Indoor temperature control method and device, electronic equipment and readable storage medium

Abstract

The present disclosure relates to the technical field of temperature control, and provides an indoor temperature control method and device, electronic equipment and a readable storage medium. The method comprises: adjusting current operating state data based on a target temperature and indoor and outdoor environment characteristic data to obtain a plurality of first candidate operating state data of a cold station device; and screening target operating state data from the first candidate operating state data based on the target temperature and current indoor and outdoor environment characteristic data; wherein a difference between a predicted temperature corresponding to the target operating state data and the target temperature is less than a first preset value, and the corresponding predicted energy consumption is the minimum value among predicted energy consumptions corresponding to the first candidate operating state data; and controlling the cold station device according to the target operating state data, thereby solving the defects of extensive temperature control and high energy consumption in the control method of the prior art and improving the accuracy and energy utilization efficiency of the cold station device in temperature control.

Description

Technical Field

[0001] This disclosure relates to the field of temperature control technology, and in particular to an indoor temperature control method, apparatus, electronic device, and readable storage medium. Background Technology

[0002] As a significant component of urban energy consumption, improving the energy efficiency of commercial parks and shopping malls is crucial for achieving the aforementioned goals. With increasing urbanization and commercial activity, energy consumption in public places like shopping malls has garnered growing attention. Cooling systems, as key facilities for regulating indoor temperature, account for a large portion of a shopping mall's total energy consumption. Existing cooling systems employ computer-based control systems that collect indoor and outdoor environmental data through sensors and automatically adjust the operating status of cooling equipment according to preset control logic. However, they lack real-time data analysis and prediction, failing to achieve precise and personalized temperature control, resulting in inaccurate temperature control and excessive energy consumption. Summary of the Invention

[0003] In view of this, the present disclosure provides an indoor temperature control method, apparatus, electronic device, and readable storage medium to solve the problem of inaccurate indoor temperature control in the prior art.

[0004] A first aspect of this disclosure provides an indoor temperature control method, comprising: acquiring current indoor and outdoor environmental characteristic data, current operating status data of a chiller plant, and a target temperature; adjusting the current operating status data based on the target temperature and the indoor and outdoor environmental characteristic data to obtain multiple first candidate operating status data of the chiller plant; selecting target operating status data from the first candidate operating status data based on the target temperature and the current indoor and outdoor environmental characteristic data; wherein the difference between the predicted temperature corresponding to the target operating status data and the target temperature is less than a first preset value, and the corresponding predicted energy consumption is the minimum value among the predicted energy consumption corresponding to the first candidate operating status data or the difference between the predicted energy consumption and the minimum value is less than a second preset value; and controlling the chiller plant according to the target operating status data.

[0005] A second aspect of this disclosure provides an indoor temperature control device, comprising: a data acquisition module for acquiring current indoor and outdoor environmental characteristic data, current operating status data of a chiller plant, and a target temperature; an adjustment module for adjusting the current operating status data based on the target temperature and the indoor and outdoor environmental characteristic data to obtain multiple first candidate operating status data of the chiller plant; a filtering module for filtering target operating status data from the first candidate operating status data based on the target temperature and the current indoor and outdoor environmental characteristic data; wherein the difference between the predicted temperature corresponding to the target operating status data and the target temperature is less than a first preset value, and the corresponding predicted energy consumption is the minimum value among the predicted energy consumptions corresponding to the first candidate operating status data or the difference between the predicted energy consumption and the minimum value is less than a second preset value; and an execution module for controlling the chiller plant according to the target operating status data.

[0006] A third aspect of this disclosure provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method described above.

[0007] A fourth aspect of this disclosure provides a readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described method.

[0008] The beneficial effects of this disclosed embodiment compared to the prior art are as follows: by acquiring current indoor and outdoor environmental characteristic data, current operating status data of the chiller equipment, and target temperature, a foundation is provided for subsequent analysis and decision-making. The indoor and outdoor environmental characteristic data and the current operating status data of the chiller equipment are important bases for formulating control strategies for the chiller equipment, i.e., candidate operating status data. The target temperature is the indoor temperature to be achieved. Based on the target temperature and indoor and outdoor environmental characteristic data, the current operating status of the chiller equipment is simulated and adjusted to generate multiple possible operating states (i.e., first candidate operating status data), providing multiple possibilities for subsequent screening. Based on the target temperature and current indoor and outdoor environmental characteristic data, target operating status data is obtained by screening from multiple first candidate operating status data. The difference between the predicted temperature and the target temperature corresponding to the target operating status data is less than a first preset value, and the corresponding predicted energy consumption is the minimum value among the predicted energy consumption corresponding to the first candidate operating status data, or the difference between the predicted energy consumption and the minimum value is less than a second preset value. From multiple first candidate operating status data, target operating status data that can both meet temperature control requirements and achieve energy consumption optimization is selected, ensuring the effectiveness and economy of the control strategy. The final selected target operating status data is executed, and the chiller plant equipment is controlled according to the target operating status data to ensure that the indoor temperature reaches the target temperature. The temperature control method proposed in this disclosure significantly improves the accuracy of temperature control and energy utilization efficiency of chiller plant equipment through real-time data collection, dual-target optimization of energy consumption and temperature, and dynamic adjustment control. It solves the defects of coarse temperature control and high energy consumption in existing control methods, and helps to better adapt to constantly changing environmental conditions and user needs, achieving more refined and efficient temperature management. Attached Figure Description

[0009] To more clearly illustrate the technical solutions in the embodiments of this disclosure, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0010] Figure 1 This is a schematic flowchart of an indoor temperature control method provided in an embodiment of this disclosure;

[0011] Figure 2 This is a first candidate running status data result table provided in an embodiment of this disclosure;

[0012] Figure 3 This is another first candidate running status data result table provided in this embodiment of the disclosure;

[0013] Figure 4This is a schematic diagram of the structure of an indoor temperature control device provided in an embodiment of this disclosure;

[0014] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0015] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, so as to provide a thorough understanding of the embodiments of this disclosure. However, those skilled in the art will understand that this disclosure may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this disclosure with unnecessary detail.

[0016] An indoor temperature control method and apparatus according to an embodiment of the present disclosure will now be described in detail with reference to the accompanying drawings.

[0017] Figure 1 This is a schematic flowchart of an indoor temperature control method provided in an embodiment of this disclosure. Figure 1 As shown, the indoor temperature control method includes:

[0018] Step 101: Obtain current indoor and outdoor environmental characteristic data, current operating status data of the chiller equipment, and target temperature.

[0019] Specifically, current indoor and outdoor environmental characteristic data can include current time, current indoor temperature, current outdoor temperature, current indoor humidity, current outdoor humidity, pedestrian flow data, outdoor wind speed and force, weather, etc. This data can be acquired in real time through various sensors installed indoors and outdoors, providing the environmental background conditions for the operation of the chiller plant equipment. Current operating status data of the chiller plant equipment can include current time, chiller power, number of chillers, number of cooling pumps, cooling pump frequency, chilled water supply temperature, chilled water return temperature, chilled water supply flow rate, chilled water return flow rate, chiller operating status, etc. This data reflects the operating status of the chiller plant system and is a crucial indicator of its performance. This data can be provided by the chiller plant equipment's built-in sensors or a separate monitoring system. By acquiring real-time data on indoor and outdoor environmental characteristics and the operating status of the chiller plant equipment, a foundation is laid for subsequent data processing and analysis. Through continuous monitoring and recording of these data, the chiller plant's temperature control system can more accurately understand indoor environmental changes and the equipment's operating status, providing reliable data support for intelligent control. Specifically, the target temperature is the indoor temperature setpoint that the chiller plant's temperature control system aims to achieve or maintain, typically set by the user. The target temperature serves as a reference point for the chiller plant's temperature control system, guiding the equipment to adjust its operating parameters to reach the target temperature. By adjusting the indoor temperature to the target temperature, the comfort of the indoor environment is improved, meeting the needs of occupants.

[0020] Step 102: Based on the target temperature and indoor and outdoor environmental characteristic data, adjust the current operating status data to obtain multiple first candidate operating status data for the chiller station equipment.

[0021] In some embodiments, indoor and outdoor environmental characteristic data include the current indoor temperature, the target temperature being the set indoor temperature expected by the user, and the current operating status data of the chiller equipment including the operating parameters of the chiller, cooling pump, cooling tower, chiller set temperature, chilled water pump frequency, etc., at the current moment. The current operating status data of the chiller equipment directly affects the current indoor temperature. Based on the target temperature and the current indoor temperature, the operating status of the chiller equipment is adjusted to generate multiple sets of possible operating status data, i.e., multiple first candidate operating status data of the chiller equipment. By dynamically adjusting the operating status of the chiller equipment, the indoor temperature can be controlled more precisely to approach the target temperature, and the lowest energy consumption operating strategy can be found while meeting temperature control requirements, thereby achieving energy conservation and emission reduction. Specifically, adjusting the operating status of the chiller plant equipment based on the target temperature and the current indoor temperature includes: if the current indoor temperature is lower than the target temperature, indicating overcooling, the number of chillers and / or the frequency of the chilled water pumps can be reduced. In this case, the search space gradually decreases from the current operating status data until the minimum number of chillers that can be turned on or completely shut down is reached. If the current indoor temperature is higher than the target temperature, indicating overheating, the number of chillers and / or the frequency of the chilled water pumps can be increased. In this case, the search space gradually increases from the current operating status data until the maximum number of chillers that can be turned on is reached. Existing temperature control of chiller plant equipment is mainly based on fixed rules and lacks flexibility. Dynamically adjusting the operating status of the chiller plant equipment based on indoor and outdoor environmental characteristics allows for fine-grained control according to actual needs, avoiding overcooling or overheating, thereby improving the accuracy of temperature control. By generating multiple first-candidate operating status data, diverse options are provided for subsequent optimization decisions. By finding the operating strategy that is closest to the target temperature and has the lowest energy consumption, energy consumption can be effectively reduced and energy waste can be avoided.

[0022] Step 103: Based on the target temperature and current indoor and outdoor environmental characteristic data, select target operating status data from the first candidate operating status data; wherein the difference between the predicted temperature corresponding to the target operating status data and the target temperature is less than a first preset value, and the corresponding predicted energy consumption is the minimum value among the predicted energy consumption corresponding to the first candidate operating status data or the difference between the predicted energy consumption and the minimum value is less than a second preset value.

[0023] In some embodiments, operating status data that meets the following two conditions is selected from multiple first candidate operating status data as target operating status data: including the difference between the predicted temperature and the target temperature and the predicted energy consumption. Based on the current indoor and outdoor environmental characteristic data and each first candidate operating status data, the indoor temperature corresponding to each first candidate operating status data is predicted to obtain the predicted temperature corresponding to each first candidate operating status data; based on the current indoor and outdoor environmental characteristic data and each first candidate operating status data, the energy consumption corresponding to each first candidate operating status data is predicted to obtain the predicted energy consumption corresponding to each first candidate operating status data. It is determined that the difference between the predicted temperature and the target temperature corresponding to the selected target operating status data is less than a first preset value, so that the indoor temperature (i.e., the predicted temperature) corresponding to the target operating status data is sufficiently close to the target temperature, and the corresponding predicted energy consumption is the minimum value among the predicted energy consumption corresponding to the first candidate operating status data, or the difference between the predicted energy consumption and the minimum value is less than a second preset value, so that the target operating status data meets the temperature requirements while also having the lowest possible energy consumption. By selecting target operating status data that is closest to the target temperature and has low energy consumption, the indoor temperature is kept within a comfortable range, and energy consumption can be effectively reduced, energy waste can be avoided, and more precise indoor temperature control can be achieved.

[0024] Step 104: Control the chiller plant equipment based on the target operating status data.

[0025] In some embodiments, target operating status data may include: chiller equipment name: the name or identifier of the chiller system; project name: the name of the current project or shopping mall; target temperature: the set target indoor temperature; number of cooling towers: the set number of cooling towers to be operated; number of chilled water pumps: the set number of chilled water pumps to be operated; chilled water pump frequency: the set operating frequency of the chilled water pumps; number of chillers: the set number of chillers to be operated; set temperature: the set set temperature of the chillers (i.e., chilled water supply temperature). Specifically, the chilled water supply temperature is the temperature of the chilled water exiting the chiller evaporator, which directly relates to the cooling capacity of the chiller unit. A lower chilled water supply temperature indicates a greater cooling capacity, and a lower supply temperature means that the chiller unit needs more energy to lower the temperature of the chilled water. Cooling towers are used to cool the hot water returned from the chiller for reuse. Increasing the number of cooling towers can improve cooling efficiency and indirectly increase the cooling capacity of the chiller, but it also increases the energy consumption of the cooling towers themselves. Chilled water pumps circulate chilled water within the chilled water plant. Increasing the number of pumps helps increase the chilled water circulation flow rate, thereby increasing the cooling capacity. However, increasing the number of pumps also increases the energy consumption of the chilled water plant. The pump frequency determines the chilled water flow rate; reducing the pump frequency reduces the chilled water flow rate, thus reducing the cooling capacity. Reducing the pump frequency also reduces energy consumption. The power consumption of a chilled water pump is positively correlated with its rotational speed. The number of chillers determines the total cooling capacity of the chilled water plant. Increasing the number of chillers increases the cooling capacity of the chilled water plant but also increases its energy consumption.

[0026] In some embodiments, the filtered target operating status data is sent to the chiller plant equipment, enabling the equipment to adjust according to the target operating status data, thus achieving intelligent control and precise control of the chiller plant equipment. By precisely controlling the operating status of the chiller plant equipment, the indoor temperature can be consistently maintained within the set target temperature range, improving the accuracy and stability of temperature control, contributing to enhanced indoor environmental comfort, and meeting users' high requirements for temperature control. Simultaneously, while meeting temperature control requirements, the energy consumption of the chiller plant equipment is reduced.

[0027] In some embodiments, the chiller plant continuously collects actual indoor and outdoor environmental characteristic data and operating status data during operation, and feeds this data back to the chiller plant's temperature control system for subsequent parameter updates and optimization. Specifically, the feedback adjustment mechanism includes: continuously collecting actual indoor and outdoor environmental characteristic data and chiller plant operating status data; feeding the collected indoor and outdoor environmental characteristic data and chiller plant operating status data back to the chiller plant's temperature control system for parameter updates and optimization. Based on the feedback data, the chiller plant's temperature control system is updated and adjusted to improve its accuracy and predictive capability. Based on the updated chiller plant's temperature control system, the generated control strategy (i.e., the selected target operating status data) is adjusted to adapt to current environmental changes and energy consumption demands. By continuously collecting actual indoor and outdoor environmental characteristic data and chiller plant operating status data and feeding them back to the chiller plant's temperature control system, the temperature control system is adjusted and optimized in a timely manner, thereby improving the accuracy and stability of prediction and control. This feedback adjustment mechanism enables the chiller plant's temperature control system to continuously adapt to changes in the indoor and outdoor environment, achieving intelligent management and optimization of the chiller plant.

[0028] The indoor temperature control method provided in this disclosure, by acquiring current indoor and outdoor environmental characteristic data, current operating status data of the chiller plant equipment, and target temperature, provides a foundation for subsequent analysis and decision-making. The indoor and outdoor environmental characteristic data and the current operating status data of the chiller plant equipment are crucial for formulating control strategies for the chiller plant equipment, i.e., candidate operating status data. The target temperature is the desired indoor temperature. Based on the target temperature and indoor and outdoor environmental characteristic data, the current operating status of the chiller plant equipment is simulated and adjusted, generating multiple possible operating states (i.e., first candidate operating status data), providing various possibilities for subsequent selection. Based on the target temperature and current indoor and outdoor environmental characteristic data, target operating status data is selected from the multiple first candidate operating status data. The difference between the predicted temperature and the target temperature corresponding to the target operating status data is less than a first preset value, and the corresponding predicted energy consumption is the minimum value among the predicted energy consumption corresponding to the first candidate operating status data, or the difference between the predicted energy consumption and the minimum value is less than a second preset value. From the multiple first candidate operating status data, target operating status data that can both meet temperature control requirements and achieve energy consumption optimization is selected, ensuring the effectiveness and economy of the control strategy. The final selected target operating status data is executed, and the chiller plant equipment is controlled according to the target operating status data to ensure that the indoor temperature reaches the target temperature. The temperature control method proposed in this disclosure significantly improves the accuracy of temperature control and energy utilization efficiency of chiller plant equipment through real-time data collection, dual-objective optimization of energy consumption and temperature, and dynamic adjustment control. It solves the defects of coarse temperature control and high energy consumption in existing control methods, and helps to better adapt to constantly changing environmental conditions and user needs, achieving more refined and efficient temperature management.

[0029] In some embodiments, the process of selecting target operating state data from first candidate operating state data based on target temperature and current indoor and outdoor environmental characteristic data includes: predicting the energy consumption corresponding to each first candidate operating state data based on current indoor and outdoor environmental characteristic data to obtain predicted energy consumption corresponding to each first candidate operating state data; predicting the indoor temperature corresponding to each first candidate operating state data based on current indoor and outdoor environmental characteristic data to obtain predicted temperature corresponding to each first candidate operating state data; selecting each first candidate operating state data based on target temperature and each predicted temperature to obtain multiple second candidate operating state data; and determining target operating state data from each second candidate operating state data based on predicted energy consumption corresponding to each second candidate operating state data.

[0030] In some embodiments, by combining current indoor and outdoor environmental characteristic data and data of each first candidate operating state, the energy consumption of the first preset time period corresponding to each first candidate operating state data is predicted to obtain the predicted energy consumption of the next preset time period corresponding to each first candidate operating state data. This evaluates the energy consumption under different operating states and provides a basis for subsequent selection. The next preset time period can be the next hour. By combining current indoor and outdoor environmental characteristic data and data of each first candidate operating state, the median indoor temperature of each preset time period corresponding to each first candidate operating state data is predicted to obtain the median indoor temperature of the next preset time period corresponding to each first candidate operating state data. This evaluates the change in indoor temperature under different operating states to ensure that the finally selected operating state can meet the target temperature requirements. Each predicted temperature is compared with the target temperature, and first candidate operating state data with predicted temperatures close to the target temperature are selected, thereby helping the selected operating state to achieve the expected temperature control. Among the selected second candidate operating state data, the second candidate operating state data with the lowest energy consumption is selected as the target operating state data, so that energy consumption is as low as possible while meeting temperature control requirements. By selecting target operating state data from various first candidate operating state data based on target temperature and current indoor and outdoor environmental characteristic data, precise temperature control and effective reduction of energy consumption can be achieved. The method provided in this disclosure improves the accuracy of temperature control, reduces energy consumption, and enhances the responsiveness and adaptability of the temperature control system of the chiller plant equipment. This solves the problem that chiller plant equipment cannot precisely control temperature and reduce energy consumption in the prior art, better meets user needs, improves energy utilization efficiency, and achieves sustainable development goals.

[0031] In some embodiments, based on current indoor and outdoor environmental feature data, the energy consumption corresponding to each first candidate operating state data is predicted to obtain the predicted energy consumption corresponding to each first candidate operating state data, including: inputting the current indoor and outdoor environmental feature data and each first candidate operating state data as a set of data into the energy consumption prediction model to obtain the predicted energy consumption in the next time period corresponding to each first candidate operating state data output by the energy consumption prediction model.

[0032] In some embodiments, the energy consumption prediction model is a prediction model trained using machine learning algorithms based on historical indoor and outdoor environmental characteristic data and historical operating status data of the chiller equipment. The energy consumption prediction model can fit the relationship between the indoor and outdoor environmental characteristic data, the operating status data of the chiller equipment, and the actual energy consumption demand. It can predict energy consumption in the next time period based on the input data, providing predicted values ​​for energy consumption under different operating conditions. Each first candidate operating state data is combined with the current indoor and outdoor environmental characteristic data to form a set of data, which is then input into the energy consumption prediction model. The energy consumption prediction model outputs the predicted energy consumption for each first candidate operating state data in the next time period, providing predicted energy consumption values ​​for different operating conditions and providing a basis for subsequent decision-making. By predicting energy consumption under different operating conditions, the operating state that is closest to the target temperature and has the lowest energy consumption can be found.

[0033] In some embodiments, based on the current indoor and outdoor environmental feature data, the indoor temperature corresponding to each first candidate operating state data is predicted to obtain the predicted temperature corresponding to each first candidate operating state data, including: inputting the current indoor and outdoor environmental feature data and each first candidate operating state data as a set of data into the temperature prediction model to obtain the predicted indoor temperature for the next time period corresponding to each first candidate operating state data output by the temperature prediction model.

[0034] In some embodiments, the temperature prediction model is a prediction model trained using machine learning algorithms based on historical indoor and outdoor environmental characteristic data and historical operating status data of the chiller plant equipment. The temperature prediction model can fit the relationship between the indoor and outdoor environmental characteristic data, the operating status data of the chiller plant equipment, and the actual temperature. It can predict the temperature in the next time period based on the input data, providing predicted values ​​for temperatures under different operating conditions. Each first candidate operating state data point is combined with the current indoor and outdoor environmental characteristic data to form a set of data, which is then input into the temperature prediction model. The temperature prediction model outputs the predicted temperature for each first candidate operating state data point in the next time period, providing predicted temperature values ​​for different operating conditions and providing a basis for subsequent decision-making. By predicting the indoor temperature under different operating conditions, the operating state closest to the target temperature can be found, achieving refined temperature control.

[0035] In some embodiments, based on the target temperature and each predicted temperature, each first candidate operating state data is filtered to obtain multiple second candidate operating state data, including: calculating the absolute value of the difference between each predicted temperature and the target temperature, and determining the first candidate operating state data corresponding to the absolute value of each difference that is less than a first preset value as the second candidate operating state data.

[0036] Specifically, the first preset value is an acceptable temperature deviation range used to filter operating states that are close to the target temperature. The first preset value can be adjusted according to actual needs to achieve the best control effect. The difference between each predicted temperature and the target temperature is calculated, and the absolute value of the difference is taken. The absolute value of the difference is used to quantify the gap between each first candidate operating state data and the target operating state data. The first candidate operating state data whose absolute value of the difference is less than the first preset value is determined as the second candidate operating state data. By filtering out the second candidate operating state data whose predicted temperature is close to the target temperature, the selection range is effectively narrowed, and the operating states that can meet the temperature control requirements are retained, laying the foundation for the subsequent selection of the operating state with the lowest energy consumption.

[0037] In some embodiments, determining the target operating state data from the predicted energy consumption corresponding to each second candidate operating state data includes: determining the second candidate operating state data corresponding to the predicted energy consumption with the smallest value as the target operating state data based on the predicted energy consumption corresponding to each second candidate operating state data.

[0038] In some embodiments, the predicted energy consumption corresponding to each second candidate operating state data is compared, and the second candidate operating state data corresponding to the predicted energy consumption with the smallest value is determined as the target operating state data, so that the selected target operating state data can meet the temperature control requirements and achieve the lowest energy consumption.

[0039] In some embodiments, the current indoor and outdoor environmental characteristic data includes the current indoor temperature, and the current operating status data includes the current number of chillers, the current chiller set temperature, and the current chilled pump frequency of the chiller station equipment. Based on the target temperature and the indoor and outdoor environmental characteristic data, the current operating status data is adjusted to obtain multiple first candidate operating status data of the chiller station equipment, including: determining the adjustment step size corresponding to the current number of chillers, the current chiller set temperature, and the current chilled pump frequency according to the current indoor temperature and the target temperature; adjusting at least one of the current number of chillers, the current chiller set temperature, and the current chilled pump frequency according to the preset adjustment step size corresponding to the current number of chillers, the current chiller set temperature, and the current chilled pump frequency to obtain multiple first candidate operating status data of the chiller station equipment, so that the predicted temperature corresponding to the first candidate operating status data approaches the target temperature.

