Energy-saving control method, system and device based on Internet of Things technology and storage medium

Abstract

The invention discloses an energy-saving control method, system and device based on the Internet of Things technology and a storage medium. The method comprises the following steps: acquiring initial data of equipment in a working area; preprocessing the initial data to obtain standard data; inputting the standard data into a pre-trained equipment energy efficiency evaluation and sorting model to obtain a high-energy-consumption equipment list; inputting the standard data of the equipment on the high-energy-consumption equipment list into a pre-trained energy-saving strategy generation model, and determining an energy-saving control strategy; and the energy-saving control strategy is sent to the high-energy-consumption equipment, the operation state of the equipment is adjusted, and energy-saving control is achieved. The method has the following effects that the real-time operation state of the equipment and the change of the external environment are dynamically sensed, the energy-saving potential point of the high-energy-consumption equipment is accurately identified, the control strategy is dynamically adjusted according to the change of the real-time state of the equipment and the effect after the strategy is implemented, and the energy utilization efficiency is efficiently improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent energy-saving control technology, and in particular to an energy-saving control method, system, device and storage medium based on Internet of Things technology. Background Art

[0002] At present, with the rapid increase in global energy consumption, the importance of energy-saving control in all walks of life has become increasingly prominent. Especially in the industrial field, the operation of high-energy-consuming equipment directly affects the energy consumption level of enterprises. Therefore, in terms of energy conservation and emission reduction, how to efficiently control the operation of these high-energy-consuming equipment has become an urgent problem to be solved. The core goal of energy-saving control technology is to improve the energy utilization efficiency of equipment and reduce energy waste through management strategies and technical means.

[0003] In one existing technology, energy-saving control relies on a fixed operating mode of the device or statistical analysis based on historical operating data. The system determines the operating status of the device by monitoring parameters such as the current and voltage of the device and combining them with preset thresholds. This approach often ignores the complexity of the device operating environment and its impact on energy consumption, and fails to make full use of real-time data to dynamically adjust the control strategy.

[0004] The existing technology only relies on simple historical data regression and statistical analysis, and is unable to dynamically perceive the real-time operating status of the equipment and changes in the external environment, and accurately identify the energy-saving potential points of high-energy-consuming equipment, resulting in low targeting and accuracy of energy consumption optimization. Summary of the invention

[0005] The present invention provides an energy-saving control method, system, device and storage medium based on Internet of Things technology to achieve real-time monitoring, dynamic adjustment and accurate identification of energy-saving potential points, thereby improving the pertinence and accuracy of energy consumption optimization.

[0006] In the first aspect, in order to solve the above technical problems, the present invention provides an energy-saving control method based on Internet of Things technology, comprising: Obtain initial operating status data and initial environmental data of equipment in the working area; Preprocessing the initial operation state data and the initial environment data to obtain standard operation state data and standard environment data; Inputting the standard operating status data and the standard environmental data into a pre-trained equipment energy efficiency evaluation and ranking model to obtain a list of high energy consumption equipment; Inputting the standard operating status data and standard environmental data of the equipment on the high-energy-consuming equipment list into a pre-trained energy-saving strategy generation model to determine an energy-saving control strategy; The energy-saving control strategy is sent to high-energy-consuming devices to adjust the operating status of the devices and achieve energy-saving control.

[0007] In an optional implementation, the training process of the device energy efficiency evaluation and ranking model includes: Building a long short-term memory network model based on historical operating status data, historical environmental data and preset benchmark energy consumption value data of the equipment, and training the long short-term memory network model; When the number of training times is greater than or equal to the preset maximum number of training times, or when the loss function value of the long short-term memory network model is less than the preset loss threshold, the training is determined to be completed, and the trained long short-term memory network model is used as the equipment energy efficiency evaluation and ranking model.

[0008] In an optional implementation, the training process of the energy-saving strategy generation model includes: Building a recurrent neural network model based on historical operating status data of the equipment, historical environmental data, and preset energy-saving technology application data, and training the recurrent neural network model; When the number of training times is greater than or equal to a preset maximum number of training times, or when the loss function value of the recurrent neural network model is less than a preset loss threshold, the training is determined to be completed and an energy-saving strategy generation model is obtained.

[0009] In an optional implementation, the inputting of the standard operating status data and the standard environment data into a pre-trained equipment energy efficiency evaluation and ranking model to obtain a list of high energy consumption equipment includes: Obtaining the actual energy loss value of each device according to the standard operating status data and the standard environmental data; By comparing the actual energy loss value of each device with the standard energy loss value of each device, the energy loss difference of each device is calculated; The energy loss differences of the devices are output and sorted according to the differences to obtain a list of high energy consumption devices.

[0010] In an optional implementation, obtaining the actual energy loss value of each device according to the standard operating status data and the standard environment data includes: The actual energy loss value is obtained by the following formula: in, Is the device in the time interval The actual energy loss in It's time The power consumption of the device, It's time The ambient temperature at It's time The ambient humidity at It's time The ambient light intensity at and are model parameters that represent the weights of the impact of device power consumption, temperature, humidity, and light intensity on energy loss.

[0011] In an optional implementation, inputting the standard operating status data and standard environment data of the equipment on the high energy consumption equipment list into a pre-trained energy-saving strategy generation model to determine the energy-saving control strategy includes: The comprehensive evaluation scores of different strategies are obtained through the following formula: in, is the comprehensive evaluation score of the strategy, To reduce energy consumption, is the weight of energy consumption reduction, is the improvement in energy efficiency ratio, which indicates the improvement in equipment energy efficiency ratio after the implementation of the strategy. Calculated, where is the energy consumption of the equipment before implementing the strategy, is the device power output before implementing the strategy, is the energy consumption of the equipment after the implementation of the strategy, is the power output of the device after the strategy is implemented; is the weight of the energy efficiency improvement, Rating for reliability, weights for reliability scores; The strategy with the highest comprehensive evaluation score corresponding to the strategy is determined as the energy-saving control strategy.

[0012] In an optional implementation manner, the preprocessing of the initial operation status data and the initial environment data to obtain standard operation status data and standard environment data includes: Performing data cleaning and normalization processing on the initial operation status data to obtain standard operation status data; The initial environmental data is subjected to missing value filling, outlier detection and correction operations to obtain standard environmental data.

[0013] In a second aspect, the present invention provides an energy-saving control system based on Internet of Things technology, comprising: A data acquisition module, used to acquire initial operating status data and initial environmental data of equipment in the working area; A data processing module, used for preprocessing the initial operation status data and the initial environment data to obtain standard operation status data and standard environment data; An energy efficiency evaluation module, used to input the standard operating status data and the standard environmental data into a pre-trained equipment energy efficiency evaluation and ranking model to obtain a list of high energy consumption equipment; A strategy generation module, used to input the standard operating status data and standard environmental data of the equipment on the high-energy-consuming equipment list into a pre-trained energy-saving strategy generation model to determine the energy-saving control strategy; The device adjustment module is used to send the energy-saving control strategy to high-energy-consuming devices, adjust the operating status of the devices, and achieve energy-saving control.

[0014] In a third aspect, the present invention further provides an electronic device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the energy-saving control method based on the Internet of Things technology described above is implemented.

[0015] In a fourth aspect, the present invention further provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned energy-saving control methods based on the Internet of Things technology.

[0016] Compared with the prior art, the present invention has the following beneficial effects: The present invention proposes an energy-saving control method based on the Internet of Things technology, which collects the operating status data and environmental data of the equipment in real time, pre-processes them, and then inputs them into a pre-trained energy efficiency evaluation and ranking model to obtain a list of high-energy consumption equipment. Then, the standard operating status data and standard environmental data of the equipment on the high-energy consumption equipment list are input into the pre-trained energy-saving strategy generation model to determine the energy-saving control strategy, and these strategies are sent to the high-energy consumption equipment to adjust the equipment operation status and achieve energy-saving control. The present invention can accurately evaluate the actual energy consumption of the equipment and generate targeted energy-saving control instructions, thereby achieving dynamic energy-saving control of high-energy consumption equipment, improving energy utilization efficiency, reducing energy consumption, and reducing waste. In addition, this method can also dynamically adjust the control strategy according to the real-time status changes of the equipment, further improving the accuracy and pertinence of the energy-saving effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a schematic diagram of a flow chart of an energy-saving control method based on Internet of Things technology provided by a first embodiment of the present invention; Figure 2 It is a schematic diagram of the structure of an energy-saving control system based on Internet of Things technology provided by the second embodiment of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] Reference Figure 1 The first embodiment of the present invention provides an energy-saving control method based on Internet of Things technology, comprising the following steps: S11, obtaining initial operating status data and initial environmental data of equipment in the working area; S12, preprocessing the initial operation status data and the initial environment data to obtain standard operation status data and standard environment data; S13, inputting the standard operating status data and the standard environmental data into a pre-trained equipment energy efficiency evaluation and ranking model to obtain a list of high energy consumption equipment; S14, inputting the standard operating status data and standard environmental data of the equipment on the high-energy-consuming equipment list into a pre-trained energy-saving strategy generation model to determine an energy-saving control strategy; S15, sending the energy-saving control strategy to high-energy consumption equipment, adjusting the equipment operation status, and realizing energy-saving control.

[0020] In step S11, the initial operating status data and initial environmental data of the equipment in the working area are obtained. The goal of this step is to provide objective initial benchmark values ​​for subsequent equipment energy efficiency evaluation through systematic data collection, so as to ensure that the formulation of energy-saving strategies has sufficient data support and high implementation effects. Specifically, the initial operating status data are the core operating parameters of the equipment under standard working conditions, such as power consumption, current, voltage, and vibration. These data can reflect the energy consumption and working characteristics of the equipment without implementing any energy-saving or adjustment measures. The initial environmental data includes external factors such as ambient temperature, humidity and air flow conditions in the working area of ​​the equipment. These environmental parameters may affect the working efficiency and energy consumption performance of the equipment. Therefore, the purpose of collecting initial operating status data and initial environmental data is to provide comprehensive data information for the evaluation of the effectiveness of energy-saving strategies, the design of optimization plans and the analysis of equipment operating status.

[0021] In terms of data collection, first of all, the operating status data of the equipment can be collected in real time through a variety of sensing devices, including voltage, current sensors, power meters, temperature sensors, vibration sensors, etc. Obtaining voltage and current data can identify the actual workload and power consumption of the equipment, while the power meter can accurately measure the power consumption of the equipment under different load conditions. For temperature data, especially the collection of internal and surface temperatures of the equipment, it can provide a basis for judging the load of the equipment, because excessively high temperatures indicate that the equipment is under a large operating load and may have high energy consumption problems. Vibration data is mainly used for mechanical equipment. Abnormal vibrations often indicate that equipment parts are worn or unstable, which may cause additional energy consumption. These key parameters not only constitute the basic data for energy efficiency evaluation, but also help identify abnormal conditions or high energy consumption characteristics during equipment operation, facilitating targeted energy-saving improvements.

[0022] Secondly, obtaining the initial environmental data of the working area can provide a basis for analyzing the impact of external factors on the energy efficiency of the equipment. Environmental data includes temperature, humidity, air flow, etc., among which temperature changes may directly affect the heat dissipation effect of the equipment. A high temperature environment will cause the internal temperature of the equipment to rise, increase the cooling demand, and thus lead to higher power consumption. Changes in humidity may have an indirect impact on the operating safety and energy efficiency of the equipment. Especially for electrical equipment, excessive humidity may cause reduced insulation performance or short circuit risks. Air flow conditions mainly affect the heat dissipation efficiency of air-cooled equipment or heat-sensitive equipment. In an environment lacking air circulation, the equipment may generate heat accumulation, further leading to a decrease in the energy efficiency of the equipment. Therefore, the environmental data of the working area can effectively help analyze whether the energy efficiency problem of the equipment is related to environmental conditions, and provide a reference for adjusting environmental control measures.

[0023] In terms of data collection, the implementation of step S11 requires the installation of a dedicated sensor network to ensure the accuracy and timeliness of equipment and environmental data. The design of the sensor network includes electrical sensors, temperature and humidity sensors, vibration sensors, and airflow sensors. Through the real-time data collection of these sensors, the system can fully understand the initial energy consumption and working environment characteristics of the equipment. The sensor data can be remotely monitored and transmitted through the Industrial Internet of Things (IIoT) platform, or the data can be locally processed through edge computing devices to reduce the delay and cost of data transmission. The sensor network provides real-time data support for the energy-saving system, which can help the dynamic adjustment and optimization of energy-saving strategies. The sensor network based on edge computing can realize hierarchical data processing, that is, basic processing of the initial operating status data and environmental data collected in real time, screening out abnormal or key data and uploading them to the central data platform. This design can significantly improve data processing efficiency.

[0024] It should be noted that the data collection in step S11 not only provides an objective benchmark for the current equipment status, but also lays the foundation for the implementation and effect evaluation of subsequent energy-saving control strategies. The initial operating status data and environmental data can reflect the energy consumption characteristics of the equipment under standard conditions, and these data can be used as inputs to the energy efficiency model after being standardized and analyzed. Based on the benchmark data, the system can gradually identify high-energy-consuming equipment, troubleshoot possible environmental influencing factors, and design personalized energy-saving strategies for different equipment types and environmental conditions. Therefore, accurate data collection is one of the prerequisites for the efficient operation of the energy-saving control system, ensuring the accuracy of energy-saving evaluation and the rationality of energy-saving strategies. During the implementation process, the collection results of the initial data can also be stored as historical data for a long time, which can be used to compare the changes in the operating status of the equipment under different energy-saving strategies in the future, thereby providing feedback basis for the improvement of energy-saving strategies.

[0025] In step S12, data preprocessing is an important step to ensure the accuracy of energy-saving control system decision-making. The purpose is to process the initially collected operating status data and environmental data into more consistent, complete and reliable data for subsequent energy efficiency evaluation and analysis. The preprocessing process of this step includes data cleaning and normalization of the initial operating status data, as well as missing value filling, outlier detection and correction of the initial environmental data. Data cleaning and standardization operations can significantly improve the quality of data, ensure the comparability between various types of data, and thus improve the computational efficiency and accuracy of the energy efficiency analysis model.

[0026] In a preferred implementation, the preprocessing of the initial operation status data and the initial environment data to obtain standard operation status data and standard environment data includes: Performing data cleaning and normalization processing on the initial operation status data to obtain standard operation status data; The initial environmental data is subjected to missing value filling, outlier detection and correction operations to obtain standard environmental data.

[0027] First, the preprocessing of the initial operating status data includes two core steps: data cleaning and normalization. The initial operating status data is the real-time working parameters of the equipment under specific environmental conditions, including power, voltage, current, temperature and other information. These data are collected in the original form, so there may be noise, outliers and inconsistent data formats. Data cleaning is mainly used to remove redundant information, eliminate noise and correct data deviations to ensure the authenticity and validity of the data. By processing the noise and outliers of the data, errors caused by factors such as sensor failure and environmental interference can be eliminated. For example, a sudden change in power or temperature values ​​may be caused by a temporary failure of the sensor, so these abnormal data can be filtered or replaced during the data cleaning process. In addition, data cleaning can also help identify and eliminate unnecessary mutation points for short-term data deviations caused by the switching state of the equipment, operating load fluctuations, etc., so as to obtain smoother and continuous equipment operating status data.

[0028] Normalization is a critical operation in data preprocessing, which can ensure that the operating status data is comparable under different equipment and different working conditions. The core of normalization is to standardize or normalize data of different dimensions and scales according to a certain proportion, so that all kinds of data are consistent on a unified scale for subsequent analysis. For example, for data of different units such as equipment power, current, temperature, etc., the data value can be limited to a unified range (such as between 0 and 1) through normalization. This can not only simplify the subsequent data processing process, but also reduce the excessive impact of certain specific indicators on the results in the energy efficiency analysis model, and prevent indicators with large data fluctuations from dominating the final analysis results. In addition, for some specific industrial equipment, there may be different operating conditions (such as low load, high load, etc.). Through normalization, the operating data of these different conditions can be made comparable in a unified evaluation system, making energy efficiency analysis more accurate and reliable.

