CN115660325B - Power grid peak regulation capacity quantization method and system - Google Patents
Power grid peak regulation capacity quantization method and system Download PDFInfo
- Publication number
- CN115660325B CN115660325B CN202211228666.3A CN202211228666A CN115660325B CN 115660325 B CN115660325 B CN 115660325B CN 202211228666 A CN202211228666 A CN 202211228666A CN 115660325 B CN115660325 B CN 115660325B
- Authority
- CN
- China
- Prior art keywords
- air source
- heat
- working medium
- temperature
- heat supply
- 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
Links
Images
Landscapes
- Air Conditioning Control Device (AREA)
Abstract
The application provides a power grid peak shaving capacity quantization method and a system, wherein the method is used for quantifying the power grid peak shaving capacity of an air source heat pump heat supply system, the air source heat pump heat supply system comprises a plurality of air source heat pumps, and an air source is utilized to heat a heat supply working medium, and the method comprises the following steps: s1: determining a plurality of key parameters affecting the temperature of a heating working medium of an air source heat pump heating system; s2: building a heat supply working medium temperature prediction model based on the key parameters and training by using the historical operation data; s3: and acquiring the quantized power grid peak regulation capacity of the air source heat pump heat supply system by using the trained heat supply working medium temperature prediction model. According to the quantization method and system, the factors which have significant influence on the peak shaving capacity of the air source heat pump heating system can be extracted according to the operation characteristics of the air source heat pump heating system, and reasonable quantization indexes are set, so that the capacity of the air source heat pump heating system participating in power grid peak shaving can be accurately quantized.
Description
Technical Field
The application belongs to the technical field of intelligent control of power grids, and further provides a power grid peak shaving capacity quantization method and system, which are used for performing quantization evaluation on the power grid peak shaving capacity of an air source heat pump heating system.
Background
The air source heat pump heating system is a novel heating system, which is used for controlling a plurality of distributed air source heat pump units to intensively heat heating hot water, and then is conveyed to a plurality of heat inlets or heat users through a heat medium pipeline by a circulating water pump in a short pipe network decentration mode, so that heat supply is realized.
The air source heat pump heat supply system has the advantages that the heat supply function is realized, and meanwhile, the required power load can be regulated by controlling the opening or closing of each air source heat pump unit contained in the air source heat pump heat supply system, so that the aim of participating in power grid peak shaving is fulfilled. The demand side is taken as a resource corresponding to the supply side to participate in power grid peak shaving, and the demand side is guided to actively track the fluctuation of the power output, so that the demand side is an important target for power grid peak shaving, and the upper power department needs to know the adjustable capacity in advance when the air source heat pump heating system with adjustable power is used for participating in demand response regulation and control.
Under the existing regulation mode, the air source heat pump load polymerizer generally directly reports that all air source heat pumps are turned on or off as maximum up-regulation/down-regulation capacity, so as to be used as the basis for matching the demand side with the supply side of an upper power department. The mode for evaluating the power grid peak shaving capacity of the air source heat pump heating system is greatly different from the actual situation, so that an electric power department cannot acquire the accurate peak shaving capacity, and further cannot reasonably formulate a peak shaving scheme and distribute peak shaving tasks.
The reason for the above problems is that: the air source heat pump heating system is used for participating in the specific operation of grid peak shaving, and a certain number of air source heat pumps in the system are started or stopped in a certain period of time so as to meet the power regulation requirement of the superior power department. However, the air source heat pump heating system is a nonlinear complex system, the operation process of the system is influenced by various external factors such as outdoor temperature, heating building area, heating pipe network laying and the like, and the primary task is to meet the requirement on indoor temperature adjustment, so that during peak shaving, if the number of operating heat pumps deviates from the heat generating and radiating balance number of the heating system, the indoor temperature of a user is influenced, the comfort level of the user is reduced, and the heating system is caused to participate in peak shaving time reduction, so that the peak shaving capacity of a power grid is directly evaluated in a state that all air source heat pumps in the system are fully turned on or turned off, the actual operation state is not consistent, and an upper electric power department cannot master the accurate peak shaving capacity and further influences the accurate peak shaving capacity of the power grid.
Therefore, when the peak shaving capacity of the power grid of the air source heat pump heating system is evaluated, the conventional power load peak shaving capacity evaluation method cannot be simply used, and a factor which has a significant influence on the peak shaving capacity of the air source heat pump heating system is extracted according to the operation characteristics of the air source heat pump heating system so as to improve the accuracy of quantitative evaluation of the peak shaving capacity of the air source heat pump heating system.
Disclosure of Invention
In order to solve the problems in the prior art, the purpose of the application is to provide a power grid peak shaving capacity quantization method and a system, which can establish a prediction model of the power grid peak shaving capacity based on the actual operation and heat transfer characteristics of an air source heat pump heating system, and quantitatively predict and evaluate the power grid peak shaving capacity by designing a proper peak shaving capacity quantization index.
An aspect of the present application provides a power grid peak shaving capacity quantization method for quantifying power grid peak shaving capacity of an air source heat pump heating system, the air source heat pump heating system includes a plurality of air source heat pumps, and utilizes an air source to heat a heating medium, including the following steps:
s1: determining a plurality of key parameters affecting the temperature of a heating working medium of an air source heat pump heating system;
s2: building a heat supply working medium temperature prediction model based on the key parameters and training by using the historical operation data;
s3: and acquiring the quantized power grid peak regulation capacity of the air source heat pump heat supply system by using the trained heat supply working medium temperature prediction model.
Further, step S1 includes the steps of:
s11: based on the (1), a heat supply working medium thermodynamic process model of the air source heat pump heat supply system is established,
Wherein ρ is the density of the heating medium, c is the specific heat capacity of the heating medium, and V is the volume (m 3 ) The method comprises the steps of carrying out a first treatment on the surface of the θ is the temperature of the heat supply working medium, t is time, and phi is the heat variation of the heat supply working medium;
s12: determining the relation between phi and theta based on the formula (2),
wherein phi is p To generate heat for the system, phi d For the heat dissipation of the system, phi 1 Phi is the heating quantity of the opened air source heat pump 2 For solar radiant heat flow, COP n For the number of open air source heat pumps, P n The quantity of the air source heat pumps is h, the surface convection heat exchange coefficient is h, A is the total heat dissipation area, delta t is the time interval and theta out Is outdoor temperature;
s13: the surface convection heat transfer coefficient h of the (3) type is used for approximate characterization,
wherein N is u The number is Knoop, l is the characteristic size, and lambda is the heat conductivity coefficient of the heat supply working medium;
s14: determining influence N under forced convection heat exchange condition u Factors of (2)
Influence of N under natural convection heat exchange u Factors of (2)
Wherein Re is the Reynolds number, pr is the Plantains number, gr is the Gelating-Raf number, u, v and a are the flow velocity, the kinematic viscosity and the thermal diffusivity of the heating working medium respectively, g is the gravitational acceleration, alpha v For the volume expansion coefficient, Δθ b Is the temperature difference between the wall temperature and the ambient temperature.
S15: based on formulas (1) to (3) and the influence N u A factor(s) that determines a number of key parameters that affect theta.
Preferably, the key parameters further comprise upper and lower limits of the temperature of the heating working medium.
Preferably, the heat supply working medium temperature prediction model is a BP neural network model.
Preferably, the input quantity of the heat supply working medium temperature prediction model comprises operation data of the key parameter at least 2 time intervals at and before the time t; and the output quantity of the heat supply working medium temperature prediction model is the heat supply working medium temperature of the next time interval at the moment t.
Preferably, the quantized grid peaking capability is a downtunable quantization value and/or an uptunable quantization value of the air source heat pump heating system corresponding to each switch control scheme.