[0040] In some embodiments, based on the difference between the current indoor temperature and the target temperature, adjustment step sizes are determined for the current number of chillers, the current chiller set temperature, and the current chiller pump frequency, respectively. Quantifying the adjustment magnitude helps to ensure that the adjusted operating state better approximates the target temperature. Adjustments are made to at least one of the current number of chillers, the current chiller set temperature, and the current chiller pump frequency according to the determined adjustment step size. This adjustment can be a single parameter adjustment or a combination of multiple parameter adjustments, generating multiple first candidate operating state data. Different operating state options are created for subsequent screening and evaluation, providing diverse selection schemes for subsequent selection and optimization. The generation of multiple first candidate operating state data increases the possibilities when selecting the optimal operating state, thus making it easier to find an operating state that meets both temperature control requirements and low energy consumption. Multiple first candidate operating state data represent different operating states, each corresponding to a predicted temperature that should approach the target temperature. For example, if the target temperature is 26 degrees Celsius, the current time is 9:00 AM, and the current operating status data shows two chillers are running, with a set temperature of 7.6 degrees Celsius and a frequency converter speed of 45, and the current indoor temperature in the mall is 25.6 degrees Celsius, this indicates that too many chillers are running. The corresponding strategy search space for the next hour is: chiller range: 2 units, 1.5 units, 1 unit; chiller set temperature range: 7.1–9.0 degrees Celsius; frequency converter range: 40–50. By combining candidate operating status data based on the number of chillers, temperature, and frequency converter speed, and inputting this data into energy consumption prediction and temperature prediction models, the temperature and energy consumption for the next hour are predicted, generating the corresponding first candidate operating status data result table. (Reference) Figure 2 and Figure 3 , Figure 2 and Figure 3 All are first candidate operating status data result tables. Each row of the result table can be split into multiple rows according to the set temperature and frequency conversion number.

[0041] In some embodiments, obtaining current indoor and outdoor environmental feature data includes: obtaining multiple initial indoor temperatures within the current time period and outdoor weather for the next time period; selecting the median from the initial indoor temperatures within the current time period as the current indoor temperature; encoding the outdoor weather for the next time period to obtain a feature vector of the outdoor weather for the next time period; and determining the feature vector of the current indoor temperature and the outdoor weather for the next time period as indoor and outdoor environmental feature data.

[0042] In some embodiments, indoor temperature data can be collected within a set time period (e.g., 1 hour) using an indoor temperature sensor. The temperature sensor can collect data every 5 minutes, obtaining multiple initial indoor temperatures. The initial indoor temperatures in previous time periods can reflect the changes in indoor temperature in the current time period. The collected initial indoor temperature data are sorted, and the median is selected as the current indoor temperature based on the number of data points. By selecting the median, the influence of extreme values ​​on indoor temperature assessment can be effectively reduced, making the current indoor temperature more representative and stable. This helps the chiller station equipment to more accurately determine the current indoor temperature conditions, thereby enabling more precise temperature control. Outdoor weather for the next time period can be obtained from weather forecasts. The outdoor weather for the next time period is encoded, converting the outdoor weather (e.g., rain, snow, sunny) and weather parameters (e.g., temperature, humidity, wind speed) into numerical or symbolic forms to obtain a feature vector of the outdoor weather for the next time period. This transforms complex weather information into a feature vector that is easy to process and analyze, which helps in subsequent input into the prediction model.

[0043] In some embodiments, multiple initial indoor temperatures within the current time period and outdoor weather for the next time period are considered as initial characteristic data of the current indoor and outdoor environment. Obtaining the initial characteristic data of the current indoor and outdoor environment and the initial characteristic data of the current operating status of the chiller plant equipment requires preprocessing the initial characteristic data to ensure data quality and usability, providing high-quality input data for subsequent prediction models. Only after obtaining the corresponding current indoor and outdoor environmental characteristic data and the current operating status data of the chiller plant equipment can these be input into the temperature prediction model and the energy consumption prediction model. Preprocessing may also include: adjusting the chiller's operating status, processing the collected energy consumption data, and adjusting the chiller's status to off if it is on and has negative or low energy consumption, and vice versa, to ensure that the chiller's operating status is consistent with the energy consumption data; removing low-energy-consumption samples, such as those caused by equipment failure, data acquisition errors, or extreme atypical conditions (e.g., the chiller is briefly turned on but consumes almost no energy), which helps reduce noise data; constructing date and time features, as time-related features (such as whether it is a holiday, whether it is a work-rest day, the number of days until the holiday, the number of days until the summer solstice, business hours, opening and closing times, etc.) have a significant impact on energy consumption, and constructing date and time features helps to predict energy consumption more accurately; and calculating wet-bulb temperature, which can more comprehensively reflect the human body's thermal sensation to the environment. As an additional feature, it helps the prediction model to more accurately understand the indoor environmental conditions, thereby improving prediction accuracy; exploratory data analysis (EDA) is performed on indoor temperature and humidity to identify outliers in the data, and outliers are filtered and the data is cleaned to ensure data accuracy and reliability; indoor-outdoor temperature difference features and chiller equipment temperature difference features are constructed. These features are directly related to changes in energy consumption. The indoor-outdoor temperature difference can reflect the magnitude of the building's heat load, while the chiller equipment temperature difference features can reflect cooling efficiency. Inputting these features into the prediction model helps the model capture the direct impact of environmental changes on energy consumption and temperature; skewed features are processed. Skewed features (such as extreme values, skewed distributions, etc.) can adversely affect the training and calculation of the prediction model. Through logarithmic transformation, normalization, or truncation, the distribution of skewed features can be improved, making the prediction easier to understand and improving the stability and generalization ability of the prediction model. By performing the above data preprocessing steps—cleaning data, constructing useful features, and handling outliers and skewed features—the quality and usability of the data input into the prediction model can be effectively improved, and the prediction accuracy and robustness of the model can be enhanced.

[0044] In some embodiments, the current indoor and outdoor environmental characteristic data and each first candidate operating status data are input into the energy consumption prediction model as a set of data. The method further includes: acquiring historical indoor and outdoor environmental characteristic data and historical operating status data of the chiller equipment; using the historical indoor and outdoor environmental characteristic data and historical operating status data as first training samples, and using the historical energy consumption corresponding to the historical operating status data as the label of the first training samples, to construct an energy consumption prediction training set and an energy consumption prediction test set; training multiple candidate energy consumption prediction models to be trained based on the energy consumption prediction training set, to obtain multiple trained candidate energy consumption prediction models; and selecting the candidate energy consumption prediction model with the smallest loss value from among the multiple candidate energy consumption prediction models based on the loss values ​​corresponding to each candidate energy consumption prediction model, and determining it as the energy consumption prediction model.

