Non-user air conditioner regulation and control modeling method considering power grid interaction and user comfort

Abstract

The invention discloses a non-user air conditioner regulation and control modeling method considering power grid interaction and user comfort, and relates to the field of air conditioner regulation and control, and the method comprises the steps: obtaining indoor and outdoor state data of an air conditioner through a monitoring sensor, carrying out the preprocessing of the state data, and constructing an air conditioner power prediction model in combination with a neural network technology; obtaining an air conditioner load demand based on the air conditioner power prediction model, and combining the air conditioner load demand with the power grid demand response signal to design a demand response mechanism; and based on the demand response mechanism, an optimal control strategy model with the user comfort level as the target is established, a simulated annealing algorithm is adopted for conducting partition solving on the optimal control strategy model, and an air conditioner regulation and control result is determined according to the solving result. According to the invention, through real-time data analysis and a prediction model, system operation parameters are dynamically adjusted, so that energy efficiency maximization and cost minimization are realized, and adaptability and response capability of the system to power grid demand changes are enhanced.

Description

Technical Field

[0001] The present invention relates to the field of air conditioning control, and in particular to a non-industrial user air conditioning control modeling method taking into account power grid interaction and user comfort. Background Art

[0002] With the continuous growth of energy demand and increasingly severe environmental problems, building energy consumption optimization has become an important area of ​​energy conservation and emission reduction. As the main component of building energy consumption, air-conditioning system accounts for a considerable proportion of the total building energy consumption. Traditional air-conditioning control strategies often adopt fixed temperature settings and simple start-stop control, lacking dynamic response to changes in indoor and outdoor environments and user needs, resulting in energy waste and low operating efficiency.

[0003] At the same time, in the existing technology, the control of the air-conditioning system mainly relies on preset control logic and manual adjustment by the user. These methods often cannot respond to changes in the indoor and outdoor environment and the actual needs of the user in a timely manner. For example, when the outdoor temperature changes, the fixed temperature setting may not guarantee indoor comfort, and it will also cause unnecessary energy waste.

[0004] For example, Chinese patent CN202410993166.1 discloses an operation management method and system for an efficient and energy-saving air-conditioning room. The method utilizes the collection of historical and real-time data, but does not take into account the demand response of the power grid when it is applied. It is impossible to reduce the pressure on the power grid by adjusting the operation mode during peak power grid load periods. Therefore, the existing intelligent control strategy still has some limitations, involving insufficient analysis and utilization of big data, insufficient consideration of user behavior and comfort, and incomplete coordination mechanism with power grid demand response.

[0005] Currently, no effective solution has been proposed for the problems in the related technologies. Summary of the invention

[0006] In view of the problems in the related art, the present invention proposes a non-industrial user air-conditioning control modeling method taking into account grid interaction and user comfort, so as to overcome the above-mentioned technical problems existing in the existing related art.

[0007] To this end, the specific technical solution adopted by the present invention is as follows:

[0008] A non-industrial user air conditioning control modeling method considering grid interaction and user comfort, the non-industrial user air conditioning control modeling method comprising:

[0009] The monitoring sensors are used to obtain the status data of air conditioners and indoor and outdoor environments. After preprocessing the status data, the air conditioner power prediction model is constructed in combination with neural network technology.

[0010] The air conditioning load demand is obtained based on the air conditioning power prediction model, and the air conditioning load demand is combined with the grid demand response signal to design a demand response mechanism;

[0011] Based on the demand response mechanism, an optimal control strategy model with user comfort as the target is established, and the simulated annealing algorithm is used to partition the optimal control strategy model, and the air conditioning control result is determined according to the solution result.

[0012] Preferably, using monitoring sensors to obtain status data of the air conditioner and indoor and outdoor environments, and after preprocessing the status data, building an air conditioner power prediction model in combination with neural network technology includes:

[0013] Use smart meters to monitor the air conditioning power during operation, and obtain the indoor and outdoor temperature and humidity of the air conditioning installation location based on temperature and humidity sensors to obtain the status data of the air conditioning and indoor and outdoor areas;

[0014] The data standardization processing technology is used to unify the time format and decimals of the status data, and the status data is divided into core points, boundary points and noise points based on the density clustering analysis technology;

[0015] Remove noise points, retain core points and boundary points, and use the data acquisition cycle to detect data missing of the state data after removing noise points;

[0016] The state data is interpolated based on the data missing situation, and the preprocessed state data is obtained according to the interpolation results. The air conditioning power prediction model is constructed in combination with neural network technology.

[0017] Preferably, interpolation processing is performed on the state data based on data missing conditions, preprocessed state data is obtained according to the interpolation processing result, and an air conditioning power prediction model is constructed in combination with a neural network technology, including:

[0018] Based on the data missing situation, the position and quantity of missing data are analyzed, and the state data of the missing position is filled by linear interpolation technology according to the analysis results to obtain the preprocessed state data;

[0019] The feature set with the greatest impact on air conditioning power is selected from the status data through statistical analysis and data mining technology, and the air conditioning power prediction model is constructed by combining the feature set with the radial basis neural network.

[0020] The filtered state data is used to train the air conditioning power prediction model, and the model parameters are adjusted to obtain the trained air conditioning power prediction model.

[0021] Preferably, obtaining the air conditioning load demand based on the air conditioning power prediction model, and combining the air conditioning load demand with the power grid demand response signal to design a demand response mechanism includes:

[0022] Based on the air conditioning power prediction model, the air conditioning power under temperature and humidity conditions is analyzed, and the air conditioning load demand in the future time period is analyzed according to the air conditioning power and energy efficiency ratio, and the load control system is used to obtain the interactive demand response of the power grid;

[0023] The air conditioning load demand is combined with the grid interactive demand response to generate the power change value corresponding to the change of air conditioning set temperature, wind speed and working mode, and the demand response mechanism is designed based on the power change value.

[0024] Preferably, an optimal control strategy model with user comfort as the goal is established based on the demand response mechanism, and the optimal control strategy model is partitioned and solved using a simulated annealing algorithm. The air conditioning control result is determined according to the solution result, including:

[0025] Based on the user's subjective thermal sensation, the user's comfort satisfaction with the air-conditioning working state under the demand response mechanism is analyzed, and the objective function is constructed according to the user's comfort satisfaction and the demand response benefit coefficient.

[0026] Use machine learning technology to select the model framework, define the demand response constraints and integrate them with the objective function to build an optimal control strategy model with user comfort as the goal;

[0027] The simulated annealing algorithm is used as an optimization technique to find a new solution to the objective function, and the Monte Carlo method is used to calculate the acceptance probability of the new solution. Based on the calculation results, the optimal solution is found to determine the air conditioning control result.

[0028] Preferably, analyzing the user's comfort satisfaction with the air-conditioning working state under the demand response mechanism based on the user's subjective thermal sensation, and constructing the objective function according to the user's comfort satisfaction and the demand response benefit coefficient includes:

[0029] Analyze the indoor relative humidity and air temperature under the demand response mechanism, analyze the air flow rate based on the air temperature, and calculate the user's subjective thermal sensation based on the human metabolic rate and human mechanical work;

[0030] Based on the user's subjective thermal sensation and satisfaction analysis formula, the user's comfort satisfaction with the air-conditioning working status under the demand response mechanism is obtained;

[0031] The demand response benefit coefficients under different types are analyzed based on the demand response time and the actual average response load, and the objective function is constructed according to the demand response benefit coefficient and the user comfort satisfaction.

[0032] Preferably, the calculation formula of the user's subjective thermal sensation is:

[0033]

[0034] Where PMV represents the user's subjective thermal sensation, e represents a natural constant, M represents the human metabolic rate, W represents the human mechanical work, and P a Indicates the water vapor pressure of the air around the human body, t a represents the air temperature, f cl It is the ratio of the actual surface area of ​​the human body after clothing to the naked surface area, t cl Indicates the outer surface temperature of the clothes, t r represents the radiation temperature, h c represents the convective heat transfer coefficient.

[0035] Preferably, analyzing the demand response benefit coefficients under different types based on the demand response time and the actual average response load, and constructing the objective function according to the demand response benefit coefficient and the user comfort satisfaction degree includes:

[0036] Analyze the demand response time and actual average response load based on the demand response mechanism, obtain the maximum allowable unit price of adjustable load according to the actual average response load, and calculate the demand response profit coefficient under different types;

[0037] The thermal comfort weight coefficient is calculated based on the capacity and actual number of people in the air-conditioning application area, and the objective function is constructed by combining the demand response benefit coefficient and the user comfort satisfaction. Different types of demand response benefit coefficients include peak shaving and valley filling demand response benefit coefficients and real-time demand response benefit coefficients.

[0038] Preferably, the calculation formula of the peak shaving and valley filling demand response benefit coefficient is:

[0039] S1 dr =R final T dr F dr ;

[0040] The calculation formula of the real-time demand response benefit coefficient is:

[0041] S2 dr =R final T dr F dr +K check R check F r ;

[0042] Where S1 dr represents the peak-shaving and valley-filling demand response benefit coefficient, S2 dr represents the real-time demand response benefit coefficient, R final represents the actual average response load, T dr represents the demand response time, F dr Indicates the maximum allowable unit price of adjustable load, K check represents the calibration factor, Rcheck represents the verification capacity, F r Denotes capacity subsidy.

[0043] Preferably, a simulated annealing algorithm is used as an optimization technique to find a new solution to the objective function, and the acceptance probability of the new solution is calculated in combination with Monte Carlo. Based on the calculation results, the optimal solution is found to determine the air conditioning control result, including:

[0044] Based on the objective function, dual optimization objectives including energy consumption and comfort are defined, and the weight of the optimization objectives is adjusted according to the number of people and environmental conditions in the air-conditioning application area;

[0045] After changing the initial parameters of the simulated annealing algorithm, the initial parameters of the air conditioner are set to obtain the initial solution. The simulated annealing algorithm is used to perturb the initial solution at each temperature, and the temperature setting and wind speed of the air conditioner are changed to obtain a new candidate solution.