Further, the downtunable quantization value corresponding to each switch control scheme is
And, the up-tunable quantization value corresponding to each switch control scheme is
Wherein P is down 、t down 、W down Power down-regulated, time down-regulated and capacity down-regulated respectively for each switch control scheme, P up 、t up 、W up Power up-regulated, time up-regulated and capacity up-regulated respectively for each switch control scheme, m n Starting up number m of air source heat pump for each switch control scheme b To realize the number of the startup machines when generating heat and balancing heat, P n Rated electric power of air source heat pump, t start To peak-shaving start time, t min T is the time when the temperature of the heat supply working medium reaches the lower limit of the temperature max The temperature of the heating working medium reaches the upper temperature limit.
Further, step S3 includes the steps of:
s31: switch control scheme for realizing heat generation and dissipation balance based on actual operation data of air source heat pump heat supply system and corresponding m b ；
S32: tracking the change condition of the temperature of the heating working medium under each switch control scheme by utilizing the heating working medium temperature prediction model based on the actual operation data of the air source heat pump heating system, wherein the switch control scheme is switched to the switch control scheme for realizing heat generation and radiation balance when the temperature of the heating working medium reaches a preset temperature limit value, and the switch control scheme is switched to each switch control scheme again after the heat generation and radiation reach balance again;
s33: and determining the quantized grid peak shaving capacity of the air source heat pump heating system corresponding to each switch control scheme in real time based on the tracking result of the step S32.
Another aspect of the present application provides a power grid peak shaving capacity quantization system for quantifying power grid peak shaving capacity of an air source heat pump heating system, the air source heat pump heating system includes a plurality of air source heat pumps, utilizes the air source to heat heating medium, the power grid peak shaving capacity quantization system includes:
The parameter determining unit is used for determining a plurality of key parameters affecting the temperature of a heating working medium of the air source heat pump heating system; the model training unit is used for establishing a heat supply working medium temperature prediction model based on the key parameters and training by using the historical operation data; and the quantization unit is used for acquiring the quantization power grid peak regulation capacity of the air source heat pump heat supply system by using the trained heat supply working medium temperature prediction model.
Further, the parameter determination unit determines the plurality of key parameters by:
the first step, a thermodynamic process model of a heat supply working medium of the air source heat pump heat supply system is established based on the formula (1),
wherein ρ is the density of the heating medium, c is the specific heat capacity of the heating medium, and V is the volume (m 3 ) The method comprises the steps of carrying out a first treatment on the surface of the θ is the temperature of the heat supply working medium, t is time, and phi is the heat variation of the heat supply working medium;
a second step of determining the relation between phi and theta based on the formula (2),
wherein phi is p To generate heat for the system, phi d For the heat dissipation of the system, phi 1 Phi is the heating quantity of the opened air source heat pump 2 For solar radiant heat flow, COP n Is opened toNumber of open air source heat pumps, P n The quantity of the air source heat pumps is h, the surface convection heat exchange coefficient is h, A is the total heat dissipation area, delta t is the time interval and theta out Is outdoor temperature;
thirdly, using the surface convection heat exchange coefficient h of the step (3) to perform approximate characterization,
wherein N is u The number is Knoop, l is the characteristic size, and lambda is the heat conductivity coefficient of the heat supply working medium;
fourth, determining the influence N under the condition of forced convection heat exchange u Factors of (2)
Influence of N under natural convection heat exchange u Factors of (2)
Wherein Re is the Reynolds number, pr is the Plantains number, gr is the Gelating-Raf number, u, v and a are the flow velocity, the kinematic viscosity and the thermal diffusivity of the heating working medium respectively, g is the gravitational acceleration, alpha v For the volume expansion coefficient, Δθ b Is the temperature difference between the wall temperature and the ambient temperature.
Fifth, based on the formulas (1) to (3) and the influence N u A factor(s) that determines a number of key parameters that affect theta.
Preferably, the key parameters further comprise upper and lower limits for preset thermal working medium temperature.
Preferably, the heat supply working medium temperature prediction model is a BP neural network model.
Preferably, the input quantity of the heat supply working medium temperature prediction model comprises operation data of the key parameter at least 2 time intervals at and before the time t; and the output quantity of the heat supply working medium temperature prediction model is the heat supply working medium temperature of the next time interval at the moment t.
Preferably, the quantized grid peaking capability is a downtunable quantization value and/or an uptunable quantization value of the air source heat pump heating system corresponding to each switch control scheme.
Further, the downtunable quantization value corresponding to each switch control scheme is
And, the up-tunable quantization value corresponding to each switch control scheme is
Wherein P is down 、t down 、W down Power down-regulated, time down-regulated and capacity down-regulated respectively for each switch control scheme, P up 、t up 、W up Power up-regulated, time up-regulated and capacity up-regulated respectively for each switch control scheme, m n Starting up number m of air source heat pump for each switch control scheme b To realize the number of the startup machines when generating heat and balancing heat, P n Rated electric power of air source heat pump, t start To peak-shaving start time, t min T is the time when the temperature of the heat supply working medium reaches the lower limit of the temperature max The temperature of the heating working medium reaches the upper temperature limit.
Further, the quantization unit obtains the quantization power grid peak shaving capacity of the air source heat pump heating system through the following steps:
the first step, a switch control scheme for realizing heat generation and radiation balance and corresponding m are determined based on actual operation data of the air source heat pump heat supply system b ；
The second step, based on the actual operation data of the air source heat pump heat supply system, tracking the change condition of the heat supply working medium temperature under each switch control scheme by utilizing the heat supply working medium temperature prediction model, wherein when the heat supply working medium temperature reaches a preset temperature limit value, the switch control scheme is switched to the switch control scheme for realizing heat generation and radiation balance, and after the heat generation and radiation reach balance again, the switch control scheme is switched to each switch control scheme again;
and thirdly, determining the quantized power grid peak regulation capacity of the air source heat pump heat supply system corresponding to each switch control scheme in real time based on the tracking result of the heat supply working medium temperature prediction model.
The method and the system for quantifying the power grid peak shaving system provided by the embodiment of the application have the following beneficial effects:
according to the technical scheme provided by the application, the heat generating and radiating model is built aiming at the actual operation characteristics of the air source heat pump heat supply system, and the heat generating and radiating model is based on a plurality of key parameters which influence the heat generating and radiating of the system and are easy to detect and acquire, so that the heat supply working medium temperature prediction model is built on the basis, and the heat supply working medium temperature change conditions under different switch control schemes can be accurately predicted;
The technical scheme provided by the application changes the mode of directly evaluating the power grid peak shaving capacity of all air source heat pumps in the system in the prior art in a full-on or full-off state, and establishes reasonable power grid peak shaving capacity quantitative indexes based on the prediction of the temperature change condition of the heat supply working medium and by combining with the actual use scene of the heat supply system. By using the quantization method and the quantization system provided by the application, the peak shaving capacity of the power grid can be evaluated in real time in accordance with the actual running state of the power grid, so that an upper power department can master the accurate peak shaving capacity and accurately peak shaving the power grid.
Drawings
FIG. 1 is a schematic diagram of the principle of operation of an air source heat pump heating system;
FIG. 2 is a flow chart illustrating an implementation of a power grid peak shaving capacity quantization method according to an embodiment of the present application;
fig. 3 is a basic structure of a BP neural network according to an embodiment of the present application;
FIG. 4 is a schematic diagram of determining an up-tunable time and a down-tunable time according to a temperature change of a heating medium according to an embodiment of the present application;
FIG. 5 is a graph showing changes in the electric power of an air source heat pump based on actual operating data of a particular air source heat pump heating system;
FIG. 6 is a prediction accuracy of a heating medium temperature prediction model constructed and trained using actual operating data of a particular air source heat pump heating system according to an embodiment of the present application;
FIG. 7 is a prediction accuracy of a heating medium temperature prediction model constructed and trained using actual operating data of another specific air source heat pump heating system according to an embodiment of the present application;
FIG. 8 is a predicted result of a heat supply medium temperature change condition of a specific air source heat pump heat supply system under different switch control schemes according to an embodiment of the present application;
FIG. 9 is a graphical result of the up-and down-tunable capabilities corresponding to FIG. 8;
fig. 10 is a schematic diagram of a system frame of a power grid peak shaving capacity quantization system according to an embodiment of the present application.
