Air conditioner energy-saving control system and method

Abstract

The invention relates to the technical field of air conditioner control, in particular to an air conditioner energy-saving control system and method, multiple factor data influencing the cooling capacity of a water chilling unit are collected in real time through the Internet of Things technology, cooling capacity prediction is conducted through machine learning or a statistical prediction model, and the cooling capacity requirement of the water chilling unit in a period of time in the future is reflected more accurately; prediction precision is improved, collected data are preprocessed, data quality and processing efficiency are improved, the preprocessed data are stored through a distributed database or a cloud storage technology, rapid access and efficient management of the data are achieved, meanwhile, the data processing speed can be increased through distributed calculation, the system response capacity can be improved, and on the basis of a cooling capacity prediction result, the system reliability is improved. An air conditioner energy-saving control scheme is formulated in advance, reasonable distribution and utilization of energy are achieved, the energy consumption of an air conditioner system is reduced, and the difficulty and cost of data collection and processing are effectively reduced through improvement in the aspects of data collection optimization, data preprocessing, data storage and the like.

Description

Technical Field

[0001] The present invention relates to the technical field of air conditioning control, and in particular to an air conditioning energy-saving control system and method. Background Art

[0002] In the prior art, when performing air conditioning energy-saving control, the influencing factors are generally input into the air conditioning cooling load prediction model, and the cooling load demanded by the air conditioner is predicted. The central air conditioner is adjusted according to the predicted cooling load, thereby achieving the purpose of energy saving. However, the system needs to keep operating at all times, which consumes a lot of power and has a poor energy-saving effect.

[0003] The existing announcement number CN117928052B discloses a central air-conditioning energy-saving control method and system. By predicting the values ​​of influencing factors that affect the cooling capacity of the central air-conditioning chiller, and then inputting the predicted values ​​into the cooling capacity prediction model, the central air-conditioning energy-saving control plan can be determined in advance; avoiding the situation where the energy-saving system keeps calculating all the time, making the central air-conditioning energy-saving effect better; at the same time, when predicting the values ​​of influencing factors that affect the cooling capacity of the central air-conditioning chiller, the predicted values ​​of the influencing factors are calculated. For influencing factors with large fluctuations, the values ​​of the influencing factors with a smaller prediction range are selected, and for influencing factors with smaller fluctuations, the values ​​of the influencing factors with a larger prediction range are selected. Through the above steps, the accuracy of the influencing factor prediction results can be improved, thereby improving the accuracy of subsequent central air-conditioning energy-saving control.

[0004] However, in order to establish and maintain a high-precision prediction model, the above-mentioned central air-conditioning energy-saving control method and system need to collect a large amount of high-quality data, including data on various factors such as ambient temperature, humidity, chiller operating parameters, building load changes, etc. The collection, storage, cleaning and preprocessing of data are complex and costly. Summary of the invention

[0005] The object of the present invention is to provide an air conditioning energy-saving control system and method, which solves the problems of complex and costly data collection, storage, cleaning and preprocessing in existing central air conditioning energy-saving control methods.

[0006] To achieve the above object, the present invention provides an air conditioning energy-saving control method, comprising the following steps:

[0007] The Internet of Things technology is used to collect data on various factors that affect the cooling capacity of air-conditioning chillers in real time. The collected data is pre-processed using data cleaning, deduplication, conversion and integration technologies, and the pre-processed data is stored using distributed databases or cloud storage technologies.

[0008] Based on the preprocessed data, machine learning or statistical prediction models are used to predict the factors that affect the cooling capacity of the air-conditioning chiller;

[0009] Input the predicted influencing factor values ​​into the cooling capacity prediction model, calculate and predict the cooling capacity demand of the chiller in the future according to the input values, and formulate the air conditioning energy-saving control plan in advance based on the cooling capacity prediction results;

[0010] Implement corresponding control measures according to the formulated energy-saving control plan, and monitor the operating status and energy consumption of the air-conditioning system in real time.

[0011] Among them, the data of various factors affecting the cooling capacity of the air-conditioning chiller are collected in real time through the Internet of Things technology, the collected data are pre-processed by using data cleaning, deduplication, conversion and integration technology, and the pre-processed data are stored by using a distributed database or cloud storage technology. The steps also include:

[0012] Sensors are used to collect data on various factors that affect the cooling capacity of air-conditioning chillers, including outdoor temperature, outdoor humidity, and sunlight radiation intensity;

[0013] The collected data is transmitted via wireless communication technology.

[0014] Among them, the data of various factors affecting the cooling capacity of the air-conditioning chiller are collected in real time through the Internet of Things technology, the collected data are pre-processed by using data cleaning, deduplication, conversion and integration technology, and the pre-processed data are stored by using a distributed database or cloud storage technology. The steps also include:

[0015] Identify and delete outliers due to sensor failures and data transmission errors;

[0016] For missing data, choose to fill or delete according to the specific situation;

[0017] Check and correct obvious errors in the data;

[0018] Identify and remove duplicate data records;

[0019] Convert data from different sources and formats into a unified format;

[0020] Normalize or standardize numerical data;

[0021] Integrate the cleaned, deduplicated, and converted data into a unified dataset to form a complete dataset, and then split the dataset into multiple data blocks according to certain rules.

[0022] Among them, the data of various factors affecting the cooling capacity of the air-conditioning chiller are collected in real time through the Internet of Things technology, the collected data are pre-processed by using data cleaning, deduplication, conversion and integration technology, and the pre-processed data are stored by using a distributed database or cloud storage technology. The steps also include:

[0023] Data blocks are replicated to different nodes through a redundant storage mechanism.

[0024] Among them, the data of various factors affecting the cooling capacity of the air-conditioning chiller are collected in real time through the Internet of Things technology, the collected data are pre-processed by using data cleaning, deduplication, conversion and integration technology, and the pre-processed data are stored by using a distributed database or cloud storage technology. The steps also include:

[0025] Data blocks are distributed and stored on different nodes according to the characteristics and access patterns of the data, and balanced distribution of data blocks is achieved through a load balancing mechanism.

[0026] Among them, the data of various factors affecting the cooling capacity of the air-conditioning chiller are collected in real time through the Internet of Things technology, the collected data are pre-processed by using data cleaning, deduplication, conversion and integration technology, and the pre-processed data are stored by using a distributed database or cloud storage technology. The steps also include:

[0027] The metadata information of data blocks is maintained through a distributed metadata management mechanism, including storage location, replication status and access control.

[0028] An air conditioning energy-saving control system comprises a data module, a prediction module, a solution module and a control module, wherein the prediction module is connected to the data module, the solution module is connected to the prediction module, and the control module is connected to the solution module;

[0029] The data module is used to collect data on various factors that affect the cooling capacity of the air-conditioning chiller in real time through the Internet of Things technology, pre-process the collected data using data cleaning, de-duplication, conversion and integration technology, and store the pre-processed data using a distributed database or cloud storage technology;

[0030] The prediction module is used to predict various factors affecting the cooling capacity of the air-conditioning chiller based on the preprocessed data using machine learning or statistical prediction models;

[0031] The scheme module is used to input the predicted influencing factor values ​​into the cooling capacity prediction model, calculate and predict the cooling capacity demand of the chiller in the future according to the input values, and formulate the air conditioning energy-saving control scheme in advance based on the cooling capacity prediction results;

[0032] The control module is used to execute corresponding control measures according to the formulated energy-saving control plan, and monitor the operating status and energy consumption of the air-conditioning system in real time.

[0033] An air-conditioning energy-saving control system and method of the present invention, the Internet of Things technology can collect data on various factors that affect the cooling capacity of the chiller in real time, ensure the timeliness and accuracy of the data, and predict the cooling capacity based on the real-time collected data through machine learning or statistical prediction models, which can more accurately reflect the cooling capacity demand of the chiller in the future period of time and improve the prediction accuracy. The collected data is pre-processed by using data cleaning, de-duplication, conversion and integration technologies to improve data quality and processing efficiency. The pre-processed data is stored using a distributed database or cloud storage technology to achieve fast access to and efficient management of data. At the same time, distributed computing can speed up data processing and improve system responsiveness. Based on the cooling capacity prediction results, an air-conditioning energy-saving control plan is formulated in advance, such as adjusting the chilled water temperature, cooling water flow, etc., to achieve reasonable allocation and utilization of energy and reduce the energy consumption of the air-conditioning system. Through improvements in data collection optimization, data pre-processing and data storage, the difficulty and cost of data collection and processing are effectively reduced. These improvements not only improve the quality and availability of data, but also provide strong support for subsequent data analysis and energy-saving strategy formulation. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art are briefly introduced below.

[0035] Figure 1 It is a flowchart of the steps of the air conditioning energy-saving control method according to the first embodiment of the present invention.

[0036] Figure 2 It is a principle block diagram of an air conditioning energy-saving control system according to a second embodiment of the present invention.

[0037] In the figure: 201-data module, 202-prediction module, 203-scheme module, 204-control module. DETAILED DESCRIPTION

[0038] Embodiments of the present invention are described in detail below. Examples of the embodiments are shown in the accompanying drawings. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, but should not be construed as limiting the present invention.

[0039] The first embodiment of the present application is:

[0040] See also Figure 1 ,in, Figure 1 The present invention provides an air conditioning energy-saving control method, which includes the following steps:

[0041] S101: Use the Internet of Things technology to collect data on various factors that affect the cooling capacity of the air-conditioning chiller in real time, use data cleaning, deduplication, conversion and integration technology to pre-process the collected data, and use distributed database or cloud storage technology to store the pre-processed data;

[0042] Specifically, outdoor temperature data is measured and collected by an outdoor temperature sensor, outdoor humidity data is measured and collected by an outdoor humidity sensor, and solar radiation sensor measures and collects solar radiation intensity data. The solar radiation sensor usually adopts the photoelectric principle and uses high-precision photosensitive elements to measure the amount of solar radiation within the spectral range. It has a wide spectrum absorption capacity and can provide stable measurement results within the full spectrum range. Wireless communication technology is introduced to transmit the collected data, reduce wiring costs, and improve the flexibility and efficiency of data collection. The collected data is identified and outliers caused by sensor failures, data transmission errors, etc. are deleted. For missing data, filling (such as mean filling, interpolation method) or deletion is selected according to the specific situation. Obvious errors in the data, such as unreasonable data range, unit errors, etc., are checked and corrected, duplicate data records are identified and deleted to avoid deviations in subsequent analysis, and data from different sources and in different formats are converted into a unified format for subsequent processing. , normalize or standardize the numerical data, eliminate the dimension difference, improve the comparability of the data, integrate the cleaned, deduplicated and converted data into a unified data set to form a complete data set, and divide the data set into multiple data blocks according to certain rules. First, define a unified data structure or mode, including the fields, data types, constraints, etc. of the data table. This data structure can accommodate data from all sources and meet the needs of subsequent analysis and processing. Use database management systems or data processing tools, such as ETL tools, to merge data from different sources according to the defined data structure, including data field mapping, type conversion, data format adjustment and other operations. During or after the data merging process, perform data verification to ensure the integrity and consistency of the data, including checking whether the required fields have been filled in, whether the data type is correct, and whether the data value is within a reasonable range. The data can be segmented according to the distribution characteristics of the data. For example, if the data set contains geographic location information, the data can be segmented into different regional blocks according to the geographic location; if the data has time series characteristics, it can be segmented according to the time window. You can also split the data set into data blocks of equal or approximately equal size according to the needs of data storage and processing, which helps balance the workload of different nodes or processing units. You can also consider the access pattern of the data and put the data blocks that are often accessed together together to reduce the latency and overhead of cross-node access. Choose an appropriate split strategy based on actual needs and data characteristics. Use the split function provided by the database management system or data processing tool, or write a custom script to perform the split operation. The split operation may include physical movement of data, such as copying data to different files or database tables, or only logical division, such as setting a partition key. After the split is completed, verify the integrity and consistency of each data block to ensure that there is no data loss or duplication. At the same time, check whether the split result meets the expected split strategy and data access pattern.Distributed databases: such as Hadoop's HBase and Cassandra, which are suitable for the storage and query of large-scale data. Cloud storage: Utilize cloud storage services provided by cloud service providers, such as Alibaba Cloud, Tencent Cloud, AWS, etc., such as object storage (OSS), block storage, etc., to achieve flexible storage and access of data. Replicate data blocks to different nodes through redundant storage mechanisms to ensure high availability and fault tolerance of data. Store data blocks on different nodes according to the characteristics and access patterns of the data, and achieve balanced distribution of data blocks through load balancing mechanisms to improve data access efficiency and overall system performance. Maintain metadata information such as storage location, replication status, access control, etc. of data blocks through distributed metadata management mechanisms to ensure that the system can efficiently manage massive data. Realize real-time collection, preprocessing and efficient storage of data on various factors that affect the cooling capacity of central air-conditioning chillers, providing a solid data foundation for subsequent data analysis and optimization.

[0043] S102: Based on the preprocessed data, a machine learning or statistical prediction model is used to predict various factors that affect the cooling capacity of the air-conditioning chiller;

[0044] S103: inputting the predicted influencing factor values ​​into the cooling capacity prediction model, calculating and predicting the cooling capacity demand of the chiller in the future according to the input values, and formulating an air conditioning energy-saving control plan in advance based on the cooling capacity prediction results;

[0045] Specifically, the method disclosed in announcement number CN117928052B is adopted. First, a prediction model for predicting the influencing factors of the energy consumption of the air-conditioning chiller is established. The long short-term memory network model is used as the prediction model for predicting the influencing factors of the energy consumption of the air-conditioning chiller. A training set is obtained based on the preprocessed data. The training set is the hourly outdoor temperature data, outdoor humidity data and solar radiation intensity data of the prediction area in the past year. The three types of data for 6 consecutive hours are used as a data set to generate multiple data sets as training sets. The training set is used to train the prediction model to make the prediction model converge, and the values ​​of the influencing factors in the next m hours are predicted. In the prediction process, for the fluctuation For factors with greater influencing factors, a smaller prediction range is selected to reduce uncertainty; for factors with smaller fluctuations, a larger prediction range is selected to cover possible fluctuations, thereby improving the accuracy of the prediction results; the predicted values ​​of the influencing factors at m moments are input into the cooling capacity prediction model of the air-conditioning chiller to predict the cooling capacity of the air-conditioning chiller at m moments; wherein, the cooling capacity prediction model of the central air-conditioning chiller is a BP neural network model, the input of the BP neural network model is the value of the influencing factor at the moment to be predicted, and the output is the cooling capacity of the central air-conditioning chiller at the moment to be predicted; an air-conditioning energy-saving control plan is formulated for the central air-conditioning according to the cooling capacity of the central air-conditioning chiller at m moments.

[0046] S104: Execute corresponding control measures according to the formulated energy-saving control plan, and monitor the operating status and energy consumption of the air-conditioning system in real time.

[0047] Specifically, according to the energy-saving control scheme, adjust the set temperature of the air conditioner to a reasonable range. For example, set the temperature at 26℃ or higher in summer and between 18℃ and 20℃ in winter to avoid setting too low or too high temperature to cause energy waste. Reasonably adjust the humidity of the air conditioner according to the season and indoor environment. In summer, maintain the indoor humidity between 50% and 60% to improve human comfort and reduce energy consumption; in winter, control the indoor humidity between 40% and 50% to maintain indoor warmth. Turn off the air conditioner during the time period when the air conditioner is not needed, such as at night or when no one is working. Automatic control is achieved through time switches or intelligent control systems to reduce unnecessary energy consumption. Energy consumption monitoring equipment, such as electricity meters and energy consumption sensors, is installed in the air conditioning system to monitor the power consumption of the air conditioner in real time. The data collected by the monitoring equipment is transmitted to the data center for processing and analysis. The system can display the operating status and energy consumption of the air conditioning system in real time, and provide early warning and alarm functions. Regularly analyze the monitoring data to evaluate the implementation effect of the energy-saving control scheme. According to the data analysis results, the energy-saving control measures are adjusted and optimized to further improve the energy-saving performance of the air-conditioning system.

[0048] At this point, the Internet of Things technology can collect data on various factors that affect the cooling capacity of the chiller in real time to ensure the timeliness and accuracy of the data. Based on the real-time collected data, the cooling capacity is predicted through machine learning or statistical prediction models, which can more accurately reflect the cooling demand of the chiller in the future and improve the prediction accuracy. The collected data is pre-processed by using data cleaning, deduplication, conversion and integration technologies to improve data quality and processing efficiency. The pre-processed data is stored using distributed databases or cloud storage technologies to achieve fast data access and efficient management. At the same time, distributed computing can speed up data processing and improve system responsiveness. Based on the cooling capacity prediction results, air conditioning energy-saving control plans can be formulated in advance, such as adjusting the chilled water temperature, cooling water flow, etc., to achieve reasonable allocation and utilization of energy and reduce the energy consumption of the air conditioning system. Through improvements in data collection optimization, data preprocessing and data storage, the difficulty and cost of data collection and processing are effectively reduced. These improvements not only improve the quality and availability of data, but also provide strong support for subsequent data analysis and energy-saving strategy formulation.

[0049] The second embodiment of the present application is:

[0050] Based on the first embodiment, please refer to Figure 2 ,in, Figure 2 The air conditioning energy-saving control system of the second embodiment of the present invention comprises a data module 201 , a prediction module 202 , a solution module 203 and a control module 204 .

[0051] According to this specific implementation, the prediction module 202 is connected to the data module 201, the solution module 203 is connected to the prediction module 202, and the control module 204 is connected to the solution module 203;

[0052] The data module 201 is used to collect data on various factors that affect the cooling capacity of the air-conditioning chiller in real time through the Internet of Things technology, pre-process the collected data using data cleaning, de-duplication, conversion and integration technology, and use a distributed database or cloud storage technology to store the pre-processed data;

[0053] The prediction module 202 is used to predict various factors affecting the cooling capacity of the air-conditioning chiller based on the preprocessed data using machine learning or statistical prediction models;

[0054] The solution module 203 is used to input the predicted influencing factor values ​​into the cooling capacity prediction model, calculate and predict the cooling capacity demand of the chiller in the future according to the input values, and formulate the air conditioning energy-saving control plan in advance based on the cooling capacity prediction results;

[0055] The control module 204 is used to execute corresponding control measures according to the formulated energy-saving control plan, and monitor the operating status and energy consumption of the air-conditioning system in real time.

[0056] Using an air conditioning energy-saving control system of the present embodiment, the data module 201 can collect data of various factors affecting the cooling capacity of the chiller in real time through the Internet of Things technology to ensure the timeliness and accuracy of the data, and use data cleaning, deduplication, conversion and integration technology to pre-process the collected data to improve data quality and processing efficiency. Distributed database or cloud storage technology is used to store pre-processed data to achieve fast access and efficient management of data. At the same time, distributed computing can speed up data processing and improve system responsiveness. The prediction module 202 predicts cooling capacity based on real-time collected data through machine learning or statistical prediction models, which can more accurately reflect the cooling capacity demand of the chiller in the future and improve prediction accuracy. The solution module 203 formulates an air conditioning energy-saving control plan in advance based on the cooling capacity prediction result, and then the control module 204 performs control, such as adjusting the chilled water temperature, cooling water flow, etc., to achieve reasonable allocation and utilization of energy and reduce the energy consumption of the air conditioning system. Through improvements in data collection optimization, data pre-processing and data storage, the difficulty and cost of data collection and processing are effectively reduced. These improvements not only improve the quality and availability of data, but also provide strong support for subsequent data analysis and energy-saving strategy formulation.

[0057] What is disclosed above is only one or more preferred embodiments of the present application, and cannot be used to limit the scope of rights of the present application. Ordinary technicians in this field can understand that all or part of the processes of implementing the above embodiments and equivalent changes made according to the claims of the present application are still within the scope covered by the present application.

Claims

1. An air conditioning energy-saving control method, characterized in that: The following steps are involved: The Internet of Things technology is used to collect data on various factors that affect the cooling capacity of air-conditioning chillers in real time. The collected data is pre-processed using data cleaning, deduplication, conversion and integration technologies, and the pre-processed data is stored using distributed databases or cloud storage technologies. Based on the preprocessed data, machine learning or statistical prediction models are used to predict the factors that affect the cooling capacity of the air-conditioning chiller; Input the predicted influencing factor values ​​into the cooling capacity prediction model, calculate and predict the cooling capacity demand of the chiller in the future according to the input values, and formulate the air conditioning energy-saving control plan in advance based on the cooling capacity prediction results; Implement corresponding control measures according to the formulated energy-saving control plan, and monitor the operating status and energy consumption of the air-conditioning system in real time.

2. The air conditioning energy saving control method according to claim 1, characterized in that: The data of various factors affecting the cooling capacity of the air-conditioning chiller are collected in real time through the Internet of Things technology, the collected data are pre-processed by using data cleaning, deduplication, conversion and integration technology, and the pre-processed data are stored by using a distributed database or cloud storage technology. The steps also include: Sensors are used to collect data on various factors that affect the cooling capacity of air-conditioning chillers, including outdoor temperature, outdoor humidity, and sunlight radiation intensity; The collected data is transmitted via wireless communication technology.

3. The air conditioning energy saving control method according to claim 2, characterized in that: The data of various factors affecting the cooling capacity of the air-conditioning chiller are collected in real time through the Internet of Things technology, the collected data are pre-processed by using data cleaning, deduplication, conversion and integration technology, and the pre-processed data are stored by using a distributed database or cloud storage technology. The steps also include: Identify and delete outliers due to sensor failures and data transmission errors; For missing data, choose to fill or delete according to the specific situation; Check and correct obvious errors in the data; Identify and remove duplicate data records; Convert data from different sources and formats into a unified format; Normalize or standardize numerical data; Integrate the cleaned, deduplicated, and converted data into a unified dataset to form a complete dataset, and then split the dataset into multiple data blocks according to certain rules.

4. The air conditioning energy saving control method according to claim 3, characterized in that: The data of various factors affecting the cooling capacity of the air-conditioning chiller are collected in real time through the Internet of Things technology, the collected data are pre-processed by using data cleaning, deduplication, conversion and integration technology, and the pre-processed data are stored by using a distributed database or cloud storage technology. The steps also include: Data blocks are replicated to different nodes through a redundant storage mechanism.

5. The air conditioning energy saving control method according to claim 3, characterized in that: The data of various factors affecting the cooling capacity of the air-conditioning chiller are collected in real time through the Internet of Things technology, the collected data are pre-processed by using data cleaning, deduplication, conversion and integration technology, and the pre-processed data are stored by using a distributed database or cloud storage technology. The steps also include: Data blocks are distributed and stored on different nodes according to the characteristics and access patterns of the data, and balanced distribution of data blocks is achieved through a load balancing mechanism.

6. The air conditioning energy saving control method according to claim 3, characterized in that: The data of various factors affecting the cooling capacity of the air-conditioning chiller are collected in real time through the Internet of Things technology, the collected data are pre-processed by using data cleaning, deduplication, conversion and integration technology, and the pre-processed data are stored by using a distributed database or cloud storage technology. The steps also include: The metadata information of data blocks is maintained through a distributed metadata management mechanism, including storage location, replication status and access control.

7. An air conditioning energy-saving control system, applicable to the air conditioning energy-saving control method according to claim 1, characterized in that: It includes a data module, a prediction module, a solution module and a control module, wherein the prediction module is connected to the data module, the solution module is connected to the prediction module, and the control module is connected to the solution module; The data module is used to collect data on various factors that affect the cooling capacity of the air-conditioning chiller in real time through the Internet of Things technology, pre-process the collected data using data cleaning, de-duplication, conversion and integration technology, and store the pre-processed data using a distributed database or cloud storage technology; The prediction module is used to predict various factors affecting the cooling capacity of the air-conditioning chiller based on the preprocessed data using machine learning or statistical prediction models; The scheme module is used to input the predicted influencing factor values ​​into the cooling capacity prediction model, calculate and predict the cooling capacity demand of the chiller in the future according to the input values, and formulate the air conditioning energy-saving control scheme in advance based on the cooling capacity prediction results; The control module is used to execute corresponding control measures according to the formulated energy-saving control plan, and monitor the operating status and energy consumption of the air-conditioning system in real time.

Images