[0046] Calculate the difference between the objective function value of the new candidate solution and the objective function value of the initial solution, and evaluate whether the new candidate solution is better than the initial solution based on the difference result;

[0047] Based on the evaluation results and Monte Carlo calculation, the acceptance probability of new candidate solutions is calculated, and the optimal solution is found according to the acceptance probability. The optimal solution is used to determine the number and operation mode of air conditioners in different areas to obtain the air conditioning control results.

[0048] The beneficial effects of the present invention are:

[0049] 1. The present invention dynamically adjusts system operating parameters through real-time data analysis and prediction models to maximize energy efficiency and minimize costs, and enhances the system's adaptability and responsiveness to changes in grid demand, thereby promoting the intelligent and green development of building energy systems.

[0050] 2. The present invention collects real-time operating data of the air-conditioning system through sensors and intelligent instruments, and analyzes and processes the data for training the air-conditioning power prediction model to predict future energy demand. At the same time, based on the prediction results and the demand response signal of the power grid, an adaptive demand response mechanism is formulated to dynamically adjust the operating mode of the air-conditioning system, and an optimization control algorithm is used to achieve system parameter optimization under the premise of meeting comfort and economic benefits, ensuring that the air-conditioning system can adapt to environmental changes and user needs and achieve long-term efficient and intelligent operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0052] Figure 1 The present invention is a flowchart of a non-industrial user air conditioning control modeling method considering grid interaction and user comfort according to an embodiment of the present invention. DETAILED DESCRIPTION

[0053] To further illustrate each embodiment, the present invention provides drawings, which are part of the disclosure of the present invention and are mainly used to illustrate the embodiments. They can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these contents, ordinary technicians in this field should be able to understand other possible implementation methods and advantages of the present invention.

[0054] According to an embodiment of the present invention, a non-industrial user air conditioning control modeling method is provided that takes into account grid interaction and user comfort.

[0055] The present invention is further described with reference to the accompanying drawings and specific embodiments. Figure 1 As shown, according to the non-industrial user air conditioning control modeling method considering grid interaction and user comfort according to an embodiment of the present invention, the non-industrial user air conditioning control modeling method includes:

[0056] Step S1, using monitoring sensors to obtain status data of the air conditioner and indoor and outdoor environments, and after preprocessing the status data, building an air conditioner power prediction model in combination with neural network technology;

[0057] Step S2: obtaining air conditioning load demand based on the air conditioning power prediction model, and combining the air conditioning load demand with the power grid demand response signal to design a demand response mechanism;

[0058] Step S3: Establish an optimal control strategy model with user comfort as the target based on the demand response mechanism, and use a simulated annealing algorithm to partition and solve the optimal control strategy model, and determine the air conditioning control result according to the solution result.

[0059] In this embodiment, when using monitoring sensors to obtain status data of the air conditioner and indoor and outdoor areas, and after preprocessing the status data, combining neural network technology to build an air conditioner power prediction model, the smart meter can be used to monitor the air conditioner power during the operation of the air conditioner, and the temperature and humidity indoors and outdoors of the air conditioner installation location can be obtained based on the temperature and humidity sensor to obtain the status data of the air conditioner and indoor and outdoor areas; the data standardization processing technology is used to unify the time format and decimals of the status data, and the status data is divided into core points, boundary points and noise points based on the density clustering analysis technology; the noise points are eliminated, the core points and boundary points are retained, and the data acquisition cycle is used to detect the data missing situation of the status data after the noise points are eliminated; the status data is interpolated based on the data missing situation, and the preprocessed status data is obtained according to the interpolation processing result, and the air conditioner power prediction model is built in combination with the neural network technology.

[0060] It should be explained that in the process of dividing the state data into core points, boundary points and noise points based on density clustering analysis technology, the local density of the state data can be obtained to obtain the density peak point as the cluster center, so as to realize the rapid division of the state data based on density, obtain state data of different densities, and perform clustering on this basis to realize the division of core points, boundary points and noise points. Specifically, the implementation steps are as follows:

[0061] Step 1: Input state data, calculate the distance matrix between any state data points, and calculate the local density of each state data point based on the distance matrix and the cutoff distance:

[0062]

[0063] In the formula, v i represents the local density of the i-th state data point, j represents the j-th state data point, and d ij represents the Euclidean distance between the i-th state data point and the j-th state data point, d c Represents the cutoff distance, and since the influence of the cutoff distance is small, the value of the cutoff distance is the adjacent average of each data point in the state data.

[0064] Step 2: Calculate the minimum distance and decision value of the state data point based on the local density of the state data point, and determine whether the difference in decision value is greater than its mean. If so, mark the corresponding state data point as the cluster center. The calculation formula for the minimum distance of the i-th state data is:

[0065]

[0066] Among them, there is an extreme case, that is, when the local density of state data i itself reaches the highest, the β of the point i The value is defined as:

[0067]

[0068] In the formula, D represents the state data set, v j Represents the local density of the j-th state data point.

[0069] The decision value α of the i-th state data point i The calculation formula is:

[0070] α i =υ i ×β i ;

[0071] Step 3: Arrange the remaining state data points in descending order according to their local density, and determine and divide them into the cluster centers closest to themselves in turn, generate density state data sets of different densities, and determine the parameter E corresponding to the density state data set psi (neighborhood radius) and Mi nPtsi (minimum points);

[0072] All state data points of the density state data set are marked as unvisited states. Select an unvisited state data point and determine whether the neighborhood of the state data point with the neighborhood radius as the radius contains the state data points with the minimum number of points. If so, mark it as a core point to establish a new cluster C, and add all the minimum points in the neighborhood to the new cluster C, otherwise mark it as a noise point.

[0073] Step 4: Calculate whether the state data points that have not been visited in the new cluster C contain at least the minimum number of state data points in their neighborhood. If so, add the state data points in the neighborhood that are not included in any cluster to cluster F and mark them as boundary points.

[0074] Repeat step 4 to continue the unvisited state data points in the new cluster C until no new state data points are added to cluster F. Repeat steps 3 to 4 until all state data points are added to a cluster or marked as noise points. Merge different densities and output the clustering results of the density-state data set.

[0075] In this embodiment, when the status data is interpolated based on the data missing situation, the pre-processed status data is obtained according to the interpolation processing result, and the air-conditioning power prediction model is constructed in combination with the neural network technology, the position and quantity of the missing data can be analyzed based on the data missing situation, and the status data at the missing position can be filled with the linear interpolation technology according to the analysis result to obtain the pre-processed status data; the feature set with the greatest impact on the air-conditioning power is screened out from the status data through statistical analysis and data mining technology, and the air-conditioning power prediction model is constructed by combining the feature set with the radial basis neural network; the air-conditioning power prediction model is trained using the screened status data, and the model parameters are adjusted to obtain the trained air-conditioning power prediction model.

[0076] It needs to be explained that, when analyzing the position and quantity of missing data based on the data missing situation and using linear interpolation technology to fill the status data of the missing positions according to the analysis results, we can first establish a star-shaped and snowflake-shaped spatial multidimensional database structure to clarify the distribution characteristics of the status data, and then perform parameter initialization operations to achieve consistent data dimension division to improve data quality, and then use basis functions to establish Lagrange interpolation polynomials, introduce normalization ideas, ensure that values ​​float within a certain range, avoid the Runge phenomenon, and generate new interpolation polynomials. The calculation result of the interpolation polynomials is the status data that fills the missing positions.

[0077] In the process of establishing the spatial multidimensional database structure, the state data topology structure is first analyzed, which helps to grasp the distribution characteristics and storage methods of the state data and facilitates interpolation processing. The topology structure of the state data can be described by a star:

[0078] ∑e(a)=e(1)e(2)…e(n);

[0079] If the data dimension is very large and the distribution is complex, the above star schema cannot meet the state data processing requirements and will affect data interpolation analysis. Assuming there are 4 dimension tables, in this case, the snowflake database model can be used:

[0080]

[0081] In the formula, ∑e(a) represents the set of state data dimension tables, e(a) represents a dimension tables, and n represents the total number of dimension tables.

[0082] When the basis function is used to establish the Lagrange interpolation polynomial, the essence of the Lagrange algorithm is to calculate a polynomial through multiple iterations, which can get the interpolation value at the calibration point. The specific process of interpolation is:

[0083] For example, the state data contains k+1 state data points (X0, Y0)…(X k , Y k), if the two random state data are different, the Lagrange interpolation polynomial is:

[0084]

[0085] In the formula, S j (X) represents an odd function, Y j represents the data position corresponding to the jth state data point, and j∈[0, k], as follows:

[0086]

[0087] Based on the Lagrange interpolation polynomial, the weight normalization idea is introduced to map the state data points to a fixed interval. The normalization idea is used to improve the basis function value to ensure that it is in the interval (0, 1), reduce the numerical instability of the polynomial, and ensure that the calibration accuracy is within the ideal range. The new Lagrange interpolation polynomial after normalization is as follows:

[0088]

[0089] Where, T j (X) represents the new basis function, y j represents the normalized state data, and the calculation result of the new Lagrange interpolation polynomial after normalization is the state data filling the missing position.

[0090] In this embodiment, when obtaining the air-conditioning load demand based on the air-conditioning power prediction model and combining the air-conditioning load demand with the power grid demand response signal to design a demand response mechanism, the air-conditioning power under temperature and humidity conditions can be analyzed based on the air-conditioning power prediction model, and the air-conditioning load demand in the future time period can be analyzed based on the air-conditioning power and energy efficiency ratio, and the load control system is used to obtain the power grid interactive demand response; the air-conditioning load demand and the power grid interactive demand response are combined to generate power change values ​​corresponding to changes in the air-conditioning set temperature, wind speed and working mode, and a demand response mechanism is designed based on the power change values.

[0091] In this embodiment, an optimal control strategy model with user comfort as the target is established based on the demand response mechanism, and the simulated annealing algorithm is used to partition and solve the optimal control strategy model. When the air-conditioning control result is determined according to the solution result, the user's comfort satisfaction with the air-conditioning working state under the demand response mechanism can be analyzed based on the user's subjective thermal sensation, and the objective function is constructed according to the user's comfort satisfaction and the demand response benefit coefficient; the model framework is selected by using machine learning technology, and the demand response constraint conditions are defined and integrated with the objective function to construct the optimal control strategy model with user comfort as the target; the simulated annealing algorithm is used as an optimization technology to find a new solution to the objective function, and the acceptance probability of the new solution is calculated in combination with Monte Carlo, and the optimal solution is found based on the calculation results to determine the air-conditioning control result.

[0092] In this embodiment, when analyzing the user's comfort satisfaction with the air-conditioning working state under the demand response mechanism based on the user's subjective thermal sensation, and constructing the objective function according to the user's comfort satisfaction and the demand response benefit coefficient, the indoor relative temperature and air temperature under the demand response mechanism can be analyzed, the air flow velocity can be analyzed according to the air temperature, and the user's subjective thermal sensation can be calculated in combination with the human metabolic rate and the human mechanical work; the user's comfort satisfaction with the air-conditioning working state under the demand response mechanism can be obtained based on the user's subjective thermal sensation and satisfaction analysis formula; the demand response benefit coefficient under different types can be analyzed based on the demand response time and the actual average response load, and the objective function can be constructed according to the demand response benefit coefficient and the user's comfort satisfaction.

[0093] In this embodiment, when analyzing the demand response benefit coefficients under different types based on the demand response time and the actual average response load, and constructing the objective function according to the demand response benefit coefficient and the user comfort satisfaction, the demand response time and the actual average response load can be analyzed based on the demand response mechanism, the maximum allowable unit price of the adjustable load is obtained according to the actual average response load, and the demand response benefit coefficients under different types are calculated; the thermal comfort weight coefficient is calculated according to the capacity and actual number of people in the air-conditioning application area, and the objective function is constructed in combination with the demand response benefit coefficient and the user comfort satisfaction. The demand response benefit coefficients under different types include the peak shaving and valley filling demand response benefit coefficient and the real-time demand response benefit coefficient.

[0094] In this embodiment, when a simulated annealing algorithm is used as an optimization technique to find a new solution to the objective function, and the acceptance probability of the new solution is calculated in combination with Monte Carlo, and the optimal solution is found based on the calculation results to determine the air conditioning control result, a dual optimization goal including energy consumption and comfort can be defined based on the objective function, and the weight of the optimization goal can be adjusted according to the number of people and the environmental conditions in the air conditioning application area; after changing the initial parameters of the simulated annealing algorithm, the initial parameters of the air conditioner are set to obtain an initial solution, the initial solution is perturbed by the simulated annealing algorithm at each temperature, and the temperature setting and wind speed of the air conditioner are changed to obtain a new candidate solution; the difference between the objective function value of the new candidate solution and the objective function value of the initial solution is calculated, and whether the new candidate solution is better than the initial solution is evaluated based on the difference result; the acceptance probability of the new candidate solution is calculated based on the evaluation result and Monte Carlo, and the optimal solution is found based on the acceptance probability, and the optimal solution is used to determine the number and operation mode of air conditioners in different areas to obtain the air conditioning control result.

[0095] In order to facilitate understanding of the above technical solutions of the present invention, the operation mode of the present invention in the actual process is described in detail below.

[0096] Step 1: Air conditioning data collection and preprocessing:

[0097] Install temperature and humidity sensors and smart meters in the air conditioning system to monitor key parameters such as indoor and outdoor temperature, humidity, and air conditioning power in real time to obtain status data. Collect the operating data of the air conditioning system through sensors to ensure the real-time and accuracy of the data. At the same time, standardize the status data, including unifying the time format, unifying the units of similar data, and retaining decimals.

[0098] At the same time, clustering is performed based on density, and data points are divided into core points, boundary points, and noise points. Noise points are usually considered to be outliers. These outliers are eliminated, and detection is performed according to the data collection cycle. After the missing values ​​are detected, the corresponding interpolation method is selected according to the data type to fill them until there are no outliers in the status data.

[0099] Step 2: Construction of air conditioning power prediction model:

[0100] Through statistical analysis and data mining methods, the features that have the greatest impact on air conditioning power are screened out from the status data, including indoor and outdoor temperature, humidity, etc. Based on the feature data set, an air conditioning power prediction model based on radial basis function (RBF) neural network is constructed. The model input is a feature vector, including set temperature, ambient temperature, wind speed, working mode, and usage time, and the output is air conditioning power. At the same time, the model is trained using historical data, and the parameters are adjusted to optimize the model performance. The trained model is used to predict the air conditioning power demand in the future time period based on temperature, humidity and time information.

[0101] The load control system obtains the grid demand response, and analyzes the air conditioning load demand in the future time period based on the air conditioning power demand and energy efficiency ratio, obtains the power change value corresponding to the air conditioning set temperature change, wind speed change and working mode change, and sets the demand response mechanism in combination with the human presence sensor information and the power change value brought by different air conditioning control methods, and completes the demand response in different areas and steps:

[0102] First, shut down all air conditioners in unmanned areas to meet part of the demand response power, and allocate the remaining required control power to air conditioners in other areas. According to the optimization strategy formulated later, the number of air conditioners that need to be regulated and the control method are statistically obtained. Before or after the demand response, the user can define or modify the control rules and weights. When executing the next demand response, the constraints will be added or modified accordingly to meet user needs.

[0103] Step 3: Use machine learning to develop an optimization strategy to optimize the operating parameters of the air conditioning system while meeting the requirements of comfort and economic benefits:

[0104] (1) PDD calculation:

[0105] The calculation formula of the user's subjective thermal sensation is:

[0106]

[0107] The water vapor pressure of the air around the human body is calculated as:

[0108]

[0109] The formula for calculating the ratio of the actual surface area of ​​the human body after clothing to the naked body surface area is:

[0110]

[0111] The calculation formula for the outer surface temperature of clothing is:

[0112]

[0113] The expression of convective heat transfer coefficient is:

[0114]

[0115] Where PMV represents the user's subjective thermal sensation, e represents a natural constant, M represents the human metabolic rate, W represents the human mechanical work, and P a Indicates the water vapor pressure of the air around the human body, t a represents the air temperature, f cl It is the ratio of the actual surface area of ​​the human body after clothing to the naked surface area, t cl Indicates the outer surface temperature of the clothes, t rrepresents the radiation temperature, h c represents the convective heat transfer coefficient, I cl represents clothing thermal resistance, and φ represents indoor relative humidity.

[0116] PPD (Predicted Percentage of Dissatisfied) refers to the predicted percentage of dissatisfaction, which is predicted based on the PMV value. It indicates the percentage of people who are expected to be dissatisfied in a specific environment. The calculation formula is as follows:

[0117] PDD=100-95exp[(0.03353PMV 4 +0.2179PMV 2 )];

[0118] The relationship between PMV and PPD can be described as a bell curve relationship, that is, the closer the PMV value is to 0 (neither cold nor hot), the lower the PPD value is, indicating that most people feel comfortable; and the further the PMV value deviates from 0 (either positive or negative), the higher the PPD value is, indicating that the percentage of people who feel dissatisfied increases.

[0119] (2) Objective function:

[0120]

[0121] In the formula, λ i Represents the thermal comfort weight coefficient, and adjusts the thermal comfort weights of different areas according to the number of people in each area; n i Indicates the actual number of people in the area; N i Indicates the maximum number of people that the area can accommodate; S dr It represents the revenue of demand response. The revenue of different types of demand response (peak shaving and valley filling demand response revenue and real-time demand response revenue) is different, specifically:

[0122] The calculation formula of the peak-shaving and valley-filling demand response benefit coefficient is:

[0123] S1 dr =R final T dr F dr ;

[0124] The calculation formula of the real-time demand response benefit coefficient is:

[0125] S2 dr =R final T dr F dr +K check R check F r ;

[0126] Where S1dr represents the peak-shaving and valley-filling demand response benefit coefficient, S2 dr represents the real-time demand response benefit coefficient, R final represents the actual average response load, T dr represents the demand response time, F dr Indicates the maximum allowable unit price of adjustable load, K check represents the calibration factor, R check represents the verification capacity, F r Denotes capacity subsidy.

[0127] (3) Demand response constraints:

[0128] Demand response constraints include peak shaving demand response, valley filling demand response and real-time demand response, among which peak shaving demand response is:

[0129]

[0130] The valley filling demand response is:

[0131]

[0132] Real-time demand response is:

[0133]

[0134] In the formula, Indicates the maximum load during the response period, represents the baseline maximum load, represents the baseline average load, represents the average load during the response period, R resp Indicates the response capability confirmation value, represents the minimum load during the response period, Indicates the baseline minimum load.

[0135] During the demand response process, the power grid considers the park as a whole, and the baseline average load and the average load during the response period should be based on the grid interaction power P t grid Calculation, the calculation method is as follows:

[0136]

[0137] Where P t grid,base It represents the typical daily load, and its calculation method is shown in Table 1 below:

[0138] Table 1 Typical daily load calculation

[0139]

[0140]

[0141] (4) Simulated annealing algorithm solution:

[0142] The simulated annealing algorithm is used to solve the above optimal control strategy in different regions. The specific implementation steps are as follows:

[0143] 1. Set the initial parameters of the simulated annealing algorithm, including the initial temperature (T), cooling rate, final temperature, etc. In the air-conditioning system parameter optimization, the objective function is a double-layer optimization goal of energy consumption and comfort, and the weights of the two optimization goals are dynamically adjusted according to the number of people and environmental conditions in different areas.

[0144] 2. At the beginning of the algorithm, an initial solution is set, that is, the initial parameter setting of the air conditioning system. At each temperature, a new candidate solution is generated by perturbing the current solution. This perturbation mainly changes the temperature setting, wind speed and other parameters of the air conditioner. For each newly generated candidate solution, the difference between its objective function value and the objective function value of the current solution is calculated to evaluate whether the new solution is better than the current solution. According to the Metropolis (Monte Carlo) criterion, the calculation formula for the probability of accepting a new solution is as follows:

[0145]

[0146] In the formula, P represents the probability of accepting a new solution, E new represents the objective function value of the new solution, E old Represents the objective function value of the current solution, T represents the current temperature. If the objective function value of the new solution is better than the current solution, the new solution is accepted. If the objective function value of the new solution is worse, there is still a certain probability of accepting the new solution. This probability gradually decreases as the temperature decreases. If the new solution is accepted, it will become the new current solution, otherwise the current solution remains unchanged.

[0147] (3) After each iteration, the temperature is lowered at a predetermined cooling rate. As the temperature decreases, the probability of accepting a poor solution gradually decreases, and the algorithm gradually converges to the optimal solution. When the temperature drops to the termination temperature or reaches the preset termination conditions, including the number of iterations and the improvement of the objective function value is less than the minimum threshold, the algorithm stops. Finally, the algorithm outputs the optimal solution found in the search process, that is, the number and operation mode of air conditioners in different areas, so as to achieve the goal of optimal overall comfort when participating in grid demand response.

[0148] In summary, with the help of the above technical solutions of the present invention, the present invention dynamically adjusts the system operating parameters through real-time data analysis and prediction models to maximize energy efficiency and minimize costs, and enhances the system's adaptability and responsiveness to changes in grid demand, thereby promoting the intelligent and green development of building energy systems. The present invention collects real-time operating data of the air-conditioning system through sensors and intelligent instruments, and analyzes and processes the data to train the air-conditioning power prediction model to predict future energy demand. At the same time, based on the prediction results and the demand response signal of the grid, an adaptive demand response mechanism is formulated to dynamically adjust the operating mode of the air-conditioning system, and an optimization control algorithm is used to achieve system parameter optimization under the premise of satisfying comfort and economic benefits, ensuring that the air-conditioning system can adapt to environmental changes and user needs, and achieve long-term efficient and intelligent operation.

[0149] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A non-industrial user air conditioning control modeling method considering grid interaction and user comfort, characterized in that: The non-industrial user air conditioning control modeling method includes: The monitoring sensors are used to obtain the status data of air conditioners and indoor and outdoor environments. After preprocessing the status data, the air conditioner power prediction model is constructed in combination with neural network technology. The air conditioning load demand is obtained based on the air conditioning power prediction model, and the air conditioning load demand is combined with the grid demand response signal to design a demand response mechanism; Based on the demand response mechanism, an optimal control strategy model with user comfort as the target is established, and the simulated annealing algorithm is used to partition the optimal control strategy model, and the air conditioning control result is determined according to the solution result.

2. A non-industrial user air conditioning control modeling method considering grid interaction and user comfort according to claim 1, characterized in that: The method of using monitoring sensors to obtain status data of the air conditioner and indoor and outdoor areas, and after preprocessing the status data, combining neural network technology to construct an air conditioner power prediction model includes: Use smart meters to monitor the air conditioning power during operation, and obtain the indoor and outdoor temperature and humidity of the air conditioning installation location based on temperature and humidity sensors to obtain the status data of the air conditioning and indoor and outdoor areas; The data standardization processing technology is used to unify the time format and decimals of the status data, and the status data is divided into core points, boundary points and noise points based on the density clustering analysis technology; Remove noise points, retain core points and boundary points, and use the data acquisition cycle to detect data missing of the state data after removing noise points; The state data is interpolated based on the data missing situation, and the preprocessed state data is obtained according to the interpolation results. The air conditioning power prediction model is constructed in combination with neural network technology.

3. A non-industrial user air conditioning control modeling method considering grid interaction and user comfort according to claim 2, characterized in that: The interpolation processing of the state data based on the data missing situation, obtaining the pre-processed state data according to the interpolation processing result, and constructing the air conditioning power prediction model in combination with the neural network technology include: Based on the data missing situation, the position and quantity of missing data are analyzed, and the state data of the missing position is filled by linear interpolation technology according to the analysis results to obtain the preprocessed state data; The feature set with the greatest impact on air conditioning power is selected from the status data through statistical analysis and data mining technology, and the air conditioning power prediction model is constructed by combining the feature set with the radial basis neural network. The filtered state data is used to train the air conditioning power prediction model, and the model parameters are adjusted to obtain the trained air conditioning power prediction model.

4. A non-industrial user air conditioning control modeling method considering grid interaction and user comfort according to claim 3, characterized in that: The method of obtaining the air conditioning load demand based on the air conditioning power prediction model and combining the air conditioning load demand with the power grid demand response signal to design a demand response mechanism includes: Based on the air conditioning power prediction model, the air conditioning power under temperature and humidity conditions is analyzed, and the air conditioning load demand in the future time period is analyzed according to the air conditioning power and energy efficiency ratio, and the load control system is used to obtain the interactive demand response of the power grid; The air conditioning load demand is combined with the grid interactive demand response to generate the power change value corresponding to the change of air conditioning set temperature, wind speed and working mode, and the demand response mechanism is designed based on the power change value.

5. The non-industrial user air conditioning control modeling method considering grid interaction and user comfort according to claim 1 is characterized in that: The optimal control strategy model based on the demand response mechanism is established with user comfort as the target, and the optimal control strategy model is partitioned and solved by using a simulated annealing algorithm. The air conditioning control result is determined according to the solution result, including: Based on the user's subjective thermal sensation, the user's comfort satisfaction with the air-conditioning working state under the demand response mechanism is analyzed, and the objective function is constructed according to the user's comfort satisfaction and the demand response benefit coefficient. Use machine learning technology to select the model framework, define the demand response constraints and integrate them with the objective function to build an optimal control strategy model with user comfort as the goal; The simulated annealing algorithm is used as an optimization technique to find a new solution to the objective function, and the Monte Carlo method is used to calculate the acceptance probability of the new solution. Based on the calculation results, the optimal solution is found to determine the air conditioning control result.

6. A non-industrial user air conditioning control modeling method considering grid interaction and user comfort according to claim 5, characterized in that: The objective function is constructed based on the user's subjective thermal sensation analysis of the user's comfort satisfaction with the air-conditioning working state under the demand response mechanism and the user's comfort satisfaction and the demand response benefit coefficient, including: Analyze the indoor relative humidity and air temperature under the demand response mechanism, analyze the air flow rate based on the air temperature, and calculate the user's subjective thermal sensation based on the human metabolic rate and human mechanical work; Based on the user's subjective thermal sensation and satisfaction analysis formula, the user's comfort satisfaction with the air-conditioning working status under the demand response mechanism is obtained; The demand response benefit coefficients under different types are analyzed based on the demand response time and the actual average response load, and the objective function is constructed according to the demand response benefit coefficient and the user comfort satisfaction.

7. A non-industrial user air conditioning control modeling method considering grid interaction and user comfort according to claim 6, characterized in that: The calculation formula of the user's subjective thermal sensation is: Where PMV represents the user's subjective thermal sensation, e represents a natural constant, M represents the human metabolic rate, W represents the human mechanical work, and P a Indicates the water vapor pressure of the air around the human body, t a represents the air temperature, f cl It is the ratio of the actual surface area of ​​the human body after clothing to the naked surface area, t cl Indicates the outer surface temperature of the clothes, t r represents the radiation temperature, h c represents the convective heat transfer coefficient.

8. A non-industrial user air conditioning control modeling method considering grid interaction and user comfort according to claim 7, characterized in that: The analysis of the demand response benefit coefficients under different types based on the demand response time and the actual average response load, and the construction of the objective function according to the demand response benefit coefficient and the user comfort satisfaction degree include: Analyze the demand response time and actual average response load based on the demand response mechanism, obtain the maximum allowable unit price of adjustable load according to the actual average response load, and calculate the demand response profit coefficient under different types; The thermal comfort weight coefficient is calculated according to the number of people that can be accommodated and the actual number of people in the air-conditioning application area, and the objective function is constructed by combining the demand response benefit coefficient and the user comfort satisfaction. The different types of demand response benefit coefficients include the peak shaving and valley filling demand response benefit coefficient and the real-time demand response benefit coefficient.

9. A non-industrial user air conditioning control modeling method considering grid interaction and user comfort according to claim 8, characterized in that: The calculation formula of the peak shaving and valley filling demand response benefit coefficient is: S1 dr =R final T dr F dr ; The calculation formula of the real-time demand response benefit coefficient is: S2 dr =R final T dr F dr +K check R check F r ; Where S1 dr represents the peak-shaving and valley-filling demand response benefit coefficient, S2 dr represents the real-time demand response benefit coefficient, R final represents the actual average response load, T dr represents the demand response time, F dr Indicates the maximum allowable unit price of adjustable load, K check represents the calibration factor, R check represents the verification capacity, F r Denotes capacity subsidy.

10. A non-industrial user air conditioning control modeling method considering grid interaction and user comfort according to claim 9, characterized in that: The method of using the simulated annealing algorithm as an optimization technique to find a new solution to the objective function, and combining the Monte Carlo method to calculate the acceptance probability of the new solution, and finding the optimal solution based on the calculation results to determine the air conditioning control result includes: Based on the objective function, dual optimization objectives including energy consumption and comfort are defined, and the weight of the optimization objectives is adjusted according to the number of people and environmental conditions in the air-conditioning application area; After changing the initial parameters of the simulated annealing algorithm, the initial parameters of the air conditioner are set to obtain the initial solution. The simulated annealing algorithm is used to perturb the initial solution at each temperature, and the temperature setting and wind speed of the air conditioner are changed to obtain a new candidate solution. Calculate the difference between the objective function value of the new candidate solution and the objective function value of the initial solution, and evaluate whether the new candidate solution is better than the initial solution based on the difference result; Based on the evaluation results and Monte Carlo calculation, the acceptance probability of new candidate solutions is calculated, and the optimal solution is found according to the acceptance probability. The optimal solution is used to determine the number and operation mode of air conditioners in different areas to obtain the air conditioning control results.

Images