Detailed Description
The present application will be further described below based on preferred embodiments with reference to the accompanying drawings.
In addition, various components on the drawings are enlarged or reduced for ease of understanding, but this is not intended to limit the scope of the present application.
The singular forms also include the plural and vice versa.
In the description of the embodiments of the present application, it should be noted that, if the terms "upper," "lower," "inner," "outer," and the like indicate an azimuth or a positional relationship based on the azimuth or the positional relationship shown in the drawings, or an azimuth or a positional relationship that a product of the embodiments of the present application conventionally puts in use, it is merely for convenience of describing the present application and simplifying the description, and does not indicate or imply that the device or element to be referred to must have a specific azimuth, be configured and operated in a specific azimuth, and therefore should not be construed as limiting the present application. Furthermore, in the description of the present application, the terms first, second, etc. are used herein for distinguishing between different elements, but not necessarily for describing a sequential or chronological order of manufacture, and may not be construed to indicate or imply a relative importance, and their names may be different in the detailed description of the present application and the claims.
The terminology used in this description is for the purpose of describing the embodiments of the present application and is not intended to be limiting of the present application. It should also be noted that unless explicitly stated or limited otherwise, the terms "disposed," "connected," and "connected" should be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; the two components can be connected mechanically, directly or indirectly through an intermediate medium, and can be communicated internally. The specific meaning of the terms in this application will be specifically understood by those skilled in the art.
The air source heat pump is a high-efficiency energy-saving heat supply device which takes outdoor air as a heat source and utilizes heat in the air to achieve the heat production effect. A plurality of distributed air source heat pumps are used for networking and unified control, and an air source heat pump heating system can be further formed. Fig. 1 shows a schematic diagram of an operation principle of a typical air source heat pump heat supply system, as shown in fig. 1, the heat supply system mainly includes a heat source side, a transmission pipe network, a user side and the like, wherein a plurality of air source heat pump units with a nominal heating capacity of more than 35kW are generally used as distributed small and medium-sized heat sources for heat source measurement, hot water (i.e. heat supply working medium) for user heating is prepared in a concentrated manner, and the hot water is conveyed to a plurality of heat inlets or heat users through a heat medium pipeline by a circulating water pump in a short pipe network decentration manner.
The air source heat pump heat supply system can realize central heat supply and can also participate in power grid peak shaving. When the air source heat pump is used for participating in power grid peak shaving, a certain number of air source heat pumps in the system need to be started or shut down in a certain period of time so as to meet the power requirements of the upper power departments on the air source heat pumps. However, during peak regulation, the heat quantity required by the air source heat pump heating system for heating a building is not greatly changed, the quantity of the air source heat pumps required to be started is relatively stable, if the quantity of the operating heat pumps deviates from the quantity of heat generating and radiating balances of the heating system, the indoor temperature of a user can be influenced, the comfort level of the user is reduced, and meanwhile, the participation of the heating system in peak regulation time is reduced, so that the operating principle of the air source heat pump heating system needs to be analyzed in detail to measure the capacity of the air source heat pump heating system in peak regulation of a power grid.
Based on the above analysis, the present application provides, by way of example, a power grid peak shaving capacity quantization method for quantifying power grid peak shaving capacity of an air source heat pump heating system, and fig. 2 shows a flowchart of implementation of the power grid peak shaving capacity quantization method provided according to the embodiment of the present application, where the quantization method provided in fig. 2 includes the following steps:
S1: determining a plurality of key parameters affecting the temperature of a heating working medium of an air source heat pump heating system;
s2: building a heat supply working medium temperature prediction model based on the key parameters and training by using the historical operation data;
s3: and acquiring the quantized power grid peak regulation capacity of the air source heat pump heat supply system by using the trained heat supply working medium temperature prediction model.
The following describes the steps S1 to S3 in detail with reference to the drawings and the specific embodiments.
Step S1 determines a plurality of key parameters which have significant influence on the heat supply effect (namely the temperature of the heat supply working medium) through analysis of the operation and heat transfer characteristics of the air source heat pump heat supply system.
At present, a building or a community taking an air source heat pump as main heating equipment adopts a central heating mode taking an air source heat pump heating system as a basic unit, the air source heat pump heating system adopts a multi-stage heating mode, each stage is connected in series, and air source heat pump loads in each stage are connected in parallel. In the air source heat pump heat supply system, a plurality of data transmission units are installed to collect operation data of the air source heat pump heat supply system in real time, and meanwhile, the data are uploaded to the cloud by utilizing an information communication technology. Under the non-regulation mode, the air source heat pump heating system runs autonomously, and the number of the heat pump starting-up units can be automatically adjusted according to the factors such as the ambient temperature, so that heat generation and heat dissipation are balanced. Under the regulation mode, the air source heat pump heating system can quantitatively turn on or off a certain amount of heat pump loads at regular time according to the upper control instruction.
Under the addition of modern information technology, a large number of sensors and data transmission units exist in the operation process of the air source heat pump heating system, and data can be collected and uploaded to the cloud in real time. Table 1 shows various data which can be collected when the current air source heat pump heating system operates, including parameters of heating working medium (circulating hot water), environmental parameters, heat production parameters, overall operation parameters of the system and the like.
Table 1 data related to real-time acquisition of air source heat pump heating system
The data collected by the data transmission unit are various, a foundation is provided for digital modeling of the air source heat pump heating system, but meanwhile too abundant data types bring another problem for modeling, namely, how to scientifically select the data types and the data objects to provide basis for digital modeling.
In the embodiment of the application, the air source heat pump heat supply station and the heat supply object (namely the district) are classified into an integral system, and the integral operation characteristics of the integral system are researched to simplify the analysis process. According to the analysis, the heat supply working medium penetrates through the heat source measuring, conveying side and tail end side heat supply processes of the heat supply system, plays an important role in the whole heat supply process, and the heat supply effect of the heat supply system can be effectively evaluated by utilizing the temperature of the heat supply working medium, so that the key variable of the temperature of the heat supply working medium can be selected as a research object, and a plurality of key parameters affecting the temperature of the heat supply working medium are determined by historical operation data of the air source heat pump heat supply system.
The process of determining a plurality of key parameters affecting the heating medium of an air source heat pump heating system in embodiments of the present application is described in detail below.
For the temperature change process of a heating working medium (generally circulating hot water), a mathematical expression of the thermodynamic process of the heating working medium as (1) can be established according to the first law of thermodynamics:
wherein ρ is the density of the heating medium, c is the specific heat capacity of the heating medium, and V is the volume (m 3 ) The method comprises the steps of carrying out a first treatment on the surface of the θ is a heating medium temperature (in the embodiment of the application, an average value of a water supply temperature and a water return temperature which can be collected in an actual operation process of the system can be selected as the heating medium temperature θ), t is time, Φ is a heating medium heat variation amount, and Φ can be further expressed by a formula (2):
by analyzing the operation mechanism of the air source heat pump, the volume of the heat supply working medium is the volume of hot water in the heat supply pipeline, the volume of the heat supply working medium can be regarded as a fixed value after the heat supply pipe network is paved, the density and the specific heat capacity of the heat supply working medium are physical parameters representing the self characteristics of the heat supply working medium, the heat supply working medium is influenced by the temperature of the working medium, and the total heat change phi of the heat supply working medium is generated by the heat generation phi p And heat dissipation capacity phi d The two parts are composed of the following expression:
Φ＝Φ p -Φ d ，
in particular, the heat production quantity Φ of the heating system p Comprises two parts, namely the heating quantity phi of all air source heat pumps in working state 1 Heat generated by solar radiation Φ 2 The method comprises the following steps:
Φ p ＝Φ 1 +Φ 2 ，
wherein phi is 1 ＝COP n ·P n ，COP n For the number of open air source heat pumps, P n Is the number of air source heat pumps.