[0029] Secondly, the initial environmental data is subjected to missing value filling, outlier detection and correction operations to generate standard environmental data. Since the environmental data comes from different sensor nodes, it may be affected by the sensor layout, acquisition frequency and sampling quality, resulting in missing values ​​in some environmental parameters (such as temperature, humidity, etc.). In order to ensure the integrity of environmental data, missing value filling is an important processing step. Common missing value filling methods include mean filling, interpolation filling and nearest neighbor filling. For continuously monitored data series, a time-based interpolation method can be used to fill missing values ​​into the data series, which can better maintain the continuity of the data. The filled data can effectively reduce the impact of missing data on subsequent energy efficiency evaluation.

[0030] After missing values ​​are filled, outlier detection and correction are also required for environmental data to ensure the authenticity and reliability of the data. Environmental data may deviate due to collection errors or external interference. For example, the values ​​of ambient temperature or humidity may fluctuate abnormally due to extreme weather conditions or sensor failures. In outlier detection, statistical methods (such as standard deviation threshold method) or machine learning methods (such as anomaly detection models based on historical data) can be used to identify these outliers. Once an outlier is detected, the abnormal data can be corrected by linear interpolation or moving average based on the previous and subsequent data sequences to make the data smoother and more continuous. This operation can effectively prevent abnormal environmental data from misleading the results of equipment energy efficiency analysis and ensure the accuracy of the analysis.

[0031] It should be noted that data preprocessing does not change the actual information of the original data, but standardizes and corrects it to ensure the validity and consistency of the data. The acquisition of standard operating status data and standard environmental data provides a more reliable benchmark for subsequent energy efficiency analysis and provides necessary input for the formulation of energy-saving strategies. Through data cleaning, normalization and missing value filling, the system can obtain a more accurate equipment operating status and environmental data model, providing a better input data basis for energy efficiency model calculation. The completion of this step can help the energy-saving control system improve data quality, make the energy efficiency evaluation model more accurate when performing energy consumption analysis, and reduce the impact of data errors on the evaluation results.

[0032] In step S13, the standard operating status data and the standard environmental data are input into the pre-trained equipment energy efficiency evaluation and ranking model to obtain a list of high-energy consumption equipment. The purpose of this step is to evaluate the energy efficiency level of the equipment and identify high-energy consumption equipment based on the actual energy consumption of the equipment, so as to provide a basis for subsequent energy-saving optimization. The implementation process of this step adopts an equipment energy efficiency evaluation and ranking model based on the long short-term memory network (LSTM) model, through which the standardized operating status data and environmental data are analyzed and ranked for energy consumption. It should be noted that the design and training of the equipment energy efficiency evaluation and ranking model include two core links in implementation: first, construct and train the LSTM model based on historical data to ensure that the model can accurately predict the energy consumption of the equipment in different states and environments; second, further identify high-energy consumption equipment through the calculation and ranking of the actual energy loss value.

[0033] In a preferred implementation, the training process of the equipment energy efficiency evaluation and ranking model includes: Building a long short-term memory network model based on historical operating status data, historical environmental data and preset benchmark energy consumption value data of the equipment, and training the long short-term memory network model; When the number of training times is greater than or equal to the preset maximum number of training times, or when the loss function value of the long short-term memory network model is less than the preset loss threshold, the training is determined to be completed, and the trained long short-term memory network model is used as the equipment energy efficiency evaluation and ranking model.

[0034] It should be noted that the LSTM model is a deep learning model suitable for processing time series data, which can capture long-term and short-term characteristics in time when analyzing the historical data of equipment energy consumption. The energy consumption data of the equipment is typical time series data, and its energy efficiency performance may be affected by the previous and next states in the time series. Therefore, LSTM can better model the dynamic characteristics of equipment energy consumption changes in this application. The training data mainly includes the historical operation status data, historical environment data and preset benchmark energy consumption value data of the equipment. In the historical operation status data, parameters such as power consumption, voltage, current and temperature are the main features, while the historical environment data includes indicators such as the working environment temperature, humidity and light intensity of the equipment. The preset benchmark energy consumption value data is used as the target output value of the LSTM model to measure the standard energy consumption level of the equipment under different environmental conditions and working conditions. These data can provide a comprehensive equipment energy consumption evaluation basis for the LSTM model, which helps to train the model to predict the actual energy loss of different equipment under various working conditions.

[0035] During the model training process, the LSTM model will repeatedly iterate training based on these historical data, and optimize the prediction effect by adjusting the model parameters. In each training iteration, the model outputs the corresponding energy consumption prediction value based on the input operating status and environmental data, and calculates the difference between it and the actual benchmark energy consumption value, that is, the loss function value of the model. Through multiple training iterations, the model continuously adjusts its internal parameters (that is, the weights of each influencing factor) to minimize the loss function value, thereby improving the prediction accuracy. When the number of training times reaches the preset maximum number of training times, or when the loss function value is less than the preset loss threshold, the training can be determined to be complete. The trained LSTM model will have a strong prediction ability and can be used as a model for equipment energy efficiency evaluation and ranking, and applied to energy consumption analysis of actual equipment and identification of high-energy consumption equipment.

[0036] In a preferred implementation, obtaining the actual energy loss value of each device according to the standard operating status data and the standard environment data includes: The actual energy loss value is obtained by the following formula: in, Is the device in the time interval The actual energy loss in It's time The power consumption of the device, It's time The ambient temperature at It's time The ambient humidity at It's time The ambient light intensity at and are model parameters that represent the weights of the impact of device power consumption, temperature, humidity, and light intensity on energy loss.

