Energy consumption optimization control method and system for heating and ventilation equipment

Abstract

The invention discloses an energy consumption optimization control method and system for heating and ventilation equipment, and the method comprises the steps: carrying out the comprehensive evaluation of the energy consumption condition of the heating and ventilation equipment, and recognizing the current energy consumption condition and energy-saving potential of the equipment; the system is connected with heating and ventilation equipment through the Internet of Things technology, and collects parameters of the heating and ventilation equipment in real time. Based on the preprocessed data, establishing energy consumption models of the water chilling unit, the cooling tower, the freezing pump and the cooling pump; building an energy consumption prediction regression model by adopting a decision tree algorithm, and predicting the total energy consumption of the heating and ventilation system in real time; according to the predicted energy consumption data, an optimization control strategy of the heating and ventilation equipment is formulated in combination with a set energy consumption control objective function; and applying the formulated optimization control strategy to the heating and ventilation equipment, carrying out real-time monitoring and feedback, and carrying out iterative optimization on the control strategy according to an actual effect. According to the method, comprehensive evaluation, real-time monitoring and optimal control of the energy consumption of the heating and ventilation equipment can be realized, and a powerful guarantee is provided for energy conservation and emission reduction of a building.

Description

Technical Field

[0001] The present invention relates to the technical field of energy consumption management, and in particular to an energy consumption optimization control method and system for heating and ventilation equipment. Background Art

[0002] Traditional energy consumption management methods have obvious limitations in the field of HVAC equipment. These methods are often based on empirical judgment or simple rule control, lacking accurate data analysis and scientific prediction models. Therefore, it is difficult for traditional methods to achieve accurate prediction and optimization control of HVAC equipment energy consumption, resulting in energy waste and low energy efficiency.

[0003] In order to solve the problems of traditional control methods, the Internet of Things technology has begun to be introduced into HVAC equipment management. Through sensors, the Internet of Things technology realizes real-time monitoring and data collection of HVAC equipment operating parameters, providing valuable information resources for energy consumption analysis and optimization control. However, relying solely on the Internet of Things technology for data collection is not enough to achieve a significant reduction in energy consumption. It is also necessary to combine advanced algorithms and models to conduct in-depth analysis and processing of the collected data in order to formulate an effective optimization control strategy.

[0004] In energy consumption management, prediction algorithms play a vital role. By analyzing historical data and real-time data, prediction algorithms can accurately predict the energy consumption trend of the HVAC system in the future. This prediction capability provides a scientific basis for optimized control, allowing control strategies to be adjusted in advance to avoid the occurrence of peak energy consumption periods. At the same time, prediction algorithms can also identify energy consumption anomalies and potential energy-saving points, providing strong support for energy-saving transformation and energy efficiency improvement.

[0005] As the problem of building energy consumption becomes increasingly prominent, the need for the development of energy-saving control algorithms is becoming increasingly urgent. Energy-saving control algorithms need to combine the operating characteristics of HVAC equipment and energy consumption models to develop optimized control strategies that meet actual needs. These strategies must not only be able to significantly reduce energy consumption, but also ensure the stable operation of equipment and the comfort of personnel.

[0006] Therefore, it is particularly important to develop an energy consumption optimization control method and system for HVAC equipment that can integrate Internet of Things technology, prediction algorithms and energy-saving control algorithms. Summary of the invention

[0007] The purpose of the present invention is to solve the problems of energy waste and low energy efficiency in the prior art and to propose an energy consumption optimization control method and system for HVAC equipment.

[0008] In order to achieve the above object, the present invention adopts the following technical solution: a method for optimizing the energy consumption of HVAC equipment, comprising the following steps: Step S1, comprehensively evaluate the energy consumption of HVAC equipment to identify the current energy consumption status and energy saving potential of the equipment; Step S2, connecting with HVAC equipment through Internet of Things technology to collect HVAC equipment parameters in real time; Step S3, establishing energy consumption models of the chiller, cooling tower, refrigeration pump and cooling pump based on the preprocessed data; Step S4, using a decision tree algorithm to build an energy consumption prediction regression model to predict the total energy consumption of the HVAC system in real time; Step S5, formulating an optimal control strategy for HVAC equipment based on the predicted energy consumption data and the set energy consumption control objective function; Step S6, applying the formulated optimization control strategy to the HVAC equipment, performing real-time monitoring and feedback, and iteratively optimizing the control strategy according to the actual effect.

[0009] Furthermore, in step S1, the following sub-steps are also included: S1-1, collecting historical energy consumption data of the equipment from the control system and energy management system of the HVAC equipment, wherein the historical energy consumption data includes equipment operation time, energy consumption and equipment parameters; S1-2, based on the collected data, analyze the energy consumption status of HVAC equipment, identify the energy consumption level of the equipment, peak energy consumption period and abnormal energy consumption points; S1-3, compare the current energy consumption level with the energy consumption level of the industry standard, evaluate the energy efficiency of the equipment, and identify the factors affecting energy consumption. The energy efficiency = (current energy consumption / industry standard energy consumption) * 100%. The factors include equipment aging, improper operation parameter settings, and changes in the external environment. S1-4, predict the energy consumption trend of the equipment under different operating conditions, and evaluate the energy saving potential of the equipment based on the predicted trend.

