Method and system for autonomously saving power consumption of dormitory air conditioner

By monitoring activities and the environment within the dormitory using sensors, and combining machine learning and genetic algorithms to optimize energy-saving strategies, the problem of poor energy efficiency and safety hazards in dormitory air conditioning power consumption has been solved. This has enabled intelligent control and safety monitoring, improving energy efficiency and user experience.

CN119026059APending Publication Date: 2024-11-26POWERCHINA CONSTR GRP

Patent Information

Application Number
CN202411481086.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-23
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

Existing energy-saving technologies for dormitory air conditioning lack in-depth analysis of human activity patterns and environmental parameters, making it impossible to flexibly adjust energy-saving strategies according to actual needs. Furthermore, they fail to effectively combine seasonal changes and time series, resulting in poor energy-saving effects and potential electrical safety hazards.

Method used

By using sensors to monitor the activity status of people and environmental conditions in the dormitory in real time, and by using machine learning and genetic algorithms to optimize energy-saving strategies, combined with safety monitoring and anomaly detection, autonomous energy-saving control can be achieved.

Benefits of technology

It enables intelligent control of air conditioning and electrical equipment in dormitories, improving energy efficiency and comfort, enhancing user interactivity, ensuring electrical safety, and improving system reliability and flexibility.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119026059A_ABST
    Figure CN119026059A_ABST
Patent Text Reader

Abstract

The invention discloses a dormitory air conditioner power utilization autonomous energy-saving method and system, and relates to the technical field of smart home control, and the method comprises the steps: monitoring the activity state of people in a dormitory and the environment condition in real time through a sensor, carrying out the preprocessing of the obtained data, carrying out the feature extraction of the preprocessed data, analyzing the extracted features, and carrying out the recognition of the extracted features. The method comprises the following steps: identifying a personnel activity mode, combining seasonal changes, environmental parameters and a time sequence, generating a preliminary energy-saving strategy according to preset rules and conditions, training a machine learning model according to historical data, predicting an optimal energy-saving strategy by utilizing a machine learning algorithm, carrying out iterative optimization on the energy-saving strategy by utilizing a genetic algorithm, and according to the optimized strategy, carrying out energy-saving optimization on the energy-saving strategy. The settings and customization strategies are adjusted while implementing safety monitoring and anomaly detection to ensure electrical safety. According to the invention, the problem of power utilization and energy conservation of many worker dormitories and employee dormitories at present is solved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of smart home control, and in particular to a method and system for autonomous energy saving of dormitory air-conditioning electricity. Background Art

[0002] In the context of increasingly severe energy consumption, dormitory air conditioning electricity management has become an important research direction in the field of energy conservation and emission reduction. In recent years, with the rapid development of sensor technology, data processing technology and machine learning algorithms, dormitory air conditioning electricity energy conservation technology has made significant progress. Traditional energy-saving methods mainly rely on simple control methods such as manually set temperature and timed on / off. Although these methods can reduce energy consumption to a certