicity of description, the foregoing division of the functional modules is merely illustrated, and in practical applications, the above function distribution may be performed by different functional modules according to needs, that is, the internal structure of the apparatus is divided into different functional modules to perform all or part of the above described functions. Each functional module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional modules are only used for distinguishing one functional module from another, and are not used for limiting the protection scope of the application. For the specific working processes of the units and modules in the system, reference may be made to the corresponding processes in the foregoing method embodiments, which are not described herein again.
The other technical scheme of the invention is as follows: the control optimization device of the source network load storage system comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, and when the processor executes the computer program, the control optimization method of the source network load storage system is realized.
The device can be a desktop computer, a notebook, a palm computer, a cloud server and other computing equipment. The apparatus may include, but is not limited to, a processor, a memory. Those skilled in the art will appreciate that the apparatus may include more or fewer components, or some components in combination, or different components, and may also include, for example, input-output devices, network access devices, etc.
The Processor may be a Central Processing Unit (CPU), or other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory may in some embodiments be an internal storage unit of the device, such as a hard disk or a memory of the device. The memory may also be an external storage device of the apparatus in other embodiments, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), etc. provided on the apparatus. Further, the memory may also include both an internal storage unit and an external storage device of the apparatus. The memory is used for storing an operating system, application programs, a BootLoader (BootLoader), data, and other programs, such as program codes of the computer programs. The memory may also be used to temporarily store data that has been output or is to be output.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment. Those of ordinary skill in the art will appreciate that the various illustrative modules and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

Claims (9)