[0010] Furthermore, in step S2, the following sub-steps are also included: S2-1, clarify the parameters that need to be monitored for HVAC equipment, including outdoor temperature, humidity, cooling tower outlet water temperature, cooling load, and chiller status; S2-2, selecting an IoT sensor that matches the parameters to be collected, and installing the sensor on the corresponding equipment, wherein the IoT sensor includes a temperature sensor, a humidity sensor, a flow sensor, a pressure sensor, and a liquid level sensor; S2-3, preprocessing the received raw data to identify and remove noise, outliers and duplicate data in the data; S2-4, for missing values ​​in the data, the k-means filling method based on Mahalanobis distance is used to fill them. The specific formula is:

[0011] in, represents a data point with missing values, Indicates that after filling The value of the data point on the lth attribute, K represents the number of clusters of k-means clustering, represents the kth cluster center formed after k-means clustering, According to the Mahalanobis distance and The closest one, belonging to the cluster A set of n complete data points, Representing a collection The value of the jth data point on the lth attribute, Representing a collection The weight of the j-th data point in .

[0012] Furthermore, in step S3, the following sub-steps are also included: S3-1, based on the collected chiller operation data, the energy consumption model of the chiller is established using the regression analysis method. The specific formula is:

[0013] in, is the energy consumption of the chiller, is the cooling capacity, is the condensation temperature, is the evaporation temperature, is the unit efficiency, a and b are the coefficients obtained by fitting; S3-2, based on the collected cooling tower operation data, the energy consumption model of the cooling tower is established using the multivariate linear regression method. The specific formula is:

[0014] in, is the energy consumption of the cooling tower, is the load of the cooling tower, is the inlet water temperature, is the outlet water temperature, is the fan efficiency, c and d are the coefficients obtained by fitting; S3-3, based on the collected operating data of the refrigeration pump and the cooling pump, the energy consumption model of the refrigeration pump and the cooling pump is established using the power function regression method. The specific formula is:

[0015] in, is the energy consumption of the pump, is the flow rate, H is the head, is the pump efficiency, and e is the coefficient obtained by fitting.

[0016] Furthermore, in step S4, the following sub-steps are also included: S4-1, use the information entropy formula to calculate the information entropy of the training set. The specific formula is:

[0017] Among them, E is information entropy, D is the data set, which is divided into m categories. The i-th category subset, Yes Category The probability of S4-2, for each candidate attribute, calculate its information entropy after splitting, and calculate the information gain, select the attribute with the highest information gain as the splitting attribute of the current node, and construct the node of the decision tree. The specific formula is:

[0018]

[0019] Where G is the information gain rate, is the i-th attribute, yes The number of different subsets included, The dataset D is split into disjoint subsets, Is a subset Total content of the sample; S4-3, for each child node, divide the data set into subsets according to the selected splitting attribute, recursively select the optimal attribute and build a decision tree until the stopping condition is met, wherein the stopping condition includes that all samples belong to the same class, no more attributes can be selected, and the maximum depth of the tree is reached; and recursively build a decision tree; S4-4, using the post-pruning method to simplify the decision tree structure by calculating the weighted confidence of the nodes; S4-5, based on the decision tree model, the total energy consumption of the HVAC system is taken as the independent variable, a multivariate linear regression equation is constructed, and the least squares method is used to solve the regression coefficient. The specific formula is:

[0020]

[0021] in, is the factor of total energy consumption of HVAC system, Y is total energy consumption, is the regression coefficient, is the error term, M is the design matrix, and N is the response variable vector.

[0022] Furthermore, in step S5, the following sub-steps are also included: S5-1, according to the collected HVAC equipment parameters, set an energy consumption control objective function for the HVAC equipment. The specific formula is:

[0023] in, is the energy consumption weight coefficient, E is the energy consumption, and are the temperature and set temperature of the ith zone, and are the humidity of the jth area and the set humidity, and are the weight coefficients of temperature and humidity respectively; S5-2, calculate the energy consumption difference based on the predicted energy consumption and the set energy consumption target, and determine the adjustment coefficient based on the energy consumption difference, equipment operating status and environmental parameters. The specific formula is:

[0024]

[0025] in, is the energy consumption difference, is the predicted energy consumption, is the set energy consumption target, k is the adjustment coefficient, g is the adjustment coefficient calculation function, U is the equipment status, T is the temperature, and RH is the humidity; S5-3, formulate an optimization control strategy based on the energy consumption difference, the adjustment coefficient and the operating characteristics of the equipment. The optimization control strategy includes adjusting the operating parameters of the equipment, starting or shutting down some equipment, adjusting the equipment operating time, and adjusting the operating parameters of the equipment through the following formula:

[0026] in, is the new operating parameter, It is the original operating parameter.

[0027] Furthermore, in step S6, the following sub-steps are also included: S6-1, deploy the optimization control strategy to the control system of the HVAC equipment to monitor the operating status and energy consumption data of the HVAC equipment in real time; S6-2, based on real-time monitoring data and preset evaluation indicators, evaluate the effect of the optimization control strategy. The specific formula is:

[0028] Among them, H is the effect evaluation index, h is the effect evaluation function, is the actual energy consumption, is the energy consumption target set; S6-3, based on the evaluation results, iteratively optimize the control strategy, adjust the operating parameters of the equipment, start or shut down some equipment, and adjust the equipment operating time.