[0037] It should be noted that in this embodiment, the actual energy loss value is calculated by establishing a multivariate linear integral equation, which takes into account the impact of multiple factors such as device power consumption, ambient temperature, ambient humidity, and ambient light intensity on energy loss. Compared with the traditional single-factor model, this multi-factor modeling method can more comprehensively reflect the impact of device operating status and environmental conditions on energy loss. In addition, the model parameters and The setting of is determined during the model training process, reflecting the contribution of each factor to the energy consumption of the equipment. It can be adjusted according to the actual situation to meet the needs of different equipment types and application scenarios, enhancing the flexibility and universality of the model. In this way, the present invention can provide accurate energy loss assessment in complex working environments, help improve energy utilization efficiency, and reduce operating costs.

[0038] In step S14, the system inputs the standard operating status data and standard environmental data of the equipment on the high-energy-consuming equipment list into the pre-trained energy-saving strategy generation model to determine the energy-saving control strategy. This step is a key link in the entire energy-saving optimization process. By combining the actual operating status and environmental parameters of the equipment, the optimal energy-saving control strategy is automatically generated to ensure that the goal of maximizing energy efficiency is achieved under the premise of normal operation and performance of the equipment.

[0039] In a preferred implementation, the training process of the energy-saving strategy generation model includes: Building a recurrent neural network model based on historical operating status data of the equipment, historical environmental data, and preset energy-saving technology application data, and training the recurrent neural network model; When the number of training times is greater than or equal to a preset maximum number of training times, or when the loss function value of the recurrent neural network model is less than a preset loss threshold, the training is determined to be completed and an energy-saving strategy generation model is obtained.

[0040] It should be noted that the training process of the model includes two main data sources: the historical operating status data of the device and the historical environmental data. The historical operating status data refers to the multi-dimensional operating indicators of the device such as power, energy consumption, and rotation speed in different time periods. These data reflect the working characteristics of the device in long-term operation, as well as the energy consumption performance under different loads or working conditions. The historical environmental data includes external factors such as ambient temperature, humidity, and light intensity, which have a direct impact on the energy consumption of the device. For example, excessively high ambient temperature may cause the device to overheat, thereby increasing power consumption. Therefore, the accuracy and completeness of environmental data are crucial in the generation of energy-saving strategies.

[0041] In the training of the energy-saving strategy generation model, preset energy-saving technology application data will also be introduced. Energy-saving technology application data refers to a set of data sets with detailed descriptions and performance indicators of various energy-saving technologies. Different energy-saving technologies (for example, frequency conversion technology, optimized cooling technology, energy recovery technology, etc.) have different implementation methods and applicable scenarios, and the application data records the parameter information of each technology. Energy-saving technology application data mainly helps the model select appropriate energy-saving technologies in different scenarios to cope with different operating requirements and conditions.

[0042] In the energy-saving strategy generation model, these data provide the model with the theoretical best operation mode. For example, the model can use the energy-saving potential information of energy-saving technology application data under specific conditions to determine when and how to switch different energy-saving technologies.

[0043] In actual applications, the model will analyze the current operating status of the device when real-time data flows in, and call the energy-saving technology application data, and determine the best energy-saving strategy suitable for the current conditions through dynamic matching and analysis. For example, by setting trigger conditions, when the model detects that the device temperature rises to a certain threshold, it can call the parameter data of the cooling technology and generate a suitable cooling strategy.

[0044] In summary, the role of energy-saving technology application data is not only to provide a set of technical features, but also to guide the model to generate energy-saving strategies. Through the dynamic use of these data by the model, the optimal energy-saving strategy under different working conditions and load conditions can be achieved, which helps to achieve more efficient energy consumption management in the actual production environment.

[0045] During the model training process, the system will perform multiple iterations to continuously optimize the model parameters. The training process will set a maximum number of training times or a threshold for the loss function. When the model's loss function value is less than the preset loss threshold, or when the number of training times reaches the maximum value, the training process is considered complete. The loss function is an indicator that measures the gap between the model's prediction and the actual value. By continuously minimizing the loss function, the model can gradually improve its prediction accuracy. When the training is completed, the model can be used to generate actual energy-saving strategies.

[0046] Specifically, after receiving the standard operating status data and standard environmental data of the equipment, the energy-saving strategy generation model after training will analyze these data and generate a set of possible energy-saving control strategies. These strategies include adjusting the operating parameters of the equipment, such as reducing power output, optimizing operating time, or applying a specific energy-saving technology (such as variable frequency control or power optimization). The system will score each strategy based on its predicted effect, and finally select the strategy with the highest score as the final energy-saving control solution.

[0047] It should be emphasized that when generating energy-saving control strategies, the model not only focuses on reducing energy consumption, but also takes into account the reliability and stability of the equipment. The core goal of the energy-saving strategy is to minimize energy consumption without affecting the normal operation and service life of the equipment. Therefore, the generated energy-saving strategy needs to balance the energy efficiency and stability of the equipment. For example, in some cases, although energy consumption can be significantly reduced by reducing the power output of the equipment, it may cause the equipment to not work properly. Therefore, when generating strategies, the system will evaluate the comprehensive effect of each strategy to ensure that the final selected strategy is not only energy-saving, but also ensures the operating efficiency and stability of the equipment.

[0048] In actual applications, this energy-saving strategy generation process is dynamic and is not fixed after it is generated once. As the operating status of the device continues to change, the system will continue to monitor the real-time operating data and environmental data of the device, and adjust the energy-saving strategy in real time based on this data. For example, when the ambient temperature rises suddenly, the system may need to adjust the cooling plan of the device to ensure that the device does not increase unnecessary energy consumption due to overheating. Similarly, when the load of the device changes, the system will also adjust the energy-saving strategy accordingly to ensure that the device can maintain optimal energy efficiency under different working conditions.

