A central air conditioning system dynamic energy management method and system based on a large model

Abstract

The present application relates to the technical field of energy management, and is a central air conditioning system dynamic energy management method and system based on a large model, specifically comprising: rolling output of short-term load demand prediction curves through a time series deep prediction model; inversion calculation of equivalent heat capacity and equivalent thermal resistance of building materials through a physical information neural network, and real-time quantification of building material thermal inertia parameters; evaluation of phase change delay time coefficients of building materials; acquisition of photovoltaic power generation prediction curves and grid time-of-use electricity price signals of a power grid system, determination of optimal energy charging and discharging time windows of building materials; and decision-making generation of optimal operation strategies of central air conditioning systems through a multi-objective decision-making algorithm. The present application solves the problem in the prior art of the lack of construction of an energy management system matched with the thermal dynamic characteristics of a building.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of energy management, and is a central air conditioning system dynamic energy management method and system based on a large model. BACKGROUND

[0002] The current energy management strategy of the central air conditioning system has serious adaptability problems when facing modern buildings using new high-performance energy-saving building materials, such as phase change materials PCM and high-heat-capacity concrete. Traditional building management systems (BMS) mostly rely on simple feedback control mechanisms (such as PID control) or static load prediction models based on historical meteorological data and operation records. The time scale of the control response is minute-level, while the thermal dynamic process of high-thermal-inertia building materials shows a slow response of hours or even days. This fundamental time scale mismatch leads to significant control lag and over-regulation of the system, which is specifically manifested in that: at the initial stage of refrigeration demand, the air conditioning output is difficult to quickly affect the indoor environment, and after the refrigeration equipment is turned off, the heat or cold stored by the building materials is still released, causing temperature fluctuations and energy waste. In addition, conventional prediction models do not consider the thermal inertia parameters of building structures and their time-varying characteristics, which cannot accurately quantify the thermal energy storage effect of building materials and cannot effectively coordinate the operation of central air conditioning and intermittent renewable energy (such as photovoltaic), resulting in the inability to achieve effective peak shaving and valley filling under the mechanism of time-of-use electricity price, and instead, the improper control may cause adverse effects, such as forced high-load operation during the peak period of night-time electricity price to offset the release of building material heat storage, causing double losses in economy and energy efficiency. SUMMARY

[0003] The application aims to solve the problem in the prior art that there is a lack of energy management systems matched with the thermal dynamic characteristics of buildings, and provides a central air conditioning system dynamic energy management method and system based on a large model.

[0004] To achieve the above purpose, the technical scheme of the central air conditioning system dynamic energy management method based on a large model comprises the following steps:

[0005] S1: fuse real-time indoor and outdoor environment data and central air conditioning equipment state data, and roll out a short-term load demand prediction curve through a time series deep prediction model;

[0006] S2: collect temperature field data of building materials, calculate the equivalent heat capacity and equivalent thermal resistance of the building materials through a physical information neural network, and quantize the thermal inertia parameters of the building materials in real time;

[0007] S3: based on the real-time quantized thermal inertia parameters of the building materials in S2, predict the temperature field change trend of the building structure in the next 3 hours, and based on the predicted temperature field change trend, evaluate the phase change delay time coefficient of the building materials.

[0008] S4: Obtain the photovoltaic power prediction curve of the power grid system and the time-of-use electricity price signal of the power grid, and determine the optimal energy charging and discharging time window of the building materials;

[0009] S5: According to S1-S4, a multi-objective decision algorithm is used to generate the optimal operation strategy of the central air conditioning system.

[0010] Preferably, in S1, the short-term refined load demand prediction curve is a refined load demand prediction curve for several hours in the future;

[0011] The acquisition strategy of the short-term refined load demand prediction curve comprises:

[0012] S11: According to real-time indoor and outdoor environmental data and equipment state data of the central air conditioner, a feature weighting fusion is performed using an attention mechanism to dynamically correct the short-term load prediction result;

[0013] S12: A multi-scale convolutional neural network is used to extract periodic patterns, trend components and abnormal fluctuation features in the historical load sequence, and the future 6-hour load prediction value is updated at a time interval of 1 hour to obtain the short-term load demand prediction curve. .

[0014] Preferably, S2 comprises the following steps:

[0015] S21: Collect temperature sensor data inside the east, south, west and north facades and the roof of the building, as well as corresponding external surface solar radiation intensity data, to form a multi-dimensional thermal state sequence, and perform data standardization processing according to the differences in solar radiation of different facades;

[0016] S22: Input the above multi-dimensional sequence into a physical information neural network, which takes the unsteady heat conduction equation as a physical constraint to construct a loss function , and optimizes the phase change material characteristics of the building materials through the loss function ;

[0017] S23: Obtain the equivalent thermal inertia parameters of the building materials by minimizing the loss function , wherein the equivalent thermal inertia parameters comprise an equivalent heat capacity and an equivalent thermal resistance ;

[0018] S24: Extract the equivalent thermal inertia parameters output by step S23, and obtain the real-time thermal inertia index of the building materials by dividing the equivalent heat capacity by the equivalent thermal resistance ;

[0019] S25: Real-time monitoring of the phase change state of the building material, and calculating the phase change degree of the building material ;

[0020] Based on the phase change degree of the building material Calculate the latent heat absorption and release rate .

[0021] Preferably, S3 comprises:

[0022] S31: Based on the equivalent thermal inertia parameter, the building structure is simplified into a thermal network model composed of thermal resistance and thermal capacity nodes, the differential equation of the discrete time state space of the thermal network model is established according to the law of conservation of energy, and the temperature field change trend of the building structure in the future 3 hours is predicted by Euler algorithm;

[0023] S32: Based on the predicted temperature field change trend, the phase change delay time coefficient of the building material is evaluated .