[0029] Furthermore, an energy consumption optimization control system for HVAC equipment includes: Data acquisition module, data preprocessing module, energy consumption model building module, energy consumption prediction module, optimization control strategy formulation module, monitoring and feedback module, data storage module; The data acquisition module is used to collect the operating parameters of the HVAC equipment in real time; The data preprocessing module is used to preprocess the collected data; The energy consumption model establishment module establishes an energy consumption model of the HVAC equipment based on the preprocessed data; The energy consumption prediction module is used to predict the total energy consumption of the HVAC system; The optimization control strategy formulation module is used to formulate and execute the optimization control strategy; The monitoring and feedback module is used to monitor the operating status of the HVAC equipment in real time and provide feedback; The data storage module is used to store collected data, pre-processed data, energy consumption models and information on optimized control strategies.

[0030] The beneficial effects brought about by the technical solution provided by the present invention include at least: The present invention conducts a comprehensive assessment of the energy consumption of HVAC equipment to identify the energy consumption status and energy-saving potential of the equipment; connects with the HVAC equipment through the Internet of Things technology to collect HVAC equipment parameters in real time; establishes energy consumption models of chillers, cooling towers, freezing pumps and cooling pumps based on preprocessed data; uses a decision tree algorithm to build an energy consumption prediction regression model to predict the total energy consumption of the HVAC system in real time; formulates an optimization control strategy for the HVAC equipment based on the predicted energy consumption data and the set energy consumption control objective function; applies the formulated optimization control strategy to the HVAC equipment for real-time monitoring and feedback, and iteratively optimizes the control strategy based on the actual effect.

[0031] The present invention integrates advanced prediction algorithms to achieve accurate prediction of the total energy consumption of the HVAC system, providing a scientific basis for optimized control.

[0032] The present invention dynamically adjusts the control strategy according to the prediction results, effectively reduces energy consumption and improves energy utilization efficiency.

[0033] The present invention continuously optimizes the control strategy through real-time monitoring and feedback mechanism to adapt to changes in different environments and operating conditions.

[0034] The present invention integrates Internet of Things technology and intelligent algorithms to achieve intelligent management and remote control of HVAC equipment and reduce manual intervention. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are 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.

[0036] Figure 1 A flow chart of a method provided by an embodiment of the present invention; Figure 2 A system module architecture diagram provided for an embodiment of the present invention. DETAILED DESCRIPTION

[0037] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the energy consumption optimization control method and system of a HVAC equipment proposed by the present invention, its specific implementation method, structure, features and effects are described in detail as follows in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures, or characteristics in one or more embodiments may be combined in any suitable form.

[0038] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0039] The following examples are for illustrative purposes only and are not intended to limit the scope of the present invention.

[0040] The specific scheme of the energy consumption optimization control method and system for HVAC equipment provided by the present invention is described in detail below with reference to the accompanying drawings.

[0041] Example See also Figure 1 , which shows a method flow chart of an energy consumption optimization control method and system for HVAC equipment provided by an embodiment of the present invention, the method comprising the following steps: Step S1: comprehensively evaluate the energy consumption of HVAC equipment to identify the current energy consumption status and energy saving potential of the equipment; Wherein step S1 also includes the following sub-steps: S1-1, collecting historical energy consumption data of the equipment from the control system and energy management system of the HVAC equipment, wherein the historical energy consumption data includes equipment operation time, energy consumption and equipment parameters; S1-2, based on the collected data, analyze the energy consumption status of HVAC equipment, identify the energy consumption level of the equipment, peak energy consumption period and abnormal energy consumption points; S1-3, compare the current energy consumption level with the energy consumption level of the industry standard, evaluate the energy efficiency of the equipment, and identify the factors affecting energy consumption. The energy efficiency = (current energy consumption / industry standard energy consumption) * 100%. The factors include equipment aging, improper operation parameter settings, and changes in the external environment. S1-4, predict the energy consumption trend of the equipment under different operating conditions, and evaluate the energy saving potential of the equipment based on the predicted trend.

[0042] It should be noted that the equipment's operating time includes total operating time: the total operating time of the equipment since it was put into use, which is used to evaluate the overall usage status of the equipment; operating time of each shift: the operating time of the equipment in different shifts (morning shift, mid-shift, and evening shift), which helps to understand the equipment's operating rules and scheduling; operating time under different working conditions: the operating time of the equipment under different working conditions (full load, partial load, and no-load), which helps to analyze the equipment's energy consumption performance under different load conditions.

[0043] Energy consumption includes electricity consumption and gas consumption. Electricity consumption refers to the electricity consumed by the equipment during operation, measured in kilowatt-hours (kWh), including the electricity consumption of the equipment itself and the electricity consumption of its related auxiliary equipment; gas consumption refers to the equipment that uses gas as energy, measured in cubic meters (m³) or standard cubic meters (Nm³).

[0044] Equipment parameters include temperature parameters: water inlet temperature, water outlet temperature, and indoor temperature, which reflect the heat exchange efficiency of the equipment and the comfort of the indoor environment; pressure parameters: system pressure and water pump head, which are used to evaluate the operating stability and safety of the equipment; flow parameters: cooling water flow and air flow, which reflect the heat transfer capacity and operating efficiency of the equipment; humidity parameters: for equipment involving humidity control, dehumidifiers and humidifiers; equipment status information: the operating status of the equipment (operating, shut down, standby), and fault alarm information, which help to promptly detect and handle equipment failures.

[0045] Energy consumption level analysis is to evaluate the overall energy consumption level of the equipment through statistical methods (average, median); energy consumption peak period identification is to analyze data to determine the time period with the highest energy consumption, which is related to peak equipment usage, external environmental conditions (temperature, humidity) or specific events (holidays); energy consumption anomaly point detection is to identify outliers in energy consumption data, which are caused by equipment failure, improper operation or data recording errors.