In particular, the heat dissipation capacity Φ of the heating system d The expression newton's cooling formula can be expressed:
Φ d ＝hAΔt＝hA(θ-θ out )，
wherein h is the surface convection heat transfer coefficient, A is the total heat dissipation area, deltat is the time interval, θ out Is the outdoor temperature.
In the above equation, h is associated with a variety of factors and cannot be measured directly by a sensor or other means, so further analysis thereof is required. The surface convection heat transfer coefficient h in the heat transfer science can be approximately characterized by the similarity criterion number, and generally, the nussel number (Nusselt number, nunumber) is adopted, and the specific expression is shown in the formula (3):
wherein N is u The number is Knoop, l is the characteristic dimension, and lambda is the heat conductivity coefficient of the heat supply working medium.
Because the Nu numbers are different in representation forms in different heat dissipation processes, in the embodiment of the application, according to the heat exchange process, analysis is respectively developed from the forced convection heat exchange of a heat supply working medium and an indoor environment and the natural convection heat exchange of the indoor environment and an outdoor environment:
In the first aspect, the heat supply working medium exchanges heat with forced convection of the indoor environment.
The forced convection process of the heating medium and the indoor environment belongs to forced heat exchange in the pipe groove, and the number in the heat transfer theory can be expressed as a function of Reynolds number (Re number) and Plandtl number (Prandtl number), namely:
wherein Re is Reynolds number, pr is Plantain number, and u, v and a are flow velocity, kinematic viscosity and thermal diffusivity of the heating working medium respectively.
In a second aspect, natural convection heat transfer from an indoor environment to an outdoor environment.
In the case of natural convection heat exchange between an indoor environment and an outdoor environment, the number of nus is not related to the number of Re any longer, but is related to the number of Grashof (Gr), that is, the number of nus in the heat dissipation process between the indoor environment and the outdoor environment is a function of the number of Gr and the number of Pr. The Gr number can be characterized as:
wherein g is gravitational acceleration, alpha v For the volume expansion coefficient, Δθ b Is the temperature difference between the wall temperature and the ambient temperature.
The physical quantity related to the heat dissipation capacity of the heating system can be obtained from the expression of the above-described similarity criterion number, as shown in table 2:
TABLE 2 physical quantity included in similarity criterion number
It can be seen from table 2 that a large number of physical quantities are involved in the above-mentioned similarity criterion, and many physical quantities (such as dynamic viscosity and thermal diffusivity of the heating medium) are difficult to directly measure. Table 3 lists the direct or indirect correspondence between the physical quantities involved in the aforementioned similarity criteria and the collectable physical quantities in the context of the actual engineering application:
TABLE 3 correspondence between similar criterion number related physical quantity and measurable physical quantity
In the embodiment of the application, through the relation between the temperature and the heat change of the heat supply working medium established by the formulas (1) - (3), and the factors having key influence on the heat dissipation capacity and the corresponding relation between the factors and the observable physical quantity, a plurality of key parameters affecting the temperature of the heat supply working medium can be determined.
For example, in some preferred embodiments, the heating medium temperature θ (t), the heat generation amount Φ at the current moment can be p Heat dissipation capacity phi d Temperature difference delta theta between indoor environment and outdoor environment b As a key factor for predicting the temperature θ (t+Δt) of the heating medium at the next time, considering that only the physical quantity having time-varying characteristics will affect θ (t+Δt) among the selected input quantities, the non-time-varying physical quantity is related only to the heating system and the characteristics of the building itself, and therefore, in order to further reduce the number of input variables, only the time-varying physical quantity in table 4 is selected as a key parameter.
Table 4 time-varying characteristics of parameters affecting the temperature of heating medium
Further, in some preferred embodiments of the present application, considering that the air source heat pump heating system is essentially a temperature controlled load, the allowable margin of the indoor environmental temperature change caused by the on-off operation of the end user should be mapped to the set upper and lower temperature limits of the heating medium, and be used as the key parameter affecting the temperature of the heating medium.
Specifically, an average value of the difference between the total backwater temperature and the intelligently set backwater temperature can be selected as a temperature control margin, and then an upper limit value expression and a lower limit value expression shown in the following formulas are obtained:
wherein θ set For supplying heat working mediumThe temperature set point is set to a temperature,
setting backwater temperature for intelligence>
For the difference between working medium temperature set value and intelligent set backwater temperature,/->
Setting a lower limit value for the temperature of the heating working medium, < + >>
Setting an upper limit value for the temperature of the heating working medium, < >>
Is a temperature control margin.
After determining a plurality of key parameters affecting the temperature of the heating working medium through the step S1, a prediction model for predicting the temperature of the heating working medium based on the key parameters is further established and trained in the step S2.
In the embodiment of the application, the heat supply working medium temperature prediction model is a BP neural network model. The BP neural network is a feedforward neural network with an input layer, an output layer and a plurality of hidden layers, and is called as the BP neural network because the weight matrix is updated by adopting a back propagation algorithm to achieve the training effect. FIG. 3 shows the basic structure of a BP neural network, where x m 、y n 、W ij 、V ij The mth input quantity, the nth output quantity, the connection weight of the input layer to the hidden layer and the connection weight of the input layer to the hidden layer of the BP neural network are respectively obtained, and after the BP neural network is trained, the values of the multiple output quantities at future time can be predicted based on the values of the multiple input quantities at past time and/or current time.
Specifically, in some preferred embodiments of the present application, the input of the heating medium temperature prediction model includes operation data of the key parameter at time t and at least 2 time intervals before time t; and the output quantity of the heat supply working medium temperature prediction model is the heat supply working medium temperature of the next time interval at the moment t. The reason for using the operation data of at least 2 time intervals at and before the time t as the input amount is that: in the actual operation process of the air source heat pump heat supply system, the temperature change of the heat supply working medium, the key parameters and the change of the system power determined by the key parameters have strong hysteresis, so that the time span range of the input quantity needs to be properly prolonged to improve the accuracy of model prediction.
In the actual implementation process, the training set and the testing set can be constructed by utilizing the actual operation data of the air source heat pump heat supply system, the heat supply working medium temperature prediction model is trained through the training set, the prediction accuracy of the prediction model is tested by using the testing set, and the tested prediction model can be used in the power grid peak shaving capacity quantization process of the step S3. The above embodiments for constructing training and testing sets based on actual data to train and test neural network models are known to those skilled in the art, and will not be described herein.
And S3, quantifying the power grid peak regulation capacity of the air source heat pump heat supply system by using the trained heat supply working medium temperature prediction model.
In the embodiment of the application, the peak shaving capacity of the quantized power grid is specifically a downtunable quantized value and/or an uptunable quantized value of the air source heat pump heating system corresponding to each switch control scheme.
In actual power grid dispatching, the power department directly provides load curves participating in the regulation period for each load aggregator, and the load aggregator controls the managed load to regulate power according to the curves. For the air source heat pump heating system, different switch control schemes can be formed by turning on or off different numbers of air source heat pump units, and correspondingly, under different switch control schemes, the system can have different downregulating quantization values and/or upregulating quantization values. At present, related researches on the participation of an air source heat pump in a peak regulation response of an electric power system are deficient in China, an air source heat pump load aggregator generally directly reports that all air source heat pumps are fully turned on or fully turned off as maximum up-regulation/down-regulation capacity, a dispatching mode mostly adopts task average allocation, the actual situation of an individual cannot be considered, extreme situations of overuse or extremely few use exist, the temperature is simpler and direct, temperature out-of-limit is easy to cause, and user comfort is reduced.