[0024] Preferably, S4 comprises the following steps:

[0025] S41: Extracting the real-time thermal inertia index of the building material output by step S25 , and performing thermal response capacity level analysis and verification of the building material according to the preset thermal inertia index threshold When the real-time thermal inertia index of the building material is greater than or equal to the thermal inertia index threshold , it is judged that the building thermal inertia is strong, and the predictive energy storage control is adopted, and step S42 is continued;

[0026] When the real-time thermal inertia index of the building material is less than the thermal inertia index threshold , it is judged that the building thermal inertia is weak, and the standard prediction control strategy is continued to be used;

[0027] S42: Presetting the latent heat effective utilization rate threshold and the phase change delay time coefficient threshold ;

[0028] S43: In step S1, the future 3-hour load prediction curve is intercepted from the load demand prediction curve, the peak load period and the valley load period are extracted, and the high peak load set and the low peak load set are respectively constituted, and the photovoltaic power generation peak period and the power grid electricity price peak period are identified;

[0029] S44: Screening the period in the high peak load set with latent heat utilization rate lower than or delay time higher than , and the number of screened periods is ;

[0030] S45: According to the thermal inertia parameter of the building material and the number of time periods screened out, the optimal charging and discharging time window of the building material is determined as The optimal charging and discharging time window of the building material is calculated, specifically:

[0031] ;

[0032] Wherein, are the optimal charging time and the optimal discharging time of the building material, respectively; are the starting time of the low price of the power grid and the starting time of the high price of the power grid, respectively;

[0033] are the difference between the set temperature of the building interior and the maximum temperature allowed by the building structure to operate; is the temperature difference between the inside and outside of the building at the current time;

[0034] is the thermal inertia time constant of the building material, which is the product of the equivalent heat capacity and the equivalent thermal resistance output in step S23; is a time delay parameter determined according to the material properties of the building material.

[0035] Preferably, S51: according to S41-S45, the control parameters to be updated of the central air conditioning system are calculated, and the control parameter adjustment strategy is specifically as follows:

[0036] ;

[0037] Wherein, k is the number of iterations of the control parameter optimization; is the comprehensive energy efficiency ratio of the central air conditioning system in the kth iteration; is the new comprehensive energy efficiency ratio target value of the central air conditioning system in the next iteration;

[0038] Z is the total number of time periods; is the preset threshold of the number of time periods; is the weight coefficient of the influence of the thermal characteristics of the building material;

[0039] S52: The updated comprehensive energy efficiency ratio target value of the optimized central air conditioning system is extracted and stored in the cloud database, and is simultaneously issued to the local controllers of the refrigeration host of the central air conditioning, the variable frequency water pump and the cooling tower through the industrial communication protocol.

[0040] S53: The power generation data of the photovoltaic power generation peak period is extracted to form a photovoltaic output set, and the air conditioning refrigeration load data of the same period is simultaneously extracted to form an air conditioning load set, and the basic load and the adjustable load are distinguished;

[0041] S54: Adopting energy management strategy based on thermal inertia of building materials, including: evaluating target cold storage capacity of building materials , monitoring cumulative cold storage capacity of building materials in real time;

[0042] When cumulative cold storage capacity is lower than target cold storage capacity , increasing running power of central air conditioning system during peak period of photovoltaic power generation, and storing excess cold in high thermal inertia building materials;

[0043] When cumulative cold storage capacity is equal to or higher than target cold storage capacity , indicating that cold storage of building materials is completed, and adjusting running power of central air conditioning system to normal working level;

[0044] The calculation strategy of target cold storage capacity is as follows:

[0045] ;

[0046] Wherein, is photovoltaic power at time t; is basic load power at time t; is latent heat absorbed or released during phase change of building materials;

[0047] S55: Evaluating mismatch degree from three different dimensions of photovoltaic output, air conditioning load and heat capacity respectively, obtaining photovoltaic evaluation item, air conditioning load evaluation item and heat capacity matching item, and synchronously evaluating photovoltaic-air conditioning load matching degree from the three dimensions .

[0048] S56: Extracting photovoltaic-air conditioning load matching degree , and judging switching of central air conditioning working mode, including:

[0049] Pre-setting matching degree threshold , and analyzing collaborative level according to matching degree, when photovoltaic-air conditioning load matching degree is greater than or equal to , triggering collaborative control execution mode;

[0050] When photovoltaic-air conditioning load matching degree is less than , not triggering collaborative control execution unit, and starting backup power grid power supply strategy;

[0051] The collaborative control execution mode includes: increasing running power of air conditioning system during peak period of photovoltaic output, storing excess cold in building structure, and releasing stored cold during peak period of electricity price.

[0052] In addition, the application discloses a central air conditioning system dynamic energy management system based on a large model.

[0053] The load prediction module, the thermal inertia quantification module, the phase change quantification module, the dynamic energy storage control module and the air conditioner operation optimization module;

[0054] The load prediction module is used for fusing real-time indoor and outdoor environment data and central air conditioner equipment state data, and outputting a short-term load demand prediction curve through a time series deep prediction model.

[0055] The thermal inertia quantification module is used for collecting temperature field data of building materials, and inversely calculating the equivalent heat capacity and the equivalent thermal resistance of the building materials through a physical information neural network, and quantifying the thermal inertia parameters of the building materials in real time.

[0056] The phase change quantification module is used for predicting the temperature field change trend of the building structure in the next three hours, and evaluating the phase change delay time coefficient of the building materials based on the predicted temperature field change trend.

[0057] The dynamic energy storage control module is used for obtaining a photovoltaic power generation prediction curve of a power grid system and a power grid time-of-use price signal, and determining the optimal energy charging and discharging time window of the building materials.

[0058] The air conditioner operation optimization module adopts a multi-objective decision algorithm to generate an optimal operation strategy of the central air conditioning system.

[0059] Compared with the prior art, the application has the following technical effects:

[0060] 1. The application inversely calculates the equivalent heat capacity and the equivalent thermal resistance of the building structure through a physical information neural network, and evaluates the phase change degree of the building materials in real time, fundamentally solving the serious control lag and excessive response problem caused by the inability to quantify the thermal dynamic characteristics of the building materials in the prior control method, enabling the system to accurately predict the temperature field change trend of the building structure in the future hours, and calculating the optimal energy charging and discharging time window in advance based on the phase change delay time constant, thereby completely avoiding room temperature fluctuation and energy waste, and greatly improving indoor thermal comfort and system operation stability.

[0061] 2. The application performs multi-objective collaborative optimization on photovoltaic power generation prediction, power grid time-of-use price signals and building energy storage characteristics, actively increases air conditioner operation power to store cold energy during the photovoltaic output peak period, and releases the stored cold energy to reduce power grid power purchase demand during the price peak period, thereby greatly improving the self-use rate of photovoltaic energy, realizing significant peak clipping and valley filling effect, effectively reducing system operation cost, and through the introduction of a photovoltaic-air conditioner load matching degree index and threshold judgment mechanism, intelligently switching the collaborative control and power grid power supply modes, and ensuring the reliability and economy of the energy dispatching strategy.

[0062] 3、The application realizes the multi-objective balance of energy consumption economy, indoor comfort and demand response income by dynamically coordinating the running state of air conditioning host, water pump and other equipment through the adaptive adjustment mechanism of the system comprehensive energy efficiency ratio as the core control parameter, so that it is always in the high-efficiency working interval. BRIEF DESCRIPTION OF DRAWINGS

[0063] In order to more clearly illustrate the technical solutions of the embodiments of the application, the drawings needed to be used in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor. Among them:

[0064] Figure 1 It is a flowchart of a dynamic energy management method of a central air conditioning system based on a large model of the application;

[0065] Figure 2 It is a structural schematic diagram of a dynamic energy management system of a central air conditioning system based on a large model of the application. DETAILED DESCRIPTION

[0066] In order to make the above-mentioned purposes, features and advantages of the application more obvious and easy to understand, the specific embodiments of the application will be described in detail below with reference to the drawings of the specification.

[0067] In the following description, many specific details are set forth in order to provide a thorough understanding of the application, but the application can also be implemented in other ways different from those described herein, and those skilled in the art can make similar generalizations without departing from the connotation of the application, therefore the application is not limited by the specific embodiments disclosed below.

[0068] Secondly, the "one embodiment" or "embodiment" referred to herein means that the specific features, structures or characteristics can be included in at least one implementation of the application. "In one embodiment" appearing in different places in this specification does not mean the same embodiment, nor is it an independent or alternative embodiment that excludes other embodiments.

[0069] Embodiment one:

[0070] As shown in the figure, a dynamic energy management method of a central air conditioning system based on a large model of the embodiment of the application, as shown in the figure, includes the following specific steps: Figure 1 Figure 1 S1: fuse real-time indoor and outdoor environment data and central air conditioning equipment state data, and output short-term load demand prediction curve through time series deep prediction model rolling;

[0071] S1: fuse real-time indoor and outdoor environment data and central air conditioning equipment state data, and output short-term load demand prediction curve through time series deep prediction model rolling; ​

[0072] In S1, the short-term refined load demand prediction curve is a refined load demand prediction curve for several hours in the future.

[0073] The acquisition strategy of the short-term refined load demand prediction curve comprises:

[0074] S11: According to real-time indoor and outdoor environment data and equipment state data of the central air conditioner, a feature weighting fusion is performed by using an attention mechanism to dynamically correct the short-term load prediction result.

[0075] S12: A multi-scale convolutional neural network is used to extract periodic patterns, trend components and abnormal fluctuation features in the historical load sequence, and a 1-hour time interval is used to rollingly update the future 6-hour load prediction value to obtain the short-term load demand prediction curve. .

[0076] Exemplarily, in the embodiment, the time series deep prediction model adopts a hybrid architecture combining a time convolution network and a Transformer attention mechanism.

[0077] S2: Collecting temperature field data of building materials, calculating the equivalent heat capacity and equivalent thermal resistance of the building materials by physical information neural network inversion, and quantifying the thermal inertia parameters of the building materials in real time.

[0078] S2 comprises the following steps:

[0079] S21: Collecting temperature sensor data inside the east, south, west and north facades and the roof of the building, as well as corresponding external surface solar radiation intensity data, to form a multi-dimensional thermal state sequence, and performing data standardization processing for different facades subjected to different solar radiation;

[0080] S22: Inputting the above multi-dimensional sequence into a physical information neural network, the physical information neural network taking a non-steady-state heat conduction equation as a physical constraint to construct a loss function , and optimizing the phase change material characteristics of the building materials through the loss function ;

[0081] Exemplarily, in the embodiment, the construction of the loss function comprises: simultaneously constructing a first loss term , a second loss term and a third loss term , and performing normalization and weighted summation processing on the first loss term , the second loss term and the third loss term by using a preset first weight coefficient, a second weight coefficient and a third weight coefficient, respectively, to finally obtain the loss function ;

[0082] The first loss term is: ;