[0046] Energy efficiency calculations evaluate the energy performance of equipment in comparison with industry standards, which may vary by region, equipment type, and operating conditions.

[0047] Energy consumption levels are divided according to energy efficiency indicators. The energy consumption level division methods include energy efficiency level identification: letter identification (such as A+++, A++, A+, A, B, C, D), the earlier the letter, the higher the energy efficiency and the lower the energy consumption; Energy Efficiency Coefficient (COP): a measure of the energy efficiency of the product, the higher the value, the lower the energy consumption and the better the energy efficiency; Energy Efficiency Index (EEI): a comprehensive indicator for energy efficiency calibration of buildings and power products, the smaller the value, the better the energy efficiency; Energy consumption: the levels are divided according to energy consumption, the lower the energy consumption, the better the energy efficiency and the higher the level.

[0048] Energy consumption trend refers to the energy consumption and its changing trend in a certain period of time. It reflects the evolution of energy consumption over time and helps to improve energy utilization efficiency.

[0049] Energy-saving potential refers to the amount of energy saving that can be achieved within a certain period of time through technological improvements, management optimization and other means. It reflects the gap between the current energy consumption level and the ideal state or the industry average level. It is an important basis for formulating energy-saving measures and promoting energy conservation and consumption reduction.

[0050] Energy-saving potential can be relatively divided according to factors such as the amount of energy saving, the difficulty of technical implementation, and the size of economic benefits. It includes: high potential level: large energy saving, high technical maturity, and significant economic benefits; medium potential level: moderate energy saving, high technical feasibility, and general economic benefits; low potential level: small energy saving, greater difficulty in technical implementation, or unclear economic benefits.

[0051] Step S2, connecting with HVAC equipment through Internet of Things technology to collect HVAC equipment parameters in real time; Wherein step S2 also includes the following sub-steps: S2-1, clarify the parameters that need to be monitored for HVAC equipment, including outdoor temperature, humidity, cooling tower outlet water temperature, cooling load, and chiller status; S2-2, selecting an IoT sensor that matches the parameters to be collected, and installing the sensor on the corresponding equipment, wherein the IoT sensor includes a temperature sensor, a humidity sensor, a flow sensor, a pressure sensor, and a liquid level sensor; S2-3, preprocessing the received raw data to identify and remove noise, outliers and duplicate data in the data; S2-4, for missing values ​​in the data, the k-means filling method based on Mahalanobis distance is used to fill them. The specific formula is:

[0052] in, represents a data point with missing values, Indicates that after filling The value of the data point on the lth attribute, K represents the number of clusters of k-means clustering, represents the kth cluster center formed after k-means clustering, According to the Mahalanobis distance and The closest one, belonging to the cluster A set of n complete data points, Representing a collection The value of the jth data point on the lth attribute, Representing a collection The weight of the j-th data point in .

[0053] It should be noted that outdoor temperature is a key factor affecting the energy consumption and performance of the HVAC system. By monitoring the outdoor temperature in real time, the system settings can be adjusted more accurately to achieve the goal of energy saving and consumption reduction; outdoor humidity: humidity and temperature work together to affect the human body's comfort, and it is also an important factor affecting the dehumidification capacity of the air-conditioning system; cooling tower water outlet temperature: reflects the heat dissipation effect of the cooling system, which helps to evaluate the performance of the cooling tower and optimize the cooling water circulation; cooling load: an important indicator to measure the cooling demand of the air-conditioning system, which directly determines the operating strategy and energy consumption level of the refrigerator; chiller status: including the on or off status of the chiller and the operating efficiency, which helps to detect unit failures in a timely manner and prevent shutdown accidents.

[0054] Temperature sensor: used to monitor outdoor temperature and cooling tower outlet water temperature; humidity sensor: used to monitor outdoor humidity; flow sensor: indirectly reflects the size of the cooling load by monitoring the cooling water flow; pressure sensor: used to monitor pressure changes in the water pipe system, which helps to detect potential water leaks or blockages; liquid level sensor: used to monitor the water level of the cooling tower, etc., to ensure the normal operation of the system.

[0055] Raw data often contains noise, outliers, and duplicate data. If not processed, it will have a negative impact on subsequent data analysis. The data preprocessing process includes identifying and removing these data to ensure the accuracy and reliability of subsequent analysis.

[0056] The k-means filling method based on Mahalanobis distance is used as the filling method. The specific process is as follows: The first step is to analyze the correlation between the attributes in the data set to determine which attributes have an important impact on the filling of missing values; The second step is to use the complete data points to perform k-means clustering to form several cluster centers; The third step is to calculate the Mahalanobis distance between the sample points with missing values ​​and each cluster center; The fourth step is to select the k complete data points closest to the missing value sample point as the nearest neighbors according to the Mahalanobis distance; The fifth step is to use the nearest neighbor data points to fill in the missing values ​​by weighted averaging. The weights can be assigned based on the distance or similarity.

[0057] Step S3: Based on the preprocessed data, establish energy consumption models of the chiller, cooling tower, freezing pump and cooling pump; Wherein step S3 also includes the following sub-steps: S3-1, based on the collected chiller operation data, the energy consumption model of the chiller is established using the regression analysis method. The specific formula is:

[0058] in, is the energy consumption of the chiller, is the cooling capacity, is the condensation temperature, is the evaporation temperature, is the unit efficiency, a and b are the coefficients obtained by fitting; S3-2, based on the collected cooling tower operation data, the energy consumption model of the cooling tower is established using the multivariate linear regression method. The specific formula is:

[0059] in, is the energy consumption of the cooling tower, is the load of the cooling tower, is the inlet water temperature, is the outlet water temperature, is the fan efficiency, c and d are the coefficients obtained by fitting; S3-3, based on the collected operating data of the refrigeration pump and the cooling pump, the energy consumption model of the refrigeration pump and the cooling pump is established using the power function regression method. The specific formula is:

[0060] in, is the energy consumption of the pump, is the flow rate, H is the head, is the pump efficiency, and e is the coefficient obtained by fitting.