[0049] In a preferred implementation, inputting the standard operating status data and standard environment data of the equipment on the high energy consumption equipment list into a pre-trained energy-saving strategy generation model to determine the energy-saving control strategy includes: The comprehensive evaluation scores of different strategies are obtained through the following formula: in, is the comprehensive evaluation score of the strategy, To reduce energy consumption, is the weight of energy consumption reduction, is the improvement in energy efficiency ratio, which indicates the improvement in equipment energy efficiency ratio after the implementation of the strategy. Calculated, where is the energy consumption of the equipment before implementing the strategy, is the device power output before implementing the strategy, is the energy consumption of the equipment after the implementation of the strategy, is the power output of the device after the strategy is implemented; is the weight of the energy efficiency improvement, Rating for reliability, weights for reliability scores; The strategy with the highest comprehensive evaluation score corresponding to the strategies is determined as the energy-saving control strategy.

[0050] It should be noted that Indicates the actual energy consumption reduction of the device after implementing a certain energy-saving strategy. This is an important indicator in the evaluation of energy-saving strategies, reflecting the actual effect of the strategy in energy consumption control. The larger the value, the better the strategy performs in reducing energy consumption. The weight of the energy consumption reduction is used to indicate the relative importance of energy consumption reduction in the comprehensive score. In some application scenarios, reducing energy consumption may be the core goal of energy saving, so this weight can be set higher to ensure that energy consumption reduction has a greater impact on the final score. Indicates the improvement of the energy efficiency ratio of the equipment after the implementation of the energy-saving strategy. The improvement of the energy efficiency ratio means that the equipment can perform its functions more effectively under the same power output, or reduce the actual energy consumption when the power remains unchanged. Represents the reliability score of an energy-saving strategy. When evaluating an energy-saving strategy, it is necessary not only to consider its energy-saving effect, but also to ensure that the strategy will not have a negative impact on the normal operation of the device. The reliability score measures whether the device can continue to operate stably and efficiently after implementing a certain energy-saving strategy. The higher the reliability score, the more stable the device's working state will be while reducing energy consumption. After evaluating these indicators, the strategy with the highest comprehensive evaluation score is finally determined as the energy-saving control strategy. This strategy will not only achieve an effective reduction in energy consumption, but also ensure that the energy efficiency ratio of the device is improved, while taking into account the stability and reliability of the device.

[0051] In step S15, the energy-saving control strategy must be issued in accordance with the communication protocol and control interface of the device management system. This involves the application of industrial Internet of Things (IoT) or automated control systems. The device management system maintains real-time connection with each high-energy-consuming device through these communication protocols, which enables the system to quickly and accurately issue energy-saving control strategies to the target device. It should be noted that different devices may have different control interfaces, so when issuing energy-saving strategies, the system needs to format them according to the specific requirements and communication protocols of each device. This type of formatting includes processes such as parameter mapping and data conversion to ensure that the energy-saving strategy can be recognized and executed by the control logic of the device.

[0052] In this process, the energy-saving control strategy is converted into a series of specific operation instructions. These operation instructions may include adjusting the power of the equipment, changing the operating time, adjusting the working cycle, etc. These adjustments will affect the key operating parameters of the equipment, such as the speed of the motor, the temperature set point of the air conditioning system, or the heating power of the heating equipment. Through these operations, the equipment can operate at the lowest energy consumption level while meeting production needs.

[0053] Secondly, after receiving the control command, the equipment will adjust its state. For example, if it involves motor-type equipment, the energy-saving control strategy may reduce the motor's operating speed by adjusting the output frequency of the inverter, thereby reducing power consumption. If it involves temperature control equipment (such as boilers or air conditioners), the control strategy may optimize energy consumption by adjusting the temperature set point or adjusting the heating / cooling power. In these processes, the key performance indicators of the equipment (such as temperature, pressure, speed, etc.) need to be kept within the allowable range, and production safety or quality cannot be affected by excessive energy reduction.

[0054] It should be noted that the adjustment of the equipment operation status is not completed in one go. In order to ensure the effectiveness of energy-saving control, the system will continuously monitor and feedback based on the real-time data of the equipment. This feedback mechanism is a key link to ensure the implementation effect of the energy-saving control strategy. After the energy-saving control strategy is issued, the system will collect the operation data of the equipment in real time, including power consumption, equipment status, production efficiency, etc., to evaluate the implementation effect of the strategy. Based on this data, the system can determine whether the current control strategy has achieved the expected energy-saving effect, and make further adjustments if necessary. For example, if it is monitored that the energy consumption of the equipment has not decreased significantly, the system may further optimize the strategy, or make timely corrections when it is found that the performance of some equipment has decreased due to the adjustment of the energy-saving strategy.

[0055] In addition, the process of issuing energy-saving control strategies is accompanied by the implementation of equipment protection measures. In energy-saving control, the stability and safety of equipment are always the priority factors. Therefore, the system will set up a series of protection mechanisms to prevent equipment damage or failure due to excessive energy saving. For example, for some high-precision equipment, the energy-saving strategy may not significantly adjust the main operating parameters of the equipment, but focus on optimizing the energy consumption of auxiliary systems, such as cooling systems or lighting equipment.

[0056] In order to facilitate the understanding of the present invention, some preferred embodiments of the present invention are further described below.

[0057] In one implementation, the energy-saving control system of the present invention adopts a device behavior learning technology that models the operation mode of the device through a deep learning algorithm. By analyzing the device data collected over a long period of time, the system can identify the energy consumption characteristics of the device under different working conditions and learn the operating habits of the device. This learning mechanism enables the system to predict the energy consumption trend of the device in the future time period, and adjust the operating parameters of the device in advance accordingly, so as to achieve more sophisticated and forward-looking energy-saving control.

[0058] In another implementation, an adaptive control logic based on reinforcement learning is integrated into the energy-saving control strategy generation model of the present invention. The logic can automatically adjust the parameters of the control strategy according to the effect of the device's real-time response to the energy-saving strategy. For example, if the system detects that a certain energy-saving measure causes a decrease in production efficiency, the reinforcement learning algorithm will adjust the intensity or timing of the measure to find the best balance between energy consumption and production efficiency. This adaptive control logic not only improves the implementation effect of energy-saving measures, but also ensures the continuity and quality of production, making energy-saving control more intelligent and efficient.

[0059] The following describes the working process of the present invention using a common scenario as an example. Figure 2 , which is Figure 1 Schematic diagram of the working scenario of the method.

[0060] In a large manufacturing company, the energy consumption management of equipment faces significant challenges, especially when it comes to multiple high-energy-consuming equipment, such as injection molding machines, laser cutting machines, and air compressors. These equipment consume a lot of electricity during the production process, resulting in high energy costs for the company. In order to optimize energy consumption and reduce costs, the company decided to implement an energy-saving control method based on IoT technology to improve energy efficiency and reduce production costs.

[0061] First, the company deployed IoT sensors in various key work areas. These sensors can monitor the operating status of the equipment and the surrounding environmental parameters in real time. The data collected by the sensors include the power consumption of the equipment, operating hours, ambient temperature, humidity, and light intensity. The collected initial operating status data and environmental data are transmitted to the central database via wireless network for preprocessing to improve the quality and reliability of the data.

[0062] After data preprocessing, the obtained standard operating status data and standard environmental data are input into the pre-trained equipment energy efficiency evaluation and ranking model. The model evaluates the energy efficiency of each device based on historical operating status data, environmental data and preset benchmark energy consumption values ​​through machine learning algorithms. The output of the model is a list of high energy consumption devices. For the equipment listed in the high-energy-consuming equipment list, its standard operating status data and environmental data are further input into the pre-trained energy-saving strategy generation model. The model generates corresponding energy-saving control strategies based on historical data and preset energy-saving technology application data. These strategies involve adjusting the operating time of the equipment, optimizing power output, improving the use mode of the equipment, etc. The model provides multiple possible energy-saving solutions for each device by comprehensively considering multiple influencing factors.

[0063] Next, a comprehensive evaluation is conducted on each strategy to determine the best energy-saving control strategy. The comprehensive evaluation score takes into account multiple factors such as energy consumption reduction, energy efficiency improvement, and strategy reliability. By calculating the comprehensive evaluation score of each strategy, the strategy with the highest score is finally selected for implementation.

[0064] After selecting and implementing the energy-saving control strategy, the corresponding control instructions are sent to the high-energy-consuming equipment to adjust its operating status.

[0065] Finally, after implementing the energy-saving control strategy, continue to monitor the operating status and energy consumption data of the equipment. Evaluate the energy-saving effect by comparing the energy consumption data before and after implementation. If it is found that some strategies fail to achieve the expected results, they will be adjusted and optimized in time to achieve continuous energy efficiency improvement.

[0066] In summary, through this energy-saving control method based on IoT technology, the factory has achieved dynamic energy-saving control of high-energy-consuming equipment, improved energy utilization efficiency, and reduced energy consumption. In addition, this method can dynamically adjust the control strategy according to the changes in the real-time status of the equipment and the effect after the implementation of the strategy, further improving the accuracy and pertinence of the energy-saving effect. In this way, the system can minimize energy consumption and improve energy efficiency while ensuring production quality and efficiency.

[0067] Reference Figure 2The second embodiment of the present invention provides an energy-saving control system based on Internet of Things technology, including: A data acquisition module, used to acquire initial operating status data and initial environmental data of equipment in the working area; A data processing module, used for preprocessing the initial operation status data and the initial environment data to obtain standard operation status data and standard environment data; An energy efficiency evaluation module, used to input the standard operating status data and the standard environmental data into a pre-trained equipment energy efficiency evaluation and ranking model to obtain a list of high energy consumption equipment; A strategy generation module, used to input the standard operating status data and standard environmental data of the equipment on the high-energy-consuming equipment list into a pre-trained energy-saving strategy generation model to determine the energy-saving control strategy; The device adjustment module is used to send the energy-saving control strategy to high-energy-consuming devices, adjust the operating status of the devices, and achieve energy-saving control.

[0068] It should be noted that an energy-saving control device based on Internet of Things technology provided in an embodiment of the present invention is used to execute all process steps of an energy-saving control method based on Internet of Things technology in the above embodiment. The working principles and beneficial effects of the two correspond one to one, and therefore will not be repeated here.

[0069] The embodiment of the present invention also provides an electronic device. The electronic device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as an energy-saving control program based on the Internet of Things technology. When the processor executes the computer program, the steps in the above-mentioned energy-saving control method embodiments based on the Internet of Things technology are implemented, such as Figure 1 Step S11 is shown. Alternatively, when the processor executes the computer program, the functions of each module / unit in the above-mentioned device embodiments are implemented, such as the energy consumption calculation module.