1. A control optimization method of a source network charge storage system is characterized in that a power supply system in the source network charge storage system comprises a photovoltaic power generation system, a waste heat storage power generation system and an energy storage battery system, wherein the source network charge storage system comprises a flexible load; the control optimization method specifically comprises the following steps:
acquiring a weather state and a first temperature of an optimized day to be controlled, and predicting the electrical load of the optimized day to be controlled by combining the weather state, the first temperature and the historical electrical load;
acquiring the date, the illumination intensity and the second temperature of the optimization day to be controlled, and predicting the photovoltaic power generation amount of the optimization day to be controlled according to the date, the illumination intensity and the second temperature;
calculating a non-absorption compensation time period of the optimization day to be controlled according to the power load and the photovoltaic power generation amount of the optimization day to be controlled and the predicted waste heat power generation amount of the waste heat storage power generation system; calculating the non-absorption compensation time period of the optimization day to be controlled comprises the following steps:
calculating the total power generation according to the photovoltaic power generation and the predicted residual heat power generation;
calculating a difference value by taking the total power generation amount as a decrement and the power load as a decrement;
selecting a time period in which the difference value is less than or equal to zero as the non-absorption compensation time period;
and in the non-absorption compensation time period, constructing an objective function by taking the minimization of the operating cost of the source network charge storage system as a target and solving to obtain the waste heat generating capacity, the charge and discharge state of the energy storage battery and the power consumption of the flexible load in the non-absorption compensation time period.
2. The method for controlling and optimizing a source-grid-load-storage system according to claim 1, wherein the objective function is:
Figure 473919DEST_PATH_IMAGE001
，
wherein the content of the first and second substances,
Figure 776725DEST_PATH_IMAGE002
for the operating cost of the source grid storage system,
Figure 117576DEST_PATH_IMAGE003
for the non-absorption compensation period of time,
Figure 265661DEST_PATH_IMAGE004
for the time instants within the non-absorption compensation period,
Figure 883724DEST_PATH_IMAGE005
，
Figure 91851DEST_PATH_IMAGE006
is composed oftThe cost of photovoltaic power generation at the time of day,
Figure 936311DEST_PATH_IMAGE007
is composed oftThe waste heat is stored for generating electricity at any moment,
Figure 622507DEST_PATH_IMAGE008
is composed oftThe cost of the energy stored at the moment,
Figure 360656DEST_PATH_IMAGE009
is composed oftThe network loss cost of the source network load storage system at the moment,
Figure 864318DEST_PATH_IMAGE010
is composed oftMoment flexible load compensation cost;
the constraint conditions of the objective function comprise power balance constraint, energy storage system constraint, waste heat storage power generation system constraint and electricity price constraint.
3. The control optimization method of the source-grid-load-storage system as claimed in claim 1 or 2, wherein the step of predicting the electrical load of the optimal day to be controlled by combining the weather state, the first temperature and the historical electrical load comprises the following steps:
and forecasting the power load of the optimization day to be controlled by adopting a BP neural network model by taking the weather state, the first temperature and the historical power load as input information.
4. The method of claim 3, wherein predicting the electrical load of the optimal day to be controlled in combination with the weather condition, the first temperature and the historical electrical load further comprises:
sampling the weather state, the first temperature and the historical electric load to obtain a plurality of sampling point data sets;
inputting a plurality of sampling point data sets into the BP neural network model, and acquiring the electric load information of a plurality of time points output by the BP neural network model;
and combining the power load information of a plurality of time points to obtain the power load of the optimization day to be controlled.
5. The control optimization method of the source-grid-load storage system according to claim 4, wherein predicting the photovoltaic power generation amount of the day to be controlled and optimized according to the date, the illumination intensity and the second temperature comprises:
determining the season of the optimization day to be controlled according to the date;
selecting a corresponding photovoltaic power generation prediction model according to the season;
and predicting the photovoltaic power generation amount of the day to be controlled and optimized by using the illumination intensity and the second temperature as input information through the photovoltaic power generation model.
6. The method for controlling and optimizing the source-grid-load-storage system according to claim 5, wherein the photovoltaic power generation prediction model is constructed based on a support vector machine regression algorithm.
7. The method of claim 2, wherein the objective function is solved by a particle swarm algorithm.
8. A control optimization device of a source network charge storage system is characterized in that a power supply system in the source network charge storage system comprises a photovoltaic power generation system, a waste heat storage power generation system and an energy storage battery system, wherein the source network charge storage system comprises a flexible load; the control optimization device comprises:
the acquisition module is used for acquiring the weather state and the first temperature of the optimization day to be controlled and predicting the power load of the optimization day to be controlled by combining the weather state, the first temperature and the historical power load;
the prediction module is used for acquiring the date, the illumination intensity and the second temperature of the optimization day to be controlled and predicting the photovoltaic power generation amount of the optimization day to be controlled according to the date, the illumination intensity and the second temperature;
the calculation module is used for calculating the non-absorption compensation time period of the optimized day to be controlled according to the power load and the photovoltaic power generation amount of the optimized day to be controlled and the predicted waste heat power generation amount of the waste heat storage power generation system; calculating the non-absorption compensation time period of the optimization day to be controlled comprises the following steps:
calculating the total power generation according to the photovoltaic power generation and the predicted residual heat power generation;
calculating a difference value by taking the total power generation amount as a decrement and the electric load as a decrement;
selecting a time period in which the difference value is less than or equal to zero as the non-absorption compensation time period;
and the control optimization module is used for constructing an objective function and solving the objective function by taking the minimization of the operating cost of the source network charge storage system as a target in the non-absorption compensation time period to obtain the waste heat generating capacity, the charge and discharge state of the energy storage battery and the power consumption of the flexible load in the non-absorption compensation time period.
9. A control optimization device of a source load storage system, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the control optimization method of the source load storage system according to any one of claims 1 to 7 when executing the computer program.
CN202210123395.9A 2022-02-10 2022-02-10 Control optimization method and device of source network load storage system Active CN114156951B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210123395.9A CN114156951B (en) 2022-02-10 2022-02-10 Control optimization method and device of source network load storage system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210123395.9A CN114156951B (en) 2022-02-10 2022-02-10 Control optimization method and device of source network load storage system

Publications (2)

Publication Number Publication Date
CN114156951A CN114156951A (en) 2022-03-08
CN114156951B true CN114156951B (en) 2022-05-17

Family

ID=80450181

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210123395.9A Active CN114156951B (en) 2022-02-10 2022-02-10 Control optimization method and device of source network load storage system

Country Status (1)

Country Link
CN (1) CN114156951B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116646986B (en) * 2023-05-29 2024-04-16 浙江正泰智维能源服务有限公司 Method, device, system and medium for supplying energy by renewable energy sources in intensive agriculture
CN116800172B (en) * 2023-08-23 2023-10-27 中通服建设有限公司 Photoelectric conversion method and energy storage system