[0083] wherein N is the number of temperature measurement points; represents the temperature predicted by the physical information neural network at the i th measurement point; represents the temperature actually measured at the i th point;

[0084] It should be noted that the first loss term is a data fitting term, which aims to quantify the prediction error of the physical information neural network;

[0085] The second loss term is: ;

[0086] wherein M is the number of configuration points randomly selected in the calculation domain, which is used to verify whether the physical information neural network satisfies the heat conduction law; is the partial derivative of temperature with respect to time; is the thermal diffusivity of the building material; is the Laplacian of temperature, which represents the spatial temperature distribution non-uniformity;

[0087] It should be noted that the second loss term is a physical constraint term, which is constructed based on the partial differential equation in the embodiment, which represents the instantaneous change rate of the temperature of a point inside an object, which is proportional to the temperature distribution around the point;

[0088] The third loss term is: ;

[0089] It should be noted that the third loss term is a phase change characteristic term; wherein K is the number of monitoring points for monitoring the phase change degree of the building material; is the predicted value of the phase change degree of the building material, is the actually measured phase change degree of the building material;

[0090] S23: The equivalent thermal inertia parameters of the building material are obtained by minimizing the loss function , wherein the equivalent thermal inertia parameters include: equivalent heat capacity and equivalent thermal resistance ;

[0091] S24: The equivalent thermal inertia parameters output by step S23 are extracted, and the real-time thermal inertia index of the building material is obtained by dividing the equivalent heat capacity by the equivalent thermal resistance ;

[0092] It should be noted that the thermal inertia index of building materials Used to quantify the heat storage and release capacity of new building materials;

[0093] S25: Real-time monitoring of the phase transition state of building materials and calculation of the degree of phase transition of building materials. ;

[0094] Based on the degree of phase change of building materials Calculate the latent heat absorption and desorption rate ;

[0095] For example, in this embodiment, a phase change degree of building materials is provided. The calculation strategy is as follows:

[0096] ;

[0097] in, Let i be the temperature measurement value at the i-th temperature measurement point. The phase transition temperature of building materials is given by , and k is the phase transition slope coefficient.

[0098] It should be noted that, considering that the phase change process of building materials is not completed instantaneously at a precise temperature point, but occurs gradually within a temperature range, the Sigmoid function is used to describe the phase change process of building materials in this embodiment. It should also be noted that, considering that the temperature distribution of phase change building materials in building components is not completely uniform, averaging is used to quantify the spatial average of the phase change degree of building materials.

[0099] For example, based on the law of conservation of energy, this embodiment also provides a method based on the degree of phase transition of building materials. Calculate the latent heat absorption and desorption rate The implementation example is as follows:

[0100] ;

[0101] in, V is the density of building materials, V is the total volume of building materials, and L is the latent heat value;

[0102] It should be noted that, This indicates the heat power absorbed or released by building materials per unit time due to phase change;

[0103] S3: Based on the real-time quantified thermal inertia parameters of building materials in S2, predict the temperature field change trend of the building structure in the next 3 hours, and evaluate the phase change delay time coefficient of building materials based on the predicted temperature field change trend.

[0104] S3 includes:

[0105] S31: Based on the equivalent thermal inertia parameter, the building structure is simplified into a thermal network model composed of thermal resistance and thermal capacity nodes, differential equations of the discrete time state space of the thermal network model are established according to the law of conservation of energy, and the temperature field change trend of the building structure in the next 3 hours is predicted by solving through the Euler algorithm;

[0106] Exemplarily, in the embodiment, a prediction implementation example of the temperature field change trend of the building structure in the next 3 hours is provided, comprising:

[0107] In the embodiment, the building is regarded as a uniform whole point, that is, a first-order RC model, the equivalent thermal capacity and the equivalent thermal resistance are taken as the resistance and the capacitance of the first-order RC model, and the outdoor temperature and the indoor temperature of the building are taken as the voltage source and the voltage across the capacitance of the first-order RC model. When the central air conditioning system operates at a power of , it acts as a reverse current source (that is, a heat absorption source) of the first-order RC model.

[0108] According to the law of conservation of energy, differential equations of the discrete time state space are established, specifically:

[0109]

[0110] For the above differential equation, in the embodiment, it needs to be explained that the left side of the differential equation is intended to represent the instantaneous power of the energy increase in the building; and the right side of the differential equation is intended to represent all external sources causing the energy change in the building, in which is the heat invasion power due to the outdoor temperature, is the refrigeration power of the central air conditioning when refrigerating, which represents the process of removing heat from the building, so subtraction is used to quantify the process of removing heat by the central air conditioning.

[0111] The current indoor and outdoor temperature and the internal temperature monitoring value of the building material are taken as the initial state, the future weather forecast data and the operating set value are taken as the input, the above differential equation is recursively solved through the Euler algorithm, and the temperature field change trend of the building structure in the next 3 hours is predicted.

[0112] S32: Based on the predicted temperature field change trend, the phase change delay time coefficient of the building material is evaluated.

[0113] Exemplarily, in the embodiment, an evaluation strategy of the phase change delay time coefficient of the building material is provided, specifically:

[0114] ;

[0115] wherein, is the actual temperature change curve, is the temperature curve of the temperature field change trend predicted in step S31, is the lowest temperature measurement value in the observation period; is the observation period;

[0116] It should be noted that in the present embodiment, the phase change delay time coefficient of the building material is evaluated to quantify the thermal response hysteresis of the building material.