[0061] It should be noted that the variables in the formula (cooling capacity, temperature) need to ensure consistent units to avoid calculation errors. The unit efficiency is a dimensionless parameter. Considering its characteristics that change with operating conditions, the fitting of coefficients a and b needs to be based on a large amount of experimental data to ensure the accuracy and reliability of the model.

[0062] The multiple linear regression model is a regression analysis model that studies the linear relationship between a dependent variable and multiple independent variables if there are two or more independent variables. The fan efficiency is a dimensionless parameter, and its characteristics that change with wind speed and wind pressure need to be considered.

[0063] Power function regression uses power function to establish the relationship between independent variables and dependent variables. It is used to describe the nonlinear growth or attenuation trend of data. It is suitable for describing scenarios where there is a nonlinear relationship between independent variables and dependent variables. Pump efficiency is a dimensionless parameter, and its characteristics of changing with flow rate and head are taken into consideration.

[0064] Step S4: Use a decision tree algorithm to build an energy consumption prediction regression model to predict the total energy consumption of the HVAC system in real time; Wherein step S4 also includes the following sub-steps: S4-1, use the information entropy formula to calculate the information entropy of the training set. The specific formula is:

[0065] Among them, E is information entropy, D is the data set, which is divided into m categories. The i-th category subset, Yes Category The probability of S4-2, for each candidate attribute, calculate its information entropy after splitting, and calculate the information gain, select the attribute with the highest information gain as the splitting attribute of the current node, and construct the node of the decision tree. The specific formula is:

[0066]

[0067] Where G is the information gain rate, is the i-th attribute, yes The number of different subsets included, The dataset D is split into disjoint subsets, Is a subset Total content of the sample; S4-3, for each child node, divide the data set into subsets according to the selected splitting attribute, recursively select the optimal attribute and build a decision tree until the stopping condition is met, wherein the stopping condition includes that all samples belong to the same class, no more attributes can be selected, and the maximum depth of the tree is reached; and recursively build a decision tree; S4-4, using the post-pruning method to simplify the decision tree structure by calculating the weighted confidence of the nodes; S4-5, based on the decision tree model, the total energy consumption of the HVAC system is taken as the independent variable, a multivariate linear regression equation is constructed, and the least squares method is used to solve the regression coefficient. The specific formula is:

[0068]

[0069] in, is the factor of total energy consumption of HVAC system, Y is total energy consumption, is the regression coefficient, is the error term, M is the design matrix, and N is the response variable vector.

[0070] It should be noted that information entropy is an indicator to measure the purity of a data set. The higher the purity, the smaller the information entropy. In the decision tree algorithm, information entropy is used to evaluate the effect of the division of a data set on a certain attribute.

[0071] Information gain indicates the reduction in information entropy after a data set is divided using a certain attribute. The greater the information gain, the better the effect of the attribute on data division.

[0072] Recursive process: For each child node, the data set is divided into subsets according to the selected splitting attributes, and the optimal attributes are recursively selected to build a decision tree.

[0073] Post-pruning method is to prune the decision tree into a smaller subtree to reduce the misclassification caused by overfitting the training data.

[0074] The specific steps of the post-pruning method include: Step 1: Generate a complete decision tree; Step 2: Randomly select a portion of data from the data set to evaluate the performance of the pruned decision tree; Step 3, starting from the bottom of the decision tree, examine each non-leaf node one by one; Step 4: For each node under investigation, calculate the validation set error rate before and after pruning. The error rate after pruning refers to the error rate corresponding to the leaf node being classified into the category with the lowest classification error rate after the node and its subtree are replaced by leaf nodes. Step 5: If the error rate after pruning is less than the error rate without pruning, prune the node to make it a leaf node, and use the mode of the node as the predicted value of the leaf node. Step 6: Repeat the above steps until all nodes have been traversed once.

[0075] The regression equation is based on the decision tree model, taking the total energy consumption of the HVAC system as the independent variable to construct a multivariate linear regression equation; the least squares method is used to solve the regression coefficient to minimize the sum of squares of the error terms.

[0076] The design matrix M contains the values ​​of all independent variables, and the response variable vector N contains the value of total energy consumption. By solving the relationship between M and N, the regression coefficient can be obtained. , thus constructing a complete regression equation.

[0077] Step S5: formulating an optimal control strategy for HVAC equipment based on the predicted energy consumption data and the set energy consumption control objective function; Wherein, in step S5, the following sub-steps are also included: S5-1, according to the collected HVAC equipment parameters, set an energy consumption control objective function f for the HVAC equipment. The specific formula is:

[0078] in, is the energy consumption weight coefficient, E is the energy consumption, and are the temperature and set temperature of the ith zone, and are the humidity of the jth area and the set humidity, and are the weight coefficients of temperature and humidity respectively; S5-2, calculate the energy consumption difference based on the predicted energy consumption and the set energy consumption target, and determine the adjustment coefficient based on the energy consumption difference, equipment operating status and environmental parameters. The specific formula is:

[0079]

[0080] in, is the energy consumption difference, is the predicted energy consumption, is the set energy consumption target, k is the adjustment coefficient, g is the adjustment coefficient calculation function, U is the equipment status, T is the temperature, and RH is the humidity; S5-3, formulate an optimization control strategy based on the energy consumption difference, the adjustment coefficient and the operating characteristics of the equipment. The optimization control strategy includes adjusting the operating parameters of the equipment, starting or shutting down some equipment, adjusting the equipment operating time, and adjusting the operating parameters of the equipment through the following formula:

[0081] in, is the new operating parameter, It is the original operating parameter.