[0070] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the electronic device.

[0071] The electronic device may be a computing device such as a desktop computer, a notebook, a PDA, and a smart tablet. The electronic device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the above components are merely examples of electronic devices and do not constitute a limitation on the electronic device. The electronic device may include more or fewer components than the above components, or a combination of certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0072] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the electronic device, and uses various interfaces and lines to connect various parts of the entire electronic device.

[0073] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the electronic device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0074] Wherein, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0075] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0076] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. An energy-saving control method based on Internet of Things technology, characterized in that: include: Obtain initial operating status data and initial environmental data of equipment in the working area; Preprocessing the initial operation state data and the initial environment data to obtain standard operation state data and standard environment data; Inputting the standard operating status data and the standard environmental data into a pre-trained equipment energy efficiency evaluation and ranking model to obtain a list of high energy consumption equipment; Inputting the standard operating status data and standard environmental data of the equipment on the high-energy-consuming equipment list into a pre-trained energy-saving strategy generation model to determine an energy-saving control strategy; The energy-saving control strategy is sent to high-energy-consuming devices to adjust the operating status of the devices and achieve energy-saving control.

2. The energy-saving control method based on Internet of Things technology according to claim 1 is characterized in that: The training process of the equipment energy efficiency evaluation and ranking model includes: Building a long short-term memory network model based on historical operating status data, historical environmental data and preset benchmark energy consumption value data of the equipment, and training the long short-term memory network model; When the number of training times is greater than or equal to the preset maximum number of training times, or when the loss function value of the long short-term memory network model is less than the preset loss threshold, the training is determined to be completed, and the trained long short-term memory network model is used as the equipment energy efficiency evaluation and ranking model.

3. The energy-saving control method based on Internet of Things technology according to claim 1 is characterized in that: The training process of the energy-saving strategy generation model includes: Building a recurrent neural network model based on historical operating status data of the equipment, historical environmental data, and preset energy-saving technology application data, and training the recurrent neural network model; When the number of training times is greater than or equal to a preset maximum number of training times, or when the loss function value of the recurrent neural network model is less than a preset loss threshold, the training is determined to be completed and an energy-saving strategy generation model is obtained.

4. The energy-saving control method based on Internet of Things technology according to claim 1 is characterized in that: The step of inputting the standard operating status data and the standard environmental data into a pre-trained equipment energy efficiency evaluation and ranking model to obtain a list of high energy consumption equipment includes: Obtaining the actual energy loss value of each device according to the standard operating status data and the standard environmental data; By comparing the actual energy loss value of each device with the standard energy loss value of each device, the energy loss difference of each device is calculated; The energy loss differences of the devices are output and sorted according to the differences to obtain a list of high energy consumption devices.

5. The energy-saving control method based on Internet of Things technology according to claim 4 is characterized in that: The obtaining of the actual energy loss value of each device according to the standard operating status data and the standard environment data includes: The actual energy loss value is obtained by the following formula: in, The device is in the time interval The actual energy loss in It's time The power consumption of the device, It's time The ambient temperature at It's time The ambient humidity at It's time The ambient light intensity at and are model parameters that represent the weights of the impact of device power consumption, temperature, humidity, and light intensity on energy loss.

6. The energy-saving control method based on Internet of Things technology according to claim 5 is characterized in that: The step of inputting the standard operating status data and standard environment data of the equipment on the high energy consumption equipment list into a pre-trained energy-saving strategy generation model to determine the energy-saving control strategy includes: The comprehensive evaluation scores of different strategies are obtained through the following formula: in, is the comprehensive evaluation score of the strategy, To reduce energy consumption, is the weight of energy consumption reduction, is the improvement in energy efficiency ratio, which indicates the improvement in equipment energy efficiency ratio after the implementation of the strategy. Calculated, where is the energy consumption of the equipment before implementing the strategy, is the device power output before implementing the strategy, is the energy consumption of the equipment after the implementation of the strategy, is the power output of the device after the strategy is implemented; is the weight of the energy efficiency improvement, Rating for reliability, weights for reliability scores; The strategy with the highest comprehensive evaluation score corresponding to the strategy is determined as the energy-saving control strategy.

7. The energy-saving control method based on Internet of Things technology according to claim 1 is characterized in that: The preprocessing of the initial operation status data and the initial environment data to obtain standard operation status data and standard environment data includes: Performing data cleaning and normalization processing on the initial operation status data to obtain standard operation status data; The initial environmental data is subjected to missing value filling, outlier detection and correction operations to obtain standard environmental data.

8. An energy-saving control system based on Internet of Things technology, characterized in that: include: A data acquisition module, used to acquire initial operating status data and initial environmental data of equipment in the working area; A data processing module, used for preprocessing the initial operation status data and the initial environment data to obtain standard operation status data and standard environment data; An energy efficiency evaluation module, used to input the standard operating status data and the standard environmental data into a pre-trained equipment energy efficiency evaluation and ranking model to obtain a list of high energy consumption equipment; A strategy generation module, used to input the standard operating status data and standard environmental data of the equipment on the high-energy-consuming equipment list into a pre-trained energy-saving strategy generation model to determine the energy-saving control strategy; The device adjustment module is used to send the energy-saving control strategy to high-energy-consuming devices, adjust the operating status of the devices, and achieve energy-saving control.

9. An electronic device, characterized in that: It includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements the energy-saving control method based on the Internet of Things technology as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the energy-saving control method based on the Internet of Things technology as described in any one of claims 1 to 7.

Images