[0117] S4: Obtain the photovoltaic power generation prediction curve of the power grid system and the time-of-use electricity price signal of the power grid, and determine the optimal charging and discharging time window of the building material;

[0118] S4 includes the following steps:

[0119] S41: Extract the real-time thermal inertia index of the building material output in step S25 , and perform thermal response capacity level analysis and verification according to a preset thermal inertia index threshold , when the real-time thermal inertia index of the building material is greater than or equal to the thermal inertia index threshold , it is judged that the building thermal inertia is strong, and the predictive energy storage control is adopted, and step S42 is continued to be executed;

[0120] When the real-time thermal inertia index of the building material is less than the thermal inertia index threshold , it is judged that the building thermal inertia is weak, and the standard prediction control strategy is continued to be adopted.

[0121] S42: Preset latent heat effective utilization rate threshold and phase change delay time coefficient threshold ;

[0122] Exemplarily, in the present embodiment, a preset strategy of the latent heat effective utilization rate threshold is provided, specifically: ;

[0123] wherein, is the maximum theoretical latent heat absorption or release rate determined according to the material properties of the building material;

[0124] It should be noted that, is used to quantify the percentage of the latent heat capacity of the building material that is effectively utilized in actual operation; represents the cumulative latent heat absorbed or released by the building material during the actual observation period; represents the maximum latent heat that the building material can theoretically absorb or release during the same observation period.

[0125] S43: The load demand prediction curve in step S1 intercepts the future 3-hour load prediction curve, extracts the peak load period and the valley load period, respectively constitutes the peak load set and the valley load set, and identifies the peak period of photovoltaic power generation and the peak period of power grid electricity price;

[0126] S44: Screening the periods in the peak load set with latent heat utilization rate lower than or delay time higher than The number of periods screened is ;

[0127] S45: According to the thermal inertia parameter of the building material and the number of periods screened , the optimal charging and discharging time window of the building material is calculated, which is specifically:

[0128] ;

[0129] Among them, respectively, the optimal charging time and the optimal discharging time of the building material; respectively, the start time of the low price of the power grid and the start time of the high price of the power grid;

[0130] respectively, the difference between the set temperature of the building interior and the maximum temperature allowed by the building structure to operate; is the temperature difference between the inside and outside of the building at the current time;

[0131] is the thermal inertia time constant of the building material, which is the product of the equivalent heat capacity and the equivalent thermal resistance output in step S23; is a time delay parameter determined according to the material properties of the building material.

[0132] It should be noted that the building material has both inherent thermal inertia time constant , and additional response delay during phase change, that is, ;

[0133] It should be noted that in the embodiment, based on the start time of the low price of the power grid and the high price of the power grid, specifically, considering the strong thermal inertia of the building materials, the response of the building materials to the temperature has thermal inertia, for the start time of the low price of the power grid, subtract the time item generated by the response of the building materials, and aim to extract the building materials in the energy absorption state before the start time of the low price of the power grid, so as to reach the expected state at the target time (i.e. the start time of the low price electricity);

[0134] For the above Aim to quantify how many thermal inertia time constants of the building materials are needed to change from the current state to the target state;

[0135] S5: According to S1-S4, a multi-objective decision algorithm is used to generate the optimal operation strategy of the central air conditioning system.

[0136] S5 includes:

[0137] S51: According to S41-S45, the control parameters to be updated of the central air conditioning system are calculated, and the control parameter adjustment strategy is as follows:

[0138] ;

[0139] Wherein, k is the number of iterations of the control parameter optimization; is the comprehensive energy efficiency ratio of the central air conditioning system in the kth iteration; is the new comprehensive energy efficiency ratio target value of the central air conditioning system in the next iteration;

[0140] Z is the total number of time periods; is the preset threshold of the number of time periods; is the weight coefficient of the influence of the thermal characteristics of the building materials;

[0141] In the embodiment, it should be noted that the building materials in step S43 are screened Aim to represent how many time periods the performance of the building materials in storing or releasing energy is not up to standard;

[0142] When , it means that these time periods cannot meet the future load demand in the building independently by the building materials, therefore, the operation energy efficiency target COP of the central air conditioning system needs to be improved to compensate for the insufficient energy storage of the building materials;

[0143] And when , it means that these time periods can meet the future load demand in the building independently by the building materials, at this time, the operation energy efficiency target COP of the central air conditioning system is reduced to save energy.

[0144] S52: extract and store the updated integrated energy efficiency ratio target value of the optimized central air conditioning system to the cloud database, and issue it to the local controllers of the refrigeration host, variable frequency water pump and cooling tower of the central air conditioning through the industrial communication protocol.

[0145] Exemplarily, in the present embodiment, after receiving the updated integrated energy efficiency ratio target value, the local controllers of the refrigeration host, variable frequency water pump and cooling tower of the central air conditioning call the internal preset optimization algorithm to autonomously solve and adjust the local execution equipment to the optimal working point. Exemplarily, the optimization algorithm is fuzzy PID.

[0146] In the present embodiment, it is also necessary to point out that, in order to avoid frequent start and stop of the equipment, a smooth transition algorithm is adopted when adjusting the frequency of the refrigeration host.