[0045] In some embodiments, historical indoor and outdoor environmental characteristic data (such as temperature, humidity, light intensity, etc.) and historical operating status data of chiller equipment (such as equipment on / off status, operating power, working duration, etc.) are acquired. This historical data forms the basis for subsequent model training. The historical data is split into a training set (energy consumption prediction training set) and an energy consumption prediction test set. The energy consumption prediction training set is used to train the candidate energy consumption prediction model to learn the inherent patterns and regularities of the data. The energy consumption prediction test set is used to evaluate the performance of the trained candidate energy consumption prediction model on unseen data to test its generalization ability. The label (i.e., historical energy consumption) is the target value that the candidate energy consumption prediction model needs to predict. Multiple candidate energy consumption prediction models are trained based on the energy consumption prediction training set. These models can be linear regression, decision trees, random forests, neural networks, etc. Training multiple candidate models provides alternative solutions for subsequent model selection, ultimately finding the most suitable energy consumption prediction model for the current situation. Multiple candidate energy consumption prediction models were tested using an energy consumption prediction test set, and the loss values ​​corresponding to each candidate model were obtained. Based on these loss values, the candidate model with the smallest loss value was selected as the final energy consumption prediction model. The candidate model with the best prediction performance was then chosen as the final energy consumption prediction model. Specifically, the aforementioned losses can be the root mean square error (RMSE) or the mean absolute error (MAE).

[0046] In some embodiments, when using historical indoor environmental feature data and historical operating status data as the first training samples, a Sequential Floating Forward Selection (SFFS) method can be used to construct each first training sample. Specifically, the historical indoor and outdoor environmental feature data and the historical operating status data of the chiller plant equipment may include: historical indoor temperature, historical outdoor temperature, historical humidity, historical light intensity, historical number of cooling towers, historical number of chilled pumps, historical chilled pump frequency, historical number of chillers, and historical chiller set temperature. Initialization is performed with an empty feature set. One feature, such as historical outdoor temperature, is selected from all features, and a floating operation is performed. Indicators such as cross-validation error can be used to determine whether removing historical outdoor temperature would improve the performance of the energy consumption prediction model. If not, historical outdoor temperature is retained, and forward selection is performed. The next feature, such as historical indoor temperature, is selected from the remaining features. Indicators such as cross-validation error can be used to determine whether removing historical indoor temperature or historical outdoor temperature would improve the performance of the energy consumption prediction model. If not, it is retained, and this process continues until no more features can be added or removed to further improve the performance of the energy consumption prediction model. The optimal first training sample that can be determined through SFFS is the optimal energy-efficient training set.

[0047] In some embodiments, before inputting the current indoor and outdoor environmental feature data and each first candidate operating status data into the temperature prediction model, the method further includes: acquiring historical indoor and outdoor environmental feature data and historical operating status data of the chiller equipment; using the historical indoor and outdoor environmental feature data and historical operating status data as first training samples, and using the historical temperature corresponding to the historical operating status data as the label of the first training samples to construct a temperature prediction training set and a temperature prediction test set; training multiple candidate temperature prediction models to be trained based on the temperature prediction training set to obtain multiple trained candidate temperature prediction models; and selecting the candidate temperature prediction model with the smallest loss value from the multiple candidate temperature prediction models based on the loss values ​​corresponding to the multiple candidate temperature prediction models to determine as the temperature prediction model.

[0048] All of the above-mentioned optional technical solutions can be combined in any way to form optional embodiments of this disclosure, and will not be described in detail here.

[0049] The following are embodiments of the apparatus disclosed herein, which can be used to execute embodiments of the method disclosed herein. For details not disclosed in the apparatus embodiments of this disclosure, please refer to the embodiments of the method disclosed herein.

[0050] Figure 4 This is a schematic diagram of an indoor temperature control device provided in an embodiment of this disclosure. Figure 4 As shown, the indoor temperature control device includes:

[0051] Data acquisition module 401 is used to acquire current indoor and outdoor environmental characteristic data, current operating status data of chiller station equipment, and target temperature;

[0052] The adjustment module 402 is used to adjust the current operating status data based on the target temperature and indoor and outdoor environmental characteristic data to obtain multiple first candidate operating status data of the chiller station equipment;

[0053] The filtering module 403 is used to filter target operating status data from the first candidate operating status data based on the target temperature and current indoor and outdoor environmental characteristic data; wherein the difference between the predicted temperature corresponding to the target operating status data and the target temperature is less than a first preset value, and the corresponding predicted energy consumption is the minimum value among the predicted energy consumption corresponding to the first candidate operating status data or the difference between the predicted energy consumption and the minimum value is less than a second preset value.

[0054] The execution module 404 is used to control the cooling plant equipment based on the target operating status data.

[0055] According to the technical solution provided in this disclosure, by acquiring current indoor and outdoor environmental characteristic data, current operating status data of the chiller equipment, and target temperature, a foundation is provided for subsequent analysis and decision-making. The indoor and outdoor environmental characteristic data and the current operating status data of the chiller equipment are important bases for formulating control strategies for the chiller equipment, i.e., candidate operating status data. The target temperature is the indoor temperature to be achieved. Based on the target temperature and indoor and outdoor environmental characteristic data, the current operating status of the chiller equipment is simulated and adjusted to generate multiple possible operating states (i.e., first candidate operating status data), providing multiple possibilities for subsequent screening. Based on the target temperature and current indoor and outdoor environmental characteristic data, target operating status data is obtained from multiple first candidate operating status data. The difference between the predicted temperature and the target temperature corresponding to the target operating status data is less than a first preset value, and the corresponding predicted energy consumption is the minimum value among the predicted energy consumption corresponding to the first candidate operating status data, or the difference between the predicted energy consumption and the minimum value is less than a second preset value. From multiple first candidate operating status data, target operating status data that can both meet temperature control requirements and achieve energy consumption optimization is selected, ensuring the effectiveness and economy of the control strategy. The final selected target operating status data is executed, and the chiller plant equipment is controlled according to the target operating status data to ensure that the indoor temperature reaches the target temperature. The temperature control method proposed in this disclosure significantly improves the accuracy of temperature control and energy utilization efficiency of chiller plant equipment through real-time data collection, multi-scheme simulation, dual-objective optimization of energy consumption and temperature, and dynamic adjustment control. It solves the defects of coarse temperature control and high energy consumption in existing control methods, and helps to better adapt to constantly changing environmental conditions and user needs, achieving more refined and efficient temperature management.