In order to correct the defects of the existing air source heat pump peak shaving capacity evaluation mode, in a preferred embodiment of the application, reasonable peak shaving capacity quantization indexes are set according to actual operation characteristics of an air source heat pump heat supply system, and the heat supply working medium temperature prediction model is used for predicting the quantization indexes. Specifically, each switch control scheme of the system can be adjusted up or down by comparing the switch control scheme with the switch control scheme when the heat generating and radiating balance is realized, meanwhile, the temperature of the heat supply working medium when the heat generating and radiating balance is realized can keep the indoor temperature stable, so that different switch control schemes obviously change the temperature of the heat supply working medium, further the indoor temperature is changed, when the temperature of the heat supply working medium exceeds an acceptable limit, peak regulation is ended, and the switch control scheme is reset to the switch control scheme when the heat generating and radiating balance is realized, so that the indoor temperature is restored to an acceptable range.
It follows that for an air source heat pump heating system, its peak shaving capacity should include different system powers as determined by turning on different numbers of air source heat pumps (i.e., different switching control schemes), the resulting different heating medium temperature out-of-limit times, and the total adjustable capacity as determined by both. Thus, in embodiments of the present application, the downtunable quantization values corresponding to the respective switch control schemes are
And, the up-tunable quantization value corresponding to each switch control scheme is
Wherein P is down 、t down 、W down Power down-regulated, time down-regulated and capacity down-regulated respectively for each switch control scheme, P up 、t up 、W up Power up-regulated, time up-regulated and capacity up-regulated respectively for each switch control scheme, m n Starting up number m of air source heat pump for each switch control scheme b To realize the number of the startup machines when generating heat and balancing heat, P n Rated electric power of air source heat pump, t start To peak-shaving start time, t min T is the time when the temperature of the heat supply working medium reaches the lower limit of the temperature max The temperature of the heating working medium reaches the upper temperature limit.
FIG. 4 shows, respectively, in a specific embodiment, the determination of the up-tunable time t as a function of the temperature change of the heating medium up And can adjust down time t down In which
The curves are the upper limit and the lower limit of the temperature of the heat supply working medium respectively.
Specifically, in the embodiment of the present application, step S3 further includes the steps of:
s31: switch control scheme for realizing heat generation and dissipation balance based on actual operation data of air source heat pump heat supply system and corresponding m b ；
S32: tracking the change condition of the temperature of the heating working medium under each switch control scheme by utilizing the heating working medium temperature prediction model based on the actual operation data of the air source heat pump heating system, wherein the switch control scheme is switched to the switch control scheme for realizing heat generation and radiation balance when the temperature of the heating working medium reaches a preset temperature limit value, and the switch control scheme is switched to each switch control scheme again after the heat generation and radiation reach balance again;
S33: and determining the quantized grid peak shaving capacity of the air source heat pump heating system corresponding to each switch control scheme in real time based on the tracking result of the step S32.
Further, in some preferred embodiments, all the switch control schemes may be ordered in real time according to the size of the adjustable capacity, with the scheme with the largest adjustable capacity being defined as the best up-switch control scheme and the scheme with the smallest adjustable capacity being defined as the best down-switch control scheme. The adjustable power and the adjustable time under the two switch control schemes are the adjustable power and the adjustable time of the air source heat pump heating system.
By using the method, the quantized value of the peak shaving capacity of the air source heat pump heating system participating in the power grid can be updated in real time, so that the upper power department can accurately and uniformly acquire the real peak shaving capacity of the demand side, and the establishment of a peak shaving plan and the distribution of peak shaving tasks are more fit with the actual situation.
Example 1
The embodiment adopts the real detection data of the operation of a certain air source heat pump heating system (hereinafter referred to as a system A) provided by a certain air source heat pump load aggregator, and the method is used for training a heating medium temperature prediction model and quantifying the peak regulation capacity of a system power grid.
In order to select data capable of reflecting the heat supply characteristics of the air source heat pump heat supply system, the operation data thereof need to be analyzed, and not only the working period with the stable operation state of the air source heat pump heat supply system, but also the period containing the active self-regulation of the air source heat pump heat supply system due to the change of the external environment are selected. Fig. 5 shows the variation of the electric power of the air source heat pump according to the actual operation data of the system a for 2 months.
As can be seen from fig. 5, during the period from day 2 month 13 to day 2 month 16, since the fluctuation range of the outdoor ambient temperature is large, the fluctuation of the power consumed by the a system also occurs, and at the same time, the time of the system in steady state operation is longer than that of the period from day 2 month 20 to day 2 month 28, and therefore, this part of data is better representative, so in this embodiment, 6000 sets (1 set acquired every 1 minute) of each operation data of the a system during the period from day 2 month 13 to day 2 month 16 are selected for constructing the prediction model of this embodiment.
The time step (i.e., Δt) is set to 3min in consideration of the balance between the data accuracy and the number. And (3) analyzing the operation data by utilizing the step (S1), and finally selecting the number of the opened air source heat pumps, the outdoor environment temperature, the total water supply temperature, the total backwater temperature and the intelligent set backwater temperature as key parameters. The number of the opened air source heat pumps and the outdoor environment temperature can be directly used, and other physical quantities related to the temperature of the heat supply working medium still need to be subjected to relevant data processing.
And then constructing and training a heat supply working medium temperature prediction model through the step S2, wherein the specific construction and training conditions are as follows:
(a) Data determination: the data sample used as the prediction model training is the actual running data of the air source heat pump heating system from 2 months 13 days to 2 months 16 days four days, 6000 groups of original data are obtained by sampling every 1min, and after the jump nodes are eliminated by taking the average, the training set is obtained by taking the 3 minutes as the step length (delta t), and 2000 groups of data are obtained. The same method is used for taking data of 2.17 days and two hours as a verification set so as to verify the accuracy of model prediction.
(b) Input output quantity determination: the actual peak regulation power instruction generally takes 15 minutes as a period, takes 3 minutes as a time interval delta t from the aspects of modeling precision and modeling speed, sets the quantity of the opened air source heat pumps, outdoor environment temperature, heat supply working medium temperature and heat supply working medium temperature at the moment t and t-delta t and t-2 delta t as upper limits, sets the lower limits of the heat supply working medium temperature as model input quantity, takes the heat supply working medium temperature at the next moment as model output quantity, and respectively generates a training set and a verification set required by a training model by taking the heat supply working medium temperature as a reference. The input and output of the heat supply working medium temperature prediction model are specifically listed in table 5.
TABLE 5 input and output of heat supply working medium temperature prediction model
(c) Determining the number of hidden layer nodes: in the process of training the prediction model, the selection of the number of hidden layer nodes is also very critical, the number of hidden layer nodes is small, the accuracy is reduced, and the number of hidden layer nodes is large, so that the training speed is reduced. In this embodiment, the number of nodes of the hidden layer is taken according to an empirical formula. The number of hidden layer nodes in the empirical formula is 2 times more than the number of input nodes, and 31 nodes are taken as the number of hidden layer nodes in the embodiment.
(d) Data preprocessing: and (3) obtaining a standard training set and a verification set by adopting a min-max normalization method from the training set and the verification set formed by the input data and the output data, so as to eliminate potential influence of different dimension data on modeling.
(e) Model training: target error of 10 -4 Maximum training times 2000, minimum gradient 10 -10 The initial weight is selected immediately, the accuracy of modeling is improved by continuously adjusting the learning rate eta, and model training is completed.
FIG. 6 shows the prediction accuracy of a heating medium temperature prediction model constructed and trained using the actual operating data of the A system, and it can be seen that the prediction model can better predict the heating medium temperature, and the error between the model predicted medium temperature and the actual operating medium temperature is smaller, and the error square root is equal 
Further, according to the above process, the historical operation data of the B air source heat pump heat supply system is selected to construct and train a prediction model, and the prediction accuracy of the obtained prediction model is shown in fig. 7. The simulation result shows that the established heat supply working medium temperature prediction model still has better simulation and tracking on the actual operation process, and can reasonably quantify the peak regulation capacity of the air source heat pump heat supply system.