[0147] S5 also includes:

[0148] S53: extract the power generation data of the photovoltaic power generation peak period to form a photovoltaic output set, and synchronously extract the air conditioning refrigeration load data of the same period to form an air conditioning load set, and distinguish the basic load and the adjustable load;

[0149] S54: adopt an energy management strategy based on the thermal inertia of building materials, which specifically includes: evaluating the target cold storage capacity of the building materials , and monitoring the cumulative cold storage capacity of the building materials in real time;

[0150] When the cumulative cold storage capacity is lower than the target cold storage capacity , increase the operating power of the central air conditioning system during the photovoltaic power generation peak period, and store the excess cold in the high thermal inertia building materials;

[0151] When the cumulative cold storage capacity is equal to or higher than the target cold storage capacity , it means that the cold storage of the building materials is completed, and the operating power of the central air conditioning system is adjusted to the normal working level;

[0152] The calculation strategy of the target cold storage capacity is as follows:

[0153] ;

[0154] Wherein, is the photovoltaic power at time t; is the basic load power at time t; is the latent heat absorbed or released during the phase change of the building materials;

[0155] In the present embodiment, the acquisition strategy of the latent heat absorption and release rate In a time period from the start time of the building material cold accumulation to the current time, the building material cold accumulation degree is calculated by integration ;

[0156] S55: The mismatch degree is evaluated from three different dimensions of photovoltaic output, air conditioning load and heat capacity respectively to obtain a photovoltaic evaluation item, an air conditioning load evaluation item and a heat capacity matching item, and the photovoltaic-air conditioning load matching degree is synchronously evaluated from the three dimensions .

[0157] Exemplarily, in the embodiment, the calculation strategy of the photovoltaic-air conditioning load matching degree is that the mismatch degree is evaluated from three different dimensions of photovoltaic output, air conditioning load and heat capacity respectively to obtain a photovoltaic evaluation item, an air conditioning load evaluation item and a heat capacity matching item, and then the three evaluation items are weighted and summed to obtain the photovoltaic-air conditioning load matching degree ;

[0158] wherein, the photovoltaic evaluation item, the air conditioning load evaluation item and the heat capacity matching item are respectively;

[0159] In the embodiment, ; ;

[0160] wherein, is the photovoltaic power at t time; is the air conditioning refrigeration demand power at t time predicted in step S1; are respectively the maximum value and the minimum value of the photovoltaic power; are respectively the maximum value and the minimum value of the air conditioning refrigeration power;

[0161] In the embodiment, ;

[0162] wherein, is the available heat capacity of the building structure at t time, which represents how much heat the building structure can absorb or release at t time; is the required heat capacity at t time, which represents how much heat energy the building structure needs to absorb or release from t time, so as to meet the comfort demand inside the building, i.e. the central air conditioner can meet the predicted load demand; is the maximum heat capacity that the building structure can store.

[0163] It should be noted that in the embodiment, the acquisition strategy of is that the measured average temperature of the current building structure is extracted, the temperature upper limit of the running temperature range allowed by the building structure is first subtracted from the measured average temperature, and then the equivalent heat capacity is multiplied by the difference to obtain ;

[0164] It should be noted that, in this embodiment, The acquisition strategy is as follows: obtain the current target set temperature of the central air conditioning system, simultaneously extract the predicted temperature field change trend of the building structure for the next 3 hours obtained in step S31, calculate the difference between the target set temperature and the predicted temperature in the temperature field change trend, and use the equivalent heat capacity... Multiplying this by the difference obtained earlier yields... ;

[0165] It should be noted that, in this embodiment, The value is the equivalent heat capacity output in step S23. The product of the building structure's permissible operating temperature range and the actual operating temperature range.

[0166] S56: Extracting the photovoltaic-air conditioning load matching degree To determine the switching of the central air conditioning operating mode, including:

[0167] Preset matching threshold And based on the matching degree, a coordination level analysis is performed. When the photovoltaic-air conditioning load matching degree is... Greater than or equal to At that time, the collaborative control execution mode is triggered;

[0168] When the photovoltaic-air conditioning load matching degree Less than At this time, the coordinated control execution unit is not triggered, and the backup power grid supply strategy is started;

[0169] The collaborative control execution mode includes: increasing the operating power of the air conditioning system during peak photovoltaic output periods, storing excess cooling capacity in the building structure, and releasing the stored cooling capacity during peak electricity price periods to reduce the cost of purchasing electricity from the grid.

[0170] In this embodiment, it should also be noted that the energy charging and discharging process of building materials adopts a fuzzy control algorithm to ensure that indoor temperature fluctuations are within a comfortable range.

[0171] Example 2:

[0172] like Figure 2 As shown in the figure, an embodiment of the present invention provides a dynamic energy management system for a central air conditioning system based on a large model, such as... Figure 2 As shown, it includes the following modules:

[0173] Load forecasting module, thermal inertia quantification module, phase change quantification module, dynamic energy storage control module, and air conditioning operation optimization module;

[0174] The load prediction module is configured to fuse real-time indoor and outdoor environment data and equipment state data of the central air conditioner, and output a short-term load demand prediction curve through a time series deep prediction model;

[0175] The thermal inertia quantification module is configured to collect temperature field data of the building materials, calculate the equivalent heat capacity and equivalent thermal resistance of the building materials through a physical information neural network, and quantize the thermal inertia parameters of the building materials in real time;

[0176] The phase change quantification module is configured to predict the temperature field change trend of the building structure in the next 3 hours, and evaluate the phase change delay time coefficient of the building materials based on the predicted temperature field change trend;

[0177] The dynamic energy storage control module is configured to obtain a photovoltaic power generation prediction curve of a power grid system and a time-of-use electricity price signal, and determine an optimal energy charging and discharging time window of the building materials;

[0178] The air conditioner operation optimization module adopts a multi-objective decision algorithm to determine an optimal operation strategy of the central air conditioner system.

[0179] Embodiment three:

[0180] The embodiment provides an electronic device, comprising a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0181] The processor executes the above-mentioned central air conditioner system dynamic energy management method based on a large model by calling the computer program stored in the memory.