[0056] In some embodiments, the filtering module 403 is configured to predict the energy consumption corresponding to each first candidate operating state data based on the current indoor and outdoor environmental feature data, to obtain the predicted energy consumption corresponding to each first candidate operating state data; predict the indoor temperature corresponding to each first candidate operating state data based on the current indoor and outdoor environmental feature data, to obtain the predicted temperature corresponding to each first candidate operating state data; filter each first candidate operating state data based on the target temperature and each predicted temperature, to obtain multiple second candidate operating state data; and determine the target operating state data from each second candidate operating state data based on the predicted energy consumption corresponding to each second candidate operating state data.

[0057] In some embodiments, the filtering module 403 is configured to input the current indoor and outdoor environmental feature data and each first candidate operating status data as a set of data into the energy consumption prediction model to obtain the predicted energy consumption in the next time period corresponding to each first candidate operating status data output by the energy consumption prediction model.

[0058] In some embodiments, the filtering module 403 is configured to input the current indoor and outdoor environmental feature data and each first candidate operating status data as a set of data into the temperature prediction model to obtain the predicted indoor temperature for the next time period corresponding to each first candidate operating status data output by the temperature prediction model.

[0059] In some embodiments, the filtering module 403 is configured to calculate the absolute value of the difference between each predicted temperature and the target temperature, and determine the first candidate operating state data corresponding to the absolute value of each difference that is less than a first preset value as the second candidate operating state data.

[0060] In some embodiments, the filtering module 403 is configured to determine the second candidate operating state data corresponding to the smallest predicted energy consumption as the target operating state data based on the predicted energy consumption corresponding to each second candidate operating state data.

[0061] In some embodiments, the current indoor and outdoor environmental characteristic data includes the current indoor temperature, and the current operating status data includes the current number of chillers, the current chiller set temperature, and the current chilled pump frequency of the chiller station equipment. The adjustment module 402 is configured to determine the adjustment step size corresponding to the current number of chillers, the current chiller set temperature, and the current chilled pump frequency respectively based on the current indoor temperature and the target temperature; and adjust at least one of the current number of chillers, the current chiller set temperature, and the current chilled pump frequency according to the preset adjustment step size corresponding to the current number of chillers, the current chiller set temperature, and the current chilled pump frequency to obtain multiple first candidate operating status data of the chiller station equipment, so that the predicted temperature corresponding to the first candidate operating status data approaches the target temperature.

[0062] In some embodiments, the data acquisition module 401 is configured to acquire multiple initial indoor temperatures within the current time period and outdoor weather for the next time period; select the median from the initial indoor temperatures within the current time period as the current indoor temperature; encode the outdoor weather for the next time period to obtain a feature vector of the outdoor weather for the next time period; and determine the feature vector of the current indoor temperature and the outdoor weather for the next time period as indoor and outdoor environmental feature data.

[0063] In some embodiments, before inputting the current indoor and outdoor environmental characteristic data and each first candidate operating status data as a set of data into the energy consumption prediction model, the indoor temperature control device is configured to acquire historical indoor and outdoor environmental characteristic data and historical operating status data of the chiller equipment; use the historical indoor and outdoor environmental characteristic data and historical operating status data as first training samples, and use the historical energy consumption corresponding to the historical operating status data as the label of the first training samples to construct an energy consumption prediction training set and an energy consumption prediction test set; train multiple candidate energy consumption prediction models to be trained based on the energy consumption prediction training set to obtain multiple trained candidate energy consumption prediction models; and select the candidate energy consumption prediction model with the smallest loss value from the multiple candidate energy consumption prediction models based on the loss values ​​corresponding to the multiple candidate energy consumption prediction models to determine as the energy consumption prediction model.

[0064] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this disclosure.

[0065] Figure 5 This is a schematic diagram of the electronic device 5 provided in an embodiment of this disclosure. Figure 5 As shown, the electronic device 5 of this embodiment includes: a processor 501, a memory 502, and a computer program 503 stored in the memory 502 and executable on the processor 501. When the processor 501 executes the computer program 503, it implements the steps in the various method embodiments described above. Alternatively, when the processor 501 executes the computer program 503, it implements the functions of each module / unit in the various device embodiments described above.

[0066] Electronic device 5 can be a desktop computer, laptop, handheld computer, cloud server, or other electronic device. Electronic device 5 may include, but is not limited to, processor 501 and memory 502. Those skilled in the art will understand that... Figure 5 This is merely an example of electronic device 5 and does not constitute a limitation on electronic device 5. It may include more or fewer components than shown, or different components.

[0067] The processor 501 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0068] The memory 502 can be an internal storage unit of the electronic device 5, such as a hard disk or RAM of the electronic device 5. The memory 502 can also be an external storage device of the electronic device 5, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, etc., equipped on the electronic device 5. The memory 502 can also include both internal and external storage units of the electronic device 5. The memory 502 is used to store computer programs and other programs and data required by the electronic device.

[0069] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0070] If integrated modules / units are implemented as software functional units and sold or used as independent products, they can be stored in a readable storage medium (e.g., a computer-readable storage medium). Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program may include computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. A computer-readable storage medium may include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0071] The above embodiments are only used to illustrate the technical solutions of this disclosure, and are not intended to limit it. Although this disclosure has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this disclosure, and should all be included within the protection scope of this disclosure.

Claims

1. An indoor temperature control method, characterized in that, include: Acquire current indoor and outdoor environmental characteristics data, current operating status data of chiller station equipment, and target temperature; Based on the target temperature and the indoor and outdoor environmental characteristic data, the current operating status data is adjusted to obtain multiple first candidate operating status data of the chiller station equipment; the current indoor and outdoor environmental characteristic data includes the current indoor temperature, and the current operating status data includes the current number of chillers, the current chiller set temperature, and the current refrigeration pump frequency of the chiller station equipment; Based on the target temperature and the current indoor and outdoor environmental characteristic data, target operating status data is obtained by filtering from the first candidate operating status data; wherein the difference between the predicted temperature corresponding to the target operating status data and the target temperature is less than a first preset value, and the corresponding predicted energy consumption is the minimum value among the predicted energy consumption corresponding to the first candidate operating status data or the difference between the predicted energy consumption and the minimum value is less than a second preset value. The cooling plant equipment is controlled based on the target operating status data; Based on the target temperature and the indoor and outdoor environmental characteristic data, the current operating status data is adjusted to obtain multiple first candidate operating status data for the chiller station equipment, including: Based on the current indoor temperature and the target temperature, determine the adjustment step size corresponding to the current number of chillers, the current chiller set temperature, and the current refrigeration pump frequency, respectively. Based on the preset adjustment step size corresponding to the current number of chillers, the current chiller set temperature, and the current chilled pump frequency, at least one of the current number of chillers, the current chiller set temperature, and the current chilled pump frequency is adjusted to obtain multiple first candidate operating status data of the chiller station equipment, so that the predicted temperature corresponding to the first candidate operating status data approaches the target temperature. The step of filtering target operating status data from the first candidate operating status data based on the target temperature and the current indoor and outdoor environmental characteristic data includes: Based on the current indoor and outdoor environmental feature data, the energy consumption corresponding to each of the first candidate operating state data is predicted to obtain the predicted energy consumption corresponding to each of the first candidate operating state data. Based on the current indoor and outdoor environmental feature data, the indoor temperature corresponding to each of the first candidate operating state data is predicted to obtain the predicted temperature corresponding to each of the first candidate operating state data. Based on the target temperature and each of the predicted temperatures, each of the first candidate operating state data is filtered to obtain multiple second candidate operating state data. Based on the predicted energy consumption corresponding to each second candidate operating state data, the target operating state data is determined from each second candidate operating state data.