On the basis of constructing a heat supply working medium temperature prediction model based on the historical operation data of the A system, different on-off control schemes of the A system are formed by changing the number of the air source heat pumps, so that the temperature change condition of the working medium of the heat supply system under different on-off control schemes is simulated on the basis of actual operation data, when the temperature of the working medium reaches a limit value due to unbalance of heat production and heat dissipation, the on-off control scheme is reset to be the on-off control scheme corresponding to the balance of heat production and heat dissipation, the adjustable time is calculated, and the up-adjustable capacity and the down-adjustable capacity of the current on-off control scheme are calculated further in real time according to the adjustable time. Fig. 8 shows the change of the temperature of the heating medium of the system a obtained under different switch control schemes, and the graphical results of the corresponding up-adjustable capacity and down-adjustable capacity are shown in fig. 9.
As can be seen from fig. 9, when the temperature of the heating medium approaches the temperature control limit value over time, the switching control scheme returns to the corresponding switching control scheme when the heat generation and dissipation balance is achieved, and the temperature of the heating medium changes in the opposite direction; when the number of the opened air source heat pumps is large, the total power is large, the heat is generated, the temperature of the heat supply working medium is continuously increased, and the increasing rate is larger as the number of the opened air source heat pumps is larger; similarly, when the number of the opened air source heat pumps is small, the total power is small, the heat generation is small, the temperature of the heat supply working medium is continuously reduced, and the reduction rate is larger when the number of the opened air source heat pumps is smaller; the simulation result accords with the thermodynamic process, and the heat supply working medium temperature prediction model established by the method of the embodiment can effectively simulate the air source heat pump heat supply system under different switch control states.
As can be seen from fig. 9, as the deviation degree of the number of the opened air source heat pumps from the number of opened air source heat pumps corresponding to the heat generating and dissipating balance state is increased, the adjustable capacity is lower due to both the up-adjustment and the down-adjustment. The adjustable power and the adjustable time only show ideal level when the number of opened heat sources is not different from the number corresponding to the heat generation and radiation balance, and the adjustable capacity of the heating system is maximum at the moment.
The utility model provides a still provide a power grid peak shaving ability quantization system through the embodiment for quantize air source heat pump heating system's power grid peak shaving ability, air source heat pump heating system contains many air source heat pumps, utilizes the air source to heat the heat supply working medium, as shown in fig. 10, power grid peak shaving ability quantization system includes:
the parameter determining unit is used for determining a plurality of key parameters affecting the temperature of a heating working medium of the air source heat pump heating system; the model training unit is used for establishing a heat supply working medium temperature prediction model based on the key parameters and training by using the historical operation data; and the quantization unit is used for acquiring the quantization power grid peak regulation capacity of the air source heat pump heat supply system by using the trained heat supply working medium temperature prediction model.
Further, the parameter determination unit determines the plurality of key parameters by:
the first step, a thermodynamic process model of a heat supply working medium of the air source heat pump heat supply system is established based on the formula (1),
wherein ρ is the density of the heating medium, c is the specific heat capacity of the heating medium, and V is the volume (m 3 ) The method comprises the steps of carrying out a first treatment on the surface of the θ is the temperature of the heat supply working medium, t is time, and phi is the heat variation of the heat supply working medium;
A second step of determining the relation between phi and theta based on the formula (2),
wherein phi is p To generate heat for the system, phi d For the heat dissipation of the system, phi 1 Phi is the heating quantity of the opened air source heat pump 2 For solar radiant heat flow, COP n For the number of open air source heat pumps, P n The quantity of the air source heat pumps is h, the surface convection heat exchange coefficient is h, A is the total heat dissipation area, delta t is the time interval and theta out Is outdoor temperature;
thirdly, using the surface convection heat exchange coefficient h of the step (3) to perform approximate characterization,
wherein N is u The number is Knoop, l is the characteristic size, and lambda is the heat conductivity coefficient of the heat supply working medium;
fourth, determining the influence N under the condition of forced convection heat exchange u Factors of (2)
Influence of N under natural convection heat exchange u Factors of (2)
Wherein Re is the Reynolds number, pr is the Plantains number, gr is the Gelating-Raf number, u, v and a are the flow velocity, the kinematic viscosity and the thermal diffusivity of the heating working medium respectively, g is the gravitational acceleration, alpha v For the volume expansion coefficient, Δθ b Is the temperature difference between the wall temperature and the ambient temperature.
Fifth, based on the formulas (1) to (3) and the influence N u A factor(s) that determines a number of key parameters that affect theta.
Preferably, the key parameters further comprise upper and lower limits for preset thermal working medium temperature.
Preferably, the heat supply working medium temperature prediction model is a BP neural network model.
Preferably, the input quantity of the heat supply working medium temperature prediction model comprises operation data of the key parameter at least 2 time intervals at and before the time t; and the output quantity of the heat supply working medium temperature prediction model is the heat supply working medium temperature of the next time interval at the moment t.
Preferably, the quantized grid peaking capability is a downtunable quantization value and/or an uptunable quantization value of the air source heat pump heating system corresponding to each switch control scheme.
Further, the downtunable quantization value corresponding to each switch control scheme is
And, the up-tunable quantization value corresponding to each switch control scheme is
Wherein P is down 、t down 、W down Power down-regulated, time down-regulated and capacity down-regulated respectively for each switch control scheme, P up 、t up 、W up Power up-regulated, time up-regulated and capacity up-regulated respectively for each switch control scheme, m n Starting up number m of air source heat pump for each switch control scheme b To realize the number of the startup machines when generating heat and balancing heat, P n Rated electric power of air source heat pump, t start To peak-shaving start time, t min T is the time when the temperature of the heat supply working medium reaches the lower limit of the temperature max The temperature of the heating working medium reaches the upper temperature limit.
Further, the quantization unit obtains the quantization power grid peak shaving capacity of the air source heat pump heating system through the following steps:
the first step, a switch control scheme for realizing heat generation and radiation balance and corresponding m are determined based on actual operation data of the air source heat pump heat supply system b ；
The second step, based on the actual operation data of the air source heat pump heat supply system, tracking the change condition of the heat supply working medium temperature under each switch control scheme by utilizing the heat supply working medium temperature prediction model, wherein when the heat supply working medium temperature reaches a preset temperature limit value, the switch control scheme is switched to the switch control scheme for realizing heat generation and radiation balance, and after the heat generation and radiation reach balance again, the switch control scheme is switched to each switch control scheme again;
and thirdly, determining the quantized power grid peak regulation capacity of the air source heat pump heat supply system corresponding to each switch control scheme in real time based on the tracking result of the heat supply working medium temperature prediction model.
While the foregoing is directed to embodiments of the present application, other and further embodiments of the invention may be devised without departing from the basic scope thereof, and the scope thereof is determined by the claims that follow.