[0082] It should be noted that the energy consumption weight coefficient is used to adjust the relative importance of energy consumption in the objective function. This coefficient can be adjusted to emphasize the importance of reducing energy consumption. Energy consumption represents the energy consumption of HVAC equipment; temperature and set temperature represent the difference between actual temperature and expected temperature. The greater the difference, the greater the value of the objective function, indicating that more energy is needed to adjust the temperature; humidity and set humidity represent the difference between actual humidity and expected humidity; the weight coefficients of temperature and humidity are used to adjust the relative importance of temperature and humidity in the objective function.

[0083] The energy consumption difference is the difference between the predicted energy consumption and the set energy consumption target. The larger the difference, the more adjustments are needed to approach the energy consumption target. The adjustment coefficient is used to adjust the operating parameters of the equipment to achieve the energy consumption target.

[0084] Adjusting the operating parameters of the equipment helps to accurately control the environment: by adjusting the temperature, humidity, and wind speed, the comfort of the indoor environment can be accurately controlled to meet the needs of different groups of people or different time periods; energy saving and consumption reduction: under the premise of ensuring comfort, appropriate adjustment of the operating parameters of the equipment can significantly reduce energy consumption; protect equipment: reasonable operating parameters can avoid long-term overload operation of equipment, reduce equipment wear and tear, and extend service life; improve air quality: adjusting the fresh air volume and exhaust air volume can help improve indoor air quality and reduce air pollution.

[0085] Starting or shutting down some equipment can help you flexibly respond to changes in demand: According to indoor and outdoor environments and personnel activities, you can flexibly start or shut down some equipment to meet energy consumption and comfort requirements in different time periods; Energy saving and emission reduction: When all equipment is not needed, shutting down some equipment can significantly reduce energy consumption and reduce energy waste; Improve system efficiency: By shutting down redundant equipment, you can improve the operating efficiency of the entire system and enable the remaining equipment to operate under more optimized conditions; Reduce operation and maintenance costs: Reducing the operating time of equipment can reduce maintenance frequency and operation and maintenance costs, and extend equipment life.

[0086] Adjusting the equipment running time helps optimize the distribution of energy consumption: According to the changes in the indoor and outdoor environment and the regularity of personnel activities, the equipment running time can be reasonably arranged to achieve the optimal distribution of energy consumption while ensuring comfort; reduce peak energy consumption: By adjusting the equipment running time, you can avoid running high-energy-consuming equipment during peak power consumption hours, which helps reduce the load on the power grid and reduce peak energy consumption. Improve energy efficiency: Running equipment during off-peak hours or during peak periods of renewable energy generation can improve energy efficiency and reduce energy costs; enhance system stability: By reasonably arranging the equipment running time, you can avoid frequent start and stop of equipment and enhance the stability and reliability of the system.

[0087] Step S6: Apply the formulated optimization control strategy to the HVAC equipment, conduct real-time monitoring and feedback, and iteratively optimize the control strategy according to the actual effect; Wherein, in step S6, the following sub-steps are also included: S6-1, deploy the optimization control strategy to the control system of the HVAC equipment to monitor the operating status and energy consumption data of the HVAC equipment in real time; S6-2, based on real-time monitoring data and preset evaluation indicators, evaluate the effect of the optimization control strategy. The specific formula is:

[0088] Among them, H is the effect evaluation index, h is the effect evaluation function, is the actual energy consumption, is the energy consumption target set; S6-3, based on the evaluation results, iteratively optimize the control strategy, adjust the operating parameters of the equipment, start or shut down some equipment, and adjust the equipment operating time.

[0089] It should be noted that the deployment of the optimization control strategy into the control system of the HVAC equipment is integrated into the control system of the HVAC equipment through programming or configuration, which involves interface docking with the existing control system and parameter setting.

[0090] The preset evaluation indicators are the key to evaluating the effectiveness of the control strategy. The effect evaluation index H is calculated by the effect evaluation function h, which takes into account the deviation between the actual energy consumption and the set energy consumption target.

[0091] The adjusted control strategy will be deployed to the control system again, and steps S1 to S6 will be repeated for iterative optimization. This process may need to be performed multiple times until the stop condition is reached. The stop condition includes achieving the preset energy-saving target: the control strategy after iterative optimization can reduce the actual energy consumption of the HVAC equipment to below the preset energy-saving target, and the iteration process can be stopped; iterative convergence: the iteration process gradually approaches a fixed value or stable state. If the control strategy changes very little after multiple consecutive iterations, or the change in the effect evaluation index H tends to be stable, it can be considered that the iteration has converged and the iteration is stopped; reaching the maximum number of iterations: in order to avoid infinite loops and over-calculation, a maximum number of iterations is set. If the number of iterations reaches this upper limit, but the other stop conditions mentioned above have not been met, the iteration can be forced to stop and implemented based on the current optimal control strategy.