[0182] The electronic device can have great differences due to different configurations or performances, and can include one or more processors (Central Processing Units, CPU) and one or more memories, wherein the memory stores at least one computer program, which is loaded and executed by the processor to realize the central air conditioner system dynamic energy management method based on a large model provided by the above-mentioned method embodiment. The electronic device can also include other components for realizing device functions, for example, the electronic device can also have a wired or wireless network interface and an input and output interface, etc., so as to perform data input and output. This embodiment will not be described here.

[0183] Embodiment four:

[0184] The embodiment provides a computer readable storage medium, which stores an erasable computer program;

[0185] When the computer program runs on the computer device, the computer device executes the above-mentioned central air conditioner system dynamic energy management method based on a large model.

[0186] For example, the computer readable storage medium can be read-only memory (ROM), random access memory (RAM), compact disc read-only memory (CD-ROM), magnetic tape, floppy disk, and optical data storage device, etc.

[0187] It should be understood that the size of the sequence number of the above processes does not mean the order of execution in various embodiments of the present application, and the execution order of the processes should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0188] It should be understood that determining B according to A does not mean that B is determined only according to A, but B can also be determined according to A and / or other information.

[0189] The above embodiments can be realized wholly or partially by software, hardware, firmware or any combination thereof. When realized by software, the above embodiments can be realized wholly or partially in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the flow or function according to the embodiments of the present application is wholly or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions can be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center through a wired network or / and wireless network. The computer readable storage medium can be any available medium accessible by a computer or a data storage device such as a server, data center and the like containing one or more available medium collections. The available medium can be a magnetic medium (for example, floppy disk, hard disk, magnetic tape), an optical medium (for example, DVD) or a semiconductor medium. The semiconductor medium can be a solid state disk.

[0190] Those skilled in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed in the present application can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0191] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system, device and unit described above can refer to the corresponding process in the foregoing method embodiment, and will not be repeated here.

[0192] In several embodiments provided by the present application, it should be understood that the disclosed system, device and method can be implemented by other ways. For example, the device embodiments described above are merely schematic, for example, the division of units is only one, and actual implementation can have another division way, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units or components shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0193] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0194] In addition, the functional units in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit.

[0195] In the description of the present application, the description of the terms "one embodiment", "example", "specific example" and the like means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are contained in at least one embodiment or example of the present application. In the present application, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

Claims

1. A dynamic energy management method for a central air conditioning system based on a large model, characterized in that, The method includes: S1: Integrates real-time indoor and outdoor environmental data and central air conditioning equipment status data, and outputs short-term load demand forecast curves through a time-series deep prediction model. S2: Collect temperature field data of building materials, calculate the equivalent heat capacity and equivalent thermal resistance of building materials through physical information neural network inversion, and quantify the thermal inertia parameters of building materials in real time. S3: Based on the real-time quantified thermal inertia parameters of building materials in S2, predict the temperature field change trend of the building structure in the next 3 hours, and evaluate the phase change delay time coefficient of building materials based on the predicted temperature field change trend. S4: Obtain the photovoltaic power generation prediction curve of the power grid system and the time-of-use electricity price signal of the power grid to determine the optimal charging and discharging time window for building materials; S4 includes the following steps: S41: Obtain the real-time thermal inertia index of building materials And according to the preset thermal inertia index threshold The thermal response capability level of building materials was analyzed and verified, based on the real-time thermal inertia index of the building materials. Greater than or equal to the thermal inertia index threshold If the building is determined to have strong thermal inertia, predictive energy storage control is adopted, and step S42 is continued. When the real-time thermal inertia index of building materials Less than the thermal inertia index threshold If the building's thermal inertia is weak, the standard predictive control strategy will continue to be used. S42: Preset threshold for the effective utilization rate of latent heat of phase change materials in building materials and phase transition delay time coefficient threshold ; S43: In step S1, the load demand forecast curve is used to extract the load forecast curve for the next 3 hours, and the peak load period and valley load period are extracted to form the peak load set and the low load set respectively, and the peak period of photovoltaic power generation and the peak period of grid electricity price are identified. S44: Screening peak load clusters with latent heat utilization rates lower than Or the delay time is higher than The number of time periods obtained by filtering is ; S45: Based on the thermal inertia parameters of building materials and the number of time periods obtained through screening... The optimal charging and discharging time window for building materials is calculated as follows: ； in, These refer to the optimal charging time and optimal releasing time for building materials. These represent the start times of the low and high electricity prices, respectively. The difference between the set indoor temperature and the maximum allowable operating temperature of the building structure; This represents the temperature difference between the inside and outside of the building at the current moment. The thermal inertia time constant of building materials is taken as the equivalent heat capacity output in step S23. With equivalent thermal resistance The product; The time delay parameter is determined based on the material properties of building materials; S5: Based on S1-S4, use a multi-objective decision-making algorithm to generate the optimal operating strategy for the central air conditioning system.

2. The dynamic energy management method for a central air conditioning system based on a large model according to claim 1, characterized in that, In S1, the short-term load demand forecast curve is a refined load demand forecast curve for the next few hours. The strategy for obtaining the short-term load demand forecast curve includes: S11: Based on real-time indoor and outdoor environmental data and central air conditioning equipment status data, an attention mechanism is used to perform feature weighted fusion and dynamically correct the short-term load forecast results. S12: A multi-scale convolutional neural network is used to extract periodic patterns, trend components, and abnormal fluctuation features from historical load sequences, and the load forecast values ​​for the next 6 hours are updated on a rolling basis at 1-hour intervals to obtain a short-term load demand forecast curve. .