Claims (6)
1. The utility model provides a power grid peak shaving capacity quantization method for quantifying the power grid peak shaving capacity of an air source heat pump heating system, wherein the air source heat pump heating system comprises a plurality of air source heat pumps and utilizes an air source to heat a heating working medium, and is characterized by comprising the following steps:
s1: determining a plurality of key parameters affecting the temperature of a heating working medium of an air source heat pump heating system;
s2: building a heat supply working medium temperature prediction model based on the key parameters and training by using historical operation data;
s3: obtaining the quantized power grid peak regulation capacity of the air source heat pump heat supply system by using the trained heat supply working medium temperature prediction model;
step S1 further comprises the steps of:
s11: based on the (1), a heat supply working medium thermodynamic process model of the air source heat pump heat supply system is established,
wherein ρ is the density of the heating medium, c is the specific heat capacity of the heating medium, V is the volume of the heating medium, and the unit is m 3 θ is the temperature of the heat supply working medium, t is time, and Φ is the heat variation of the heat supply working medium;
s12: determining the relation between phi and theta based on the formula (2),
wherein phi is p To generate heat for the system, phi d For the heat dissipation of the system, phi 1 Phi is the heating quantity of the opened air source heat pump 2 For solar radiant heat flow, COP n For the number of open air source heat pumps, P n The quantity of the air source heat pumps is h, the surface convection heat exchange coefficient is h, A is the total heat dissipation area, delta t is the time interval and theta out Is outdoor temperature;
s13: the surface convection heat transfer coefficient h of the (3) type is used for approximate characterization,
wherein N is u The number is Knoop, l is the characteristic size, and lambda is the heat conductivity coefficient of the heat supply working medium;
s14: determining influence M under forced convection heat exchange condition u Factors of (2)
Influence of N under natural convection heat exchange u Factors of (2)
Wherein Re is the Reynolds number, pr is the Plantains number, gr is the Gelating-Raf number, u, v and a are the flow velocity, the kinematic viscosity and the thermal diffusivity of the heating working medium respectively, g is the gravitational acceleration, alpha v For the volume expansion coefficient, Δθ b Is the temperature difference between the wall temperature and the ambient temperature;
s15: based on formulas (1) to (3) and the influence N u Determining a plurality of key parameters affecting θ;
the key parameters comprise the temperature of a heating working medium, the heat generation amount, the heat dissipation amount and the temperature difference between the indoor environment and the outdoor environment at the current moment;
the heat supply working medium temperature prediction model is a BP neural network model;
the quantized power grid peak regulation capability is a downtunable quantized value and/or an uptunable quantized value of the air source heat pump heating system corresponding to each switch control scheme;
The down-tunable quantization value corresponding to each switch control scheme is
And, the up-tunable quantization value corresponding to each switch control scheme is
Wherein P is down 、t down 、W down Power down-regulated, time down-regulated and capacity down-regulated respectively for each switch control scheme, P up 、t up 、W up Power up-regulated, time up-regulated and capacity up-regulated respectively for each switch control scheme, m n Starting up number m of air source heat pump for each switch control scheme b To realize the number of the startup machines when generating heat and balancing heat, P n Rated electric power of air source heat pump, t start To peak-shaving start time, t min T is the time when the temperature of the heat supply working medium reaches the lower limit of the temperature max The temperature of the heating working medium reaches the upper temperature limit;
step S3 further comprises the steps of:
s31: switch control scheme for realizing heat generation and dissipation balance based on actual operation data of air source heat pump heat supply system and corresponding m b ；
S32: tracking the change condition of the temperature of the heating working medium under each switch control scheme by utilizing the heating working medium temperature prediction model based on the actual operation data of the air source heat pump heating system, wherein the switch control scheme is switched to the switch control scheme for realizing heat generation and radiation balance when the temperature of the heating working medium reaches a preset temperature limit value, and the switch control scheme is switched to each switch control scheme again after the heat generation and radiation reach balance again;
S33: and determining the quantized grid peak shaving capacity of the air source heat pump heating system corresponding to each switch control scheme in real time based on the tracking result of the step S32.
2. The power grid peak shaver capacity quantization method according to claim 1, characterized in that:
the key parameters also comprise preset upper and lower limits of the temperature of the heating working medium.
3. The power grid peak shaver capacity quantization method according to claim 1, characterized in that:
the input quantity of the heat supply working medium temperature prediction model comprises operation data of the key parameters at least 2 time intervals at and before the time t;
and the output quantity of the heat supply working medium temperature prediction model is the heat supply working medium temperature of the next time interval at the moment t.
4. The utility model provides a power grid peak shaving ability quantization system for carry out the quantization to air source heat pump heating system's power grid peak shaving ability, air source heat pump heating system contains many air source heat pumps, utilizes the air source to heat heating medium, its characterized in that includes:
the parameter determining unit is used for determining a plurality of key parameters affecting the temperature of a heating working medium of the air source heat pump heating system;
the model training unit is used for establishing a heat supply working medium temperature prediction model based on the key parameters and training by using historical operation data;
The quantization unit is used for acquiring the quantization power grid peak regulation capacity of the air source heat pump heat supply system by using the trained heat supply working medium temperature prediction model;
the parameter determination unit determines the plurality of key parameters by:
the first step, a thermodynamic process model of a heat supply working medium of the air source heat pump heat supply system is established based on the formula (1),
wherein ρ is the density of the heating medium, c is the specific heat capacity of the heating medium, V is the volume of the heating medium, and the unit is m 3 θ is the temperature of the heat supply working medium, t is time, and Φ is the heat variation of the heat supply working medium;
a second step of determining the relation between phi and theta based on the formula (2),
wherein phi is p To generate heat for the system, phi d For the heat dissipation of the system, phi 1 Phi is the heating quantity of the opened air source heat pump 2 For solar radiant heat flow, COP n For the number of open air source heat pumps, P n The quantity of the air source heat pumps is h, the surface convection heat exchange coefficient is h, A is the total heat dissipation area, delta t is the time interval and theta out Is outdoor temperature;
thirdly, using the surface convection heat exchange coefficient h of the step (3) to perform approximate characterization,
wherein M is u The number is Knoop, l is the characteristic size, and lambda is the heat conductivity coefficient of the heat supply working medium;
fourth, determining the influence N under the condition of forced convection heat exchange u Factors of (2)
Influence of N under natural convection heat exchange u Factors of (2)
Wherein Re is the Reynolds number, pr is the Plantains number, gr is the Gelating-Raf number, u, v and a are the flow velocity, the kinematic viscosity and the thermal diffusivity of the heating working medium respectively, g is the gravitational acceleration, alpha v For the volume expansion coefficient, Δθ b Is the temperature difference between the wall temperature and the ambient temperature;
fifth, based on the formulas (1) to (3) and the influence N u Determining a plurality of key parameters affecting θ;
the key parameters comprise the temperature of a heating working medium, the heat generation amount, the heat dissipation amount and the temperature difference between the indoor environment and the outdoor environment at the current moment;
the heat supply working medium temperature prediction model is a BP neural network model;
the quantized power grid peak regulation capability is a downtunable quantized value and/or an uptunable quantized value of the air source heat pump heating system corresponding to each switch control scheme;
the down-tunable quantization value corresponding to each switch control scheme is
And, the up-tunable quantization value corresponding to each switch control scheme is
Wherein P is down 、t down 、W down Power down-regulated, time down-regulated and capacity down-regulated respectively for each switch control scheme, P up 、t up 、W up Power up-adjustable and time up-adjustable respectively for each switch control scheme Interval and up-adjustable capacity, m n Starting up number m of air source heat pump for each switch control scheme b To realize the number of the startup machines when generating heat and balancing heat, P n Rated electric power of air source heat pump, t start To peak-shaving start time, t min T is the time when the temperature of the heat supply working medium reaches the lower limit of the temperature max The temperature of the heating working medium reaches the upper temperature limit;
the quantization unit acquires the quantization power grid peak shaving capacity of the air source heat pump heat supply system through the following steps:
the first step, a switch control scheme for realizing heat generation and radiation balance and corresponding m are determined based on actual operation data of the air source heat pump heat supply system b ；
The second step, based on the actual operation data of the air source heat pump heat supply system, tracking the change condition of the heat supply working medium temperature under each switch control scheme by utilizing the heat supply working medium temperature prediction model, wherein when the heat supply working medium temperature reaches a preset temperature limit value, the switch control scheme is switched to the switch control scheme for realizing heat generation and radiation balance, and after the heat generation and radiation reach balance again, the switch control scheme is switched to each switch control scheme again;
and thirdly, determining the quantized power grid peak regulation capacity of the air source heat pump heat supply system corresponding to each switch control scheme in real time based on the tracking result of the heat supply working medium temperature prediction model.
5. The grid peak shaver capacity quantization system of claim 4, wherein:
the key parameters also comprise preset upper and lower limits of the temperature of the heating working medium.