2. The method according to claim 1, characterized in that, The step of predicting the energy consumption corresponding to each of the first candidate operating state data based on the current indoor and outdoor environmental feature data, to obtain the predicted energy consumption corresponding to each of the first candidate operating state data, includes: The current indoor and outdoor environmental feature data and each of the first candidate operating status data are respectively input into the energy consumption prediction model as a set of data to obtain the predicted energy consumption in the next time period corresponding to each of the first candidate operating status data output by the energy consumption prediction model. The step of predicting the indoor temperature corresponding to each of the first candidate operating state data based on the current indoor and outdoor environmental feature data, and obtaining the predicted temperature corresponding to each of the first candidate operating state data, includes: The current indoor and outdoor environmental feature data and each of the first candidate operating status data are respectively input into the temperature prediction model as a set of data to obtain the predicted indoor temperature for the next time period corresponding to each of the first candidate operating status data output by the temperature prediction model.

3. The method according to claim 1, characterized in that, Based on the target temperature and each of the predicted temperatures, the first candidate operating state data is filtered to obtain multiple second candidate operating state data, including: Calculate the absolute value of the difference between each of the predicted temperatures and the target temperature, and determine the first candidate operating state data corresponding to the absolute value of each difference that is less than the first preset value as the second candidate operating state data; The step of determining the target operating state data from the predicted energy consumption corresponding to each second candidate operating state data includes: Based on the predicted energy consumption corresponding to each of the second candidate operating state data, the second candidate operating state data corresponding to the predicted energy consumption with the smallest value is determined as the target operating state data.

4. The method according to claim 1, characterized in that, The acquisition of current indoor and outdoor environmental feature data includes: Get multiple initial indoor temperatures for the current time period and outdoor weather for the next time period; The median of the initial indoor temperatures within the current time period is selected as the current indoor temperature. The outdoor weather for the next time period is encoded to obtain the feature vector of the outdoor weather for the next time period. The feature vectors of the current indoor temperature and the outdoor weather for the next time period are determined as the indoor and outdoor environmental feature data.

5. The method according to claim 2, characterized in that, Before inputting the current indoor and outdoor environmental characteristic data and each of the first candidate operating status data as a set of data into the energy consumption prediction model, the method further includes: Acquire historical indoor and outdoor environmental characteristic data and historical operating status data of the cooling station equipment; The historical indoor environmental feature data and the historical operating status data are used as the first training samples, and the historical energy consumption corresponding to the historical operating status data is used as the label of the first training sample to construct an energy consumption prediction training set and an energy consumption prediction test set. Based on the energy consumption prediction training set, multiple candidate energy consumption prediction models to be trained are trained respectively to obtain multiple trained candidate energy consumption prediction models. Based on the loss values ​​corresponding to multiple candidate energy consumption prediction models, the candidate energy consumption prediction model with the smallest loss value is selected from the multiple candidate energy consumption prediction models and determined as the energy consumption prediction model.

6. An indoor temperature control device, characterized in that, include: The data acquisition module is used to acquire current indoor and outdoor environmental characteristic data, current operating status data of the chiller station equipment, and target temperature; The adjustment module is used to adjust the current operating status data based on the target temperature and the indoor and outdoor environmental characteristic data to obtain multiple first candidate operating status data of the chiller station equipment; the current indoor and outdoor environmental characteristic data includes the current indoor temperature, and the current operating status data includes the current number of chillers, the current chiller set temperature, and the current refrigeration pump frequency of the chiller station equipment; The filtering module is used to filter target operating status data from the first candidate operating status data based on the target temperature and the current indoor and outdoor environmental characteristic data; wherein the difference between the predicted temperature corresponding to the target operating status data and the target temperature is less than a first preset value, and the corresponding predicted energy consumption is the minimum value among the predicted energy consumption corresponding to the first candidate operating status data or the difference between the predicted energy consumption and the minimum value is less than a second preset value. An execution module is used to control the cooling plant equipment based on the target operating status data; The adjustment module is specifically used to: determine the adjustment step size corresponding to the current number of chillers, the current chiller set temperature, and the current chilled pump frequency based on the current indoor temperature and the target temperature; adjust at least one of the current number of chillers, the current chiller set temperature, and the current chilled pump frequency according to the preset adjustment step size corresponding to the current number of chillers, the current chiller set temperature, and the current chilled pump frequency, to obtain multiple first candidate operating status data of the chiller station equipment, so that the predicted temperature corresponding to the first candidate operating status data approaches the target temperature; The filtering module is specifically used to: predict the energy consumption corresponding to each of the first candidate operating state data based on the current indoor and outdoor environmental feature data, and obtain the predicted energy consumption corresponding to each of the first candidate operating state data; Based on the current indoor and outdoor environmental feature data, the indoor temperature corresponding to each of the first candidate operating state data is predicted to obtain the predicted temperature corresponding to each of the first candidate operating state data; based on the target temperature and each of the predicted temperatures, each of the first candidate operating state data is filtered to obtain multiple second candidate operating state data. Based on the predicted energy consumption corresponding to each second candidate operating state data, the target operating state data is determined from each second candidate operating state data.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 5.

8. A readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 5.

Images