3. The dynamic energy management method for a central air conditioning system based on a large model according to claim 2, characterized in that, S2 includes the following steps: S21: Collect temperature sensor data from the four facades (east, south, west, and north) and the interior of the roof, as well as the corresponding solar radiation intensity data from the exterior surface, to form a multidimensional thermal state sequence. Standardize the data based on the differences in solar radiation received by different facades. S22: Input the above multidimensional thermal state sequence into a physical information neural network. The physical information neural network uses the unsteady-state heat conduction equation as a physical constraint to construct a loss function. Through the loss function Optimize the phase change material properties of building materials; S23: By minimizing the loss function The equivalent thermal inertia parameters of building materials are obtained through inversion, and the equivalent thermal inertia parameters include: equivalent heat capacity. With equivalent thermal resistance ; S24: Extract the equivalent thermal inertia parameter output in step S23, and use the equivalent heat capacity. Divide by equivalent thermal resistance Obtain the real-time thermal inertia index of building materials ; S25: Real-time monitoring of the phase transition state of building materials and calculation of the degree of phase transition of building materials. ; Based on the degree of phase change of building materials Calculate the latent heat absorption and desorption rate .

4. The dynamic energy management method for a central air conditioning system based on a large model according to claim 3, characterized in that, S3 include: S31: Based on the equivalent thermal inertia parameter, the building structure is simplified into a thermal network model composed of thermal resistance and thermal capacity nodes. According to the law of conservation of energy, the differential equation of the discrete-time state space of the thermal network model is established and solved by the Euler algorithm to predict the temperature field change trend of the building structure in the next 3 hours. S32: Based on the predicted temperature field change trend, evaluate the phase change delay time coefficient of building materials. .

5. The dynamic energy management method for a central air conditioning system based on a large model according to claim 4, characterized in that, S5 include: S51: Based on S41-S45, calculate the control parameters of the central air conditioning system to be updated. The specific adjustment strategy for the control parameters is as follows: ； Where k is the number of iterations for optimizing the control parameters; Let be the overall energy efficiency ratio of the central air conditioning system in the kth iteration; This will be the new target value for the overall energy efficiency ratio of the central air conditioning system in the next iteration. Z represents the total number of time periods; This is a preset threshold for the number of time periods; The weighting coefficient for the influence of the thermal properties of building materials; S52: Extracts and stores the optimized and updated comprehensive energy efficiency ratio target value of the central air conditioning system to the cloud database, and simultaneously sends it to the local controllers of the central air conditioning chiller, variable frequency water pump and cooling tower through the industrial communication protocol.

6. The dynamic energy management method for a central air conditioning system based on a large model according to claim 5, characterized in that, S5 also includes: S53: Extract the power generation data during peak photovoltaic power generation periods to form a photovoltaic output set, and simultaneously extract the air conditioning cooling load data during the same period to form an air conditioning load set, and distinguish between base load and adjustable load; S54: Employ an energy management strategy based on the thermal inertia of building materials, specifically including: assessing the target cooling capacity of building materials. Real-time monitoring of the cumulative cold storage capacity of building materials; When the cumulative cold storage capacity is lower than the target cold storage capacity During peak photovoltaic power generation periods, the operating power of the central air conditioning system is increased to store excess cooling capacity in high-heat-inert building materials. When the cumulative cold storage capacity is equal to or higher than the target cold storage capacity When the building materials have completed their cold storage, the central air conditioning system will be adjusted to its normal operating power. Among them, the target cold storage capacity The calculation strategy is as follows: ； in, Let be the photovoltaic power generation at time t; Let be the base load power at time t; The latent heat absorbed or released during the phase change process of building materials; S55: The degree of mismatch is evaluated from three different dimensions: photovoltaic output, air conditioning load, and heat capacity. This yields photovoltaic evaluation items, air conditioning load evaluation items, and heat capacity matching items. The photovoltaic-air conditioning load matching degree is then evaluated simultaneously from these three dimensions. .

7. The dynamic energy management method for a central air conditioning system based on a large model according to claim 6, characterized in that, S5 also includes: S56: Extracting the photovoltaic-air conditioning load matching degree To determine the switching of the central air conditioning operating mode, including: Preset matching threshold And based on the matching degree, a coordination level analysis is performed. When the photovoltaic-air conditioning load matching degree is... Greater than or equal to At that time, the collaborative control execution mode is triggered; When the photovoltaic-air conditioning load matching degree Less than At this time, the coordinated control execution unit is not triggered, and the backup power grid supply strategy is started; The coordinated control execution mode includes: increasing the operating power of the air conditioning system during peak photovoltaic output periods, storing excess cooling capacity in the building structure, and releasing the stored cooling capacity during peak electricity price periods.

8. A dynamic energy management system for a central air conditioning system based on a large model, used to implement the dynamic energy management method for a central air conditioning system based on a large model as described in any one of claims 1-7, characterized in that, The system includes: Load forecasting module, thermal inertia quantification module, phase change quantification module, dynamic energy storage control module, and air conditioning operation optimization module; The load forecasting module is used to integrate real-time indoor and outdoor environmental data and central air conditioning equipment status data, and output short-term load demand forecast curves through a time-series deep forecasting model. The thermal inertia quantification module is used to collect temperature field data of building materials, calculate the equivalent heat capacity and equivalent thermal resistance of building materials through physical information neural network inversion, and quantify the thermal inertia parameters of building materials in real time. The phase change module is used to predict the temperature field change trend of the building structure in the next 3 hours, and to evaluate the phase change delay time coefficient of the building materials based on the predicted temperature field change trend. The dynamic energy storage control module is used to acquire the photovoltaic power generation prediction curve of the power grid system and the time-of-use electricity price signal of the power grid, and to determine the optimal charging and discharging time window for building materials. The air conditioning operation optimization module uses a multi-objective decision-making algorithm to generate the optimal operation strategy for the central air conditioning system.

Images