6. The grid peak shaver capacity quantization system of claim 4, wherein:
the input quantity of the heat supply working medium temperature prediction model comprises operation data of the key parameters at least 2 time intervals at and before the time t;
and the output quantity of the heat supply working medium temperature prediction model is the heat supply working medium temperature of the next time interval at the moment t.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211228666.3A CN115660325B (en) | 2022-10-08 | 2022-10-08 | Power grid peak regulation capacity quantization method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211228666.3A CN115660325B (en) | 2022-10-08 | 2022-10-08 | Power grid peak regulation capacity quantization method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115660325A CN115660325A (en) | 2023-01-31 |
| CN115660325B true CN115660325B (en) | 2023-05-30 |
Family
ID=84986899
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211228666.3A Active CN115660325B (en) | 2022-10-08 | 2022-10-08 | Power grid peak regulation capacity quantization method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115660325B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009036415A (en) * | 2007-07-31 | 2009-02-19 | Mayekawa Mfg Co Ltd | Heat pump cycle system using geo-heat |
| CN110160127A (en) * | 2019-05-17 | 2019-08-23 | 烟台锐控自动化控制工程有限公司 | Mist based on fluid heat transferring modeling calculates three-level net for thermal control system |
| CN111578371A (en) * | 2020-05-22 | 2020-08-25 | 浙江大学 | Data-driven accurate regulation and control method for urban centralized heating system |
Family Cites Families (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000075903A (en) * | 1998-09-01 | 2000-03-14 | Toshiba Corp | Device and method for constructing operation quantity prediction model and computer-readable recording medium where operation quantity prediction model structuring program is recorded |
| CN105202623B (en) * | 2015-09-21 | 2018-02-23 | 国家电网公司 | A kind of thermal power plant unit heating peak modulation capacity Forecasting Methodology |
| CN106248259B (en) * | 2016-09-28 | 2018-09-25 | 华中科技大学 | A kind of system corrects the dynamic temperature measurement method of hot thermocouple inertial drift |
| CN107491626B (en) * | 2017-10-09 | 2019-09-27 | 清华大学 | A kind of calculating and modeling method of heat supply network heating power adjustability |
| CN108319131B (en) * | 2017-12-27 | 2021-02-26 | 国网山东省电力公司电力科学研究院 | Unit peak regulation capacity evaluation method based on data mining |
| CN109193808A (en) * | 2018-11-13 | 2019-01-11 | 国网河北能源技术服务有限公司 | Peak load regulation network energy force prediction method and device |
| GB201911093D0 (en) * | 2019-08-02 | 2019-09-18 | Exergyn Ltd | System and method for supporting SMA material and optimising heat transfer in a SMA heat pump |
| CN110906571B (en) * | 2019-11-30 | 2021-06-08 | 华南理工大学 | Solar heat pump hot water system control strategy optimization method based on machine learning |
| CN111047463B (en) * | 2019-12-02 | 2023-06-23 | 国网河北省电力有限公司电力科学研究院 | Peak regulating capability evaluation method for heat supply unit after heat supply modification by adopting low-temperature waste heat pump |
| CN111520808B (en) * | 2020-03-09 | 2021-04-13 | 华电电力科学研究院有限公司 | Complex combined heat and power heating system based on low-temperature waste heat recovery and electric heating load adjusting method |
| CN111429020B (en) * | 2020-04-07 | 2023-12-29 | 中国矿业大学 | Multi-time scale economic dispatching method of electric heating system considering heat storage characteristics of heat supply network |
| CN111626506B (en) * | 2020-05-27 | 2022-08-26 | 华北电力大学 | Regional photovoltaic power probability prediction method based on federal learning and cooperative regulation and control system thereof |
| CN112377985B (en) * | 2020-10-10 | 2022-02-01 | 湖南大唐先一科技有限公司 | Heat supply unit peak regulation lower limit evaluation method and system based on feedback neural network |
| CN112348696B (en) * | 2020-10-10 | 2024-03-22 | 湖南大唐先一科技有限公司 | BP neural network-based heating unit peak regulation upper limit evaluation method and system |
| CN113531644A (en) * | 2021-08-11 | 2021-10-22 | 山东佐耀智能装备股份有限公司 | Power grid dispatching and peak-shaving system of air source heat pump station |
| CN113606750B (en) * | 2021-10-09 | 2021-12-24 | 山东佐耀科技有限公司 | Peak regulation control instruction optimal distribution method and system for air source heat pump load |
| CN114485244B (en) * | 2022-02-14 | 2023-10-13 | 中国电建集团华东勘测设计研究院有限公司 | Thermal diode, thermal rectification coating, phase-change heat storage and supply device and heat monitoring method |
| CN114740727B (en) * | 2022-04-25 | 2024-05-17 | 东南大学溧阳研究院 | Dynamic energy efficiency optimization control method for air source heat pump under outdoor temperature disturbance condition |
-
2022
- 2022-10-08 CN CN202211228666.3A patent/CN115660325B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009036415A (en) * | 2007-07-31 | 2009-02-19 | Mayekawa Mfg Co Ltd | Heat pump cycle system using geo-heat |
| CN110160127A (en) * | 2019-05-17 | 2019-08-23 | 烟台锐控自动化控制工程有限公司 | Mist based on fluid heat transferring modeling calculates three-level net for thermal control system |
| CN111578371A (en) * | 2020-05-22 | 2020-08-25 | 浙江大学 | Data-driven accurate regulation and control method for urban centralized heating system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115660325A (en) | 2023-01-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109270842B (en) | Bayesian network-based regional heat supply model prediction control system and method | |
| CN108916986B (en) | Information physical fusion secondary pipe network variable flow hydraulic balance regulation and control method and system | |
| CN109253494B (en) | Control method of electric heat storage device based on heat load prediction | |
| CN112128841A (en) | Whole-network balance adjusting method based on load prediction and room temperature feedback correction | |
| CN107025334B (en) | Method and device for establishing overall dynamic model of heat users of central heating system | |
| Yuan et al. | Study on refined control and prediction model of district heating station based on support vector machine | |
| Ledva et al. | Real-time energy disaggregation of a distribution feeder's demand using online learning | |
| Yuan et al. | A new feedback predictive model for improving the operation efficiency of heating station based on indoor temperature | |
| Sun et al. | Integrated control strategy of district heating system based on load forecasting and indoor temperature measurement | |
| CN114565167B (en) | Dynamic load prediction and regulation method for thermal inlet | |
| Sretenović et al. | Support vector machine for the prediction of heating energy use | |
| CN116624984A (en) | Economic and responsive double-objective optimization model predictive control method for ice storage air conditioning system | |
| Sun et al. | Research on control strategy integrated with characteristics of user's energy-saving behavior of district heating system | |
| CN116436033A (en) | Temperature control load frequency response control method based on user satisfaction and reinforcement learning | |
| Huang et al. | Model predictive control for energy-efficient buildings: An airport terminal building study | |
| CN114484556B (en) | Water supply temperature regulation and control method based on target energy consumption management and control | |
| CN111473408A (en) | Control method of heat supply control system based on climate compensation | |
| CN112268350B (en) | Air conditioner side load prediction method based on system delay | |
| CN115660325B (en) | Power grid peak regulation capacity quantization method and system | |
| Wang et al. | Research on intelligent regulation of air conditioning energy saving based on human thermal comfort | |
| Hlava et al. | Application of PID controller based on the localization method for ancillary service provision | |
| CN116307074A (en) | Method for acquiring real thermal data, system and method for constructing neural network model of thermal data, and method for predicting thermal load | |
| CN113078629B (en) | Aggregate power distribution model for cluster temperature control load aggregate power regulation and control and distributed consistency control method | |
| Martinčević et al. | Comfort control in buildings with adherence to the required thermal energy input in zones | |
| CN113701232A (en) | Heat supply system building-level regulation and control method and system based on temperature diversity analysis |
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 |