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9863666B1 (en) * 2013-08-14 2018-01-09 The United States Of America As Represented By The Administrator Of The National Aeronautics And Space Administration Heliostat with stowing and wind survival capabilities
JP6520517B2 (en) * 2015-07-22 2019-05-29 富士電機株式会社 Supply and demand planning device, program
CN106779291B (en) * 2016-11-15 2020-09-25 国网浙江省电力公司经济技术研究院 Intelligent power utilization park demand response strategy
CN107528345B (en) * 2017-09-30 2020-06-05 国电南瑞科技股份有限公司 Multi-time-scale network source load and storage coordination control method
CN109687504B (en) * 2018-11-14 2021-02-23 杭州赫智电子科技有限公司 Micro-grid energy optimization distribution method based on source-load balance
CN109462231B (en) * 2018-11-15 2020-09-01 合肥工业大学 Load optimization scheduling method, system and storage medium for residential micro-grid
CN109742812B (en) * 2019-03-11 2022-06-14 长沙理工大学 Source-load-storage coordinated scheduling method for improving new energy consumption
CN111952966A (en) * 2019-12-11 2020-11-17 国网辽宁省电力有限公司经济技术研究院 Source load storage system staged coordination optimization method considering wind power consumption capacity
CN112290598B (en) * 2020-09-17 2022-06-28 河北电力交易中心有限公司 Distributed photovoltaic power generation management and settlement method based on electric power spot environment
CN112671040A (en) * 2021-01-11 2021-04-16 华北电力大学 Day-ahead optimal scheduling method of multi-energy complementary system considering maximum new energy consumption
CN112865075B (en) * 2021-01-12 2023-10-20 许继集团有限公司 AC/DC hybrid micro-grid optimization method

Also Published As

Publication number Publication date
CN114156951A (en) 2022-03-08

Similar Documents

Publication Publication Date Title
CN112614009B (en) Power grid energy management method and system based on deep expectation Q-learning
Liu et al. Residential energy scheduling for variable weather solar energy based on adaptive dynamic programming
Moghaddam et al. Multi-objective operation management of a renewable MG (micro-grid) with back-up micro-turbine/fuel cell/battery hybrid power source
CN114156951B (en) Control optimization method and device of source network load storage system
CN107039975B (en) Energy management method for distributed energy system
CN107423852A (en) A kind of light storage combined plant optimizing management method of meter and typical scene
CN111934360B (en) Virtual power plant-energy storage system energy collaborative optimization regulation and control method based on model predictive control
CN107565607A (en) A kind of micro-capacitance sensor Multiple Time Scales energy dispatching method based on Spot Price mechanism
CN115169723A (en) Power generation power prediction method, load prediction method and model training method
CN113962455A (en) Virtual power plant energy storage optimization scheduling strategy based on model predictive control
Zhong et al. An Orderly EV Charging Scheduling Method Based on Deep Learning in Cloud‐Edge Collaborative Environment
Chatziagorakis et al. Enhancement of hybrid renewable energy systems control with neural networks applied to weather forecasting: the case of Olvio
CN116151551A (en) Regulation and control method and device for electric heating comprehensive energy system and regulation and control equipment
CN115882523A (en) Optimal operation method, system and equipment for power system with distributed energy storage
Dou et al. Double‐deck optimal schedule of micro‐grid based on demand‐side response
TWI639962B (en) Particle Swarm Optimization Fuzzy Logic Control Charging Method Applied to Smart Grid
Wang et al. Research on short‐term and mid‐long term optimal dispatch of multi‐energy complementary power generation system
CN108683211B (en) Virtual power plant combination optimization method and model considering distributed power supply volatility
CN115693787A (en) Method for analyzing new energy acceptance of optical storage and distribution power grid in consideration of source load randomness
Zhang et al. Coordinated dispatch of the wind-thermal power system by optimizing electric vehicle charging
CN115115145A (en) Demand response scheduling method and system for distributed photovoltaic intelligent residence
Wu et al. Research on optimal storage capacity of DC micro‐grid system in PV station
CN115705608A (en) Virtual power plant load sensing method and device
CN109950920B (en) Photovoltaic station side electrochemical energy storage charging and discharging plan making method based on dynamic programming algorithm
Zandi et al. An automatic learning framework for smart residential communities

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