[0092] See also Figure 2 , which shows a system module architecture diagram of an energy consumption optimization control system for HVAC equipment provided by an embodiment of the present invention, the system comprising: Data acquisition module, data preprocessing module, energy consumption model building module, energy consumption prediction module, optimization control strategy formulation module, monitoring and feedback module, data storage module; The data acquisition module is used to collect the operating parameters of the HVAC equipment in real time; The data preprocessing module is used to preprocess the collected data; The energy consumption model establishment module establishes an energy consumption model of the HVAC equipment based on the preprocessed data; The energy consumption prediction module is used to predict the total energy consumption of the HVAC system; The optimization control strategy formulation module is used to formulate and execute the optimization control strategy; The monitoring and feedback module is used to monitor the operating status of the HVAC equipment in real time and provide feedback; The data storage module is used to store collected data, pre-processed data, energy consumption models and information on optimized control strategies.

[0093] It should be noted that the data acquisition module is the basis of the system and is responsible for real-time collection of the operating parameters of HVAC equipment, including but not limited to temperature, humidity, air volume, water flow rate, pressure, and power consumption.

[0094] The data preprocessing module is used to clean, denoise, and format the collected raw data to improve the quality and availability of the data, including processing missing values, outliers, duplicate values, etc.

[0095] The energy consumption model building module builds the energy consumption model of HVAC equipment based on the preprocessed data using statistical methods, which can describe the relationship between equipment energy consumption and operating parameters.

[0096] The energy consumption prediction module uses the energy consumption model and combines the current and future operating parameters to predict the total energy consumption of the HVAC system, which helps to evaluate the energy consumption under different control strategies. The prediction results can provide an important reference for the formulation of optimized control strategies. By comparing the predicted energy consumption under different strategies, the optimal strategy can be selected to reduce energy consumption.

[0097] The optimization control strategy formulation module formulates and executes optimization control strategies based on energy consumption prediction results and current equipment operating status. Effective strategies can significantly improve the energy efficiency and operating efficiency of equipment.

[0098] The monitoring and feedback module is used to monitor the operating status of HVAC equipment in real time and feed back the monitoring results to the optimization control strategy formulation module. It can help the system to promptly discover and solve problems during equipment operation and ensure the effective implementation of the optimization control strategy. The monitoring data can also be used to further improve the energy consumption model and optimize the control strategy.

[0099] The data storage module is used to store the collected data, pre-processed data, energy consumption models and information on optimization control strategies, which helps the system analyze and compare historical data to evaluate the optimization effect and continuously improve it.

[0100] In this way, an energy consumption optimization control method and system for HVAC equipment can realize real-time monitoring, prediction and optimization control of equipment energy consumption, which can not only improve the energy efficiency and operating efficiency of the equipment, but also reduce energy consumption and operating costs, and contribute to sustainable development.

[0101] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for optimizing the control of energy consumption of HVAC equipment, characterized in that: The method includes: Step S1, comprehensively evaluate the energy consumption of HVAC equipment to identify the current energy consumption status and energy saving potential of the equipment; Step S2, connecting with HVAC equipment through Internet of Things technology to collect HVAC equipment parameters in real time; Step S3, based on the preprocessed data, establishing energy consumption models of the chiller, cooling tower, freezing pump and cooling pump; Step S4, using a decision tree algorithm to build an energy consumption prediction regression model to predict the total energy consumption of the HVAC system in real time; Step S5, formulating an optimal control strategy for HVAC equipment based on the predicted energy consumption data and the set energy consumption control objective function; Step S6, applying the formulated optimization control strategy to the HVAC equipment, performing real-time monitoring and feedback, and iteratively optimizing the control strategy according to the actual effect.

2. The energy consumption optimization control method of HVAC equipment according to claim 1, characterized in that: Wherein step S1 also includes the following sub-steps: S1-1, collecting historical energy consumption data of the equipment from the control system and energy management system of the HVAC equipment, wherein the historical energy consumption data includes equipment operation time, energy consumption and equipment parameters; S1-2, based on the collected data, analyze the energy consumption status of HVAC equipment, identify the energy consumption level of the equipment, peak energy consumption period and abnormal energy consumption points; S1-3, compare the current energy consumption level with the energy consumption level of the industry standard, evaluate the energy efficiency of the equipment, and identify the factors affecting energy consumption. The energy efficiency = (current energy consumption / industry standard energy consumption) * 100%. The factors include equipment aging, improper operation parameter settings, and changes in the external environment. S1-4, predict the energy consumption trend of the equipment under different operating conditions, and evaluate the energy saving potential of the equipment based on the predicted trend.

3. The energy consumption optimization control method of HVAC equipment according to claim 1, characterized in that: Wherein step S2 also includes the following sub-steps: S2-1, clarify the parameters that need to be monitored for HVAC equipment, including outdoor temperature, humidity, cooling tower outlet water temperature, cooling load, and chiller status; S2-2, selecting an IoT sensor that matches the parameters to be collected, and installing the sensor on the corresponding equipment, wherein the IoT sensor includes a temperature sensor, a humidity sensor, a flow sensor, a pressure sensor, and a liquid level sensor; S2-3, preprocessing the received raw data to identify and remove noise, outliers and duplicate data in the data; S2-4, for missing values ​​in the data, the k-means filling method based on Mahalanobis distance is used to fill them. The specific formula is: ； in, represents a data point with missing values, Indicates that after filling The value of the data point on the lth attribute, K represents the number of clusters of k-means clustering, represents the kth cluster center formed after k-means clustering, ( ) indicates that according to the Mahalanobis distance and The closest one, belonging to the cluster A set of n complete data points, Representing a collection ( ) is the value of the jth data point on the lth attribute, Representing a collection ( ) is the weight of the jth data point in .

4. The method for optimizing the control of energy consumption of HVAC equipment according to claim 1, characterized in that: Wherein step S3 also includes the following sub-steps: S3-1, based on the collected chiller operation data, the energy consumption model of the chiller is established using the regression analysis method. The specific formula is: ； in, is the energy consumption of the chiller, is the cooling capacity, is the condensation temperature, is the evaporation temperature, is the unit efficiency, a and b are the coefficients obtained by fitting; S3-2, based on the collected cooling tower operation data, the energy consumption model of the cooling tower is established using the multivariate linear regression method. The specific formula is: ； in, is the energy consumption of the cooling tower, is the load of the cooling tower, is the inlet water temperature, is the outlet water temperature, is the fan efficiency, c and d are the coefficients obtained by fitting; S3-3, based on the collected operating data of the refrigeration pump and the cooling pump, the energy consumption model of the refrigeration pump and the cooling pump is established using the power function regression method. The specific formula is: ； in, is the energy consumption of the pump, is the flow rate, H is the head, is the pump efficiency, and e is the coefficient obtained by fitting.

5. The method for optimizing the control of energy consumption of HVAC equipment according to claim 1, characterized in that: Wherein step S4 also includes the following sub-steps: S4-1, use the information entropy formula to calculate the information entropy of the training set. The specific formula is: ； Among them, E is information entropy, D is the data set, which is divided into m categories. The i-th category subset, Yes Category probability; S4-2, for each candidate attribute, calculate its information entropy after splitting, and calculate the information gain, select the attribute with the highest information gain as the splitting attribute of the current node, and construct the node of the decision tree. The specific formula is: ； ； Where G is the information gain rate, is the i-th attribute, yes The number of different subsets included, The dataset D is split into disjoint subsets, Is a subset Total content of the sample; S4-3, for each child node, divide the data set into subsets according to the selected splitting attribute, recursively select the optimal attribute and build a decision tree until the stopping condition is met, wherein the stopping condition includes that all samples belong to the same class, no more attributes can be selected, and the maximum depth of the tree is reached; and recursively build a decision tree; S4-4, using post-pruning method to simplify the decision tree structure by calculating the weighted confidence of the nodes; S4-5, based on the decision tree model, the total energy consumption of the HVAC system is taken as the independent variable, a multivariate linear regression equation is constructed, and the least squares method is used to solve the regression coefficient. The specific formula is: ； ； in, , , …, is the factor of total energy consumption of HVAC system, Y is total energy consumption, , , …, is the regression coefficient, is the error term, M is the design matrix, and N is the response variable vector.

6. The method for optimizing the control of energy consumption of HVAC equipment according to claim 1, characterized in that: Wherein, in step S5, the following sub-steps are also included: S5-1, according to the collected HVAC equipment parameters, set an energy consumption control objective function for the HVAC equipment. The specific formula is: ； in, is the energy consumption weight coefficient, E is the energy consumption, and are the temperature and set temperature of the ith zone, and are the humidity of the jth area and the set humidity, and are the weight coefficients of temperature and humidity respectively; S5-2, calculate the energy consumption difference based on the predicted energy consumption and the set energy consumption target, and determine the adjustment coefficient based on the energy consumption difference, equipment operating status and environmental parameters. The specific formula is: ； ； in, is the energy consumption difference, is the predicted energy consumption, is the set energy consumption target, k is the adjustment coefficient, g is the adjustment coefficient calculation function, U is the equipment status, T is the temperature, and RH is the humidity; S5-3, formulate an optimization control strategy based on the energy consumption difference, the adjustment coefficient and the operating characteristics of the equipment. The optimization control strategy includes adjusting the operating parameters of the equipment, starting or shutting down some equipment, adjusting the equipment operating time, and adjusting the operating parameters of the equipment through the following formula: ； in, is the new operating parameter, It is the original operating parameter.

7. The method for optimizing the control of energy consumption of HVAC equipment according to claim 1, characterized in that: Wherein, in step S6, the following sub-steps are also included: S6-1, deploy the optimization control strategy to the control system of the HVAC equipment to monitor the operating status and energy consumption data of the HVAC equipment in real time; S6-2, based on real-time monitoring data and preset evaluation indicators, evaluate the effect of the optimization control strategy. The specific formula is: ； Among them, H is the effect evaluation index, h is the effect evaluation function, is the actual energy consumption, is the energy consumption target set; S6-3, based on the evaluation results, iteratively optimize the control strategy, adjust the operating parameters of the equipment, start or shut down some equipment, and adjust the equipment operating time.

8. An energy consumption optimization control system for HVAC equipment, characterized in that: include: Data acquisition module, data preprocessing module, energy consumption model building module, energy consumption prediction module, optimization control strategy formulation module, monitoring and feedback module, data storage module; The data acquisition module is used to collect the operating parameters of the HVAC equipment in real time; The data preprocessing module is used to preprocess the collected data; The energy consumption model establishment module establishes an energy consumption model of the HVAC equipment based on the preprocessed data; The energy consumption prediction module is used to predict the total energy consumption of the HVAC system; The optimization control strategy formulation module is used to formulate and execute the optimization control strategy; The monitoring and feedback module is used to monitor the operating status of the HVAC equipment in real time and provide feedback; The data storage module is used to store collected data, pre-processed data, energy consumption models and information on optimized control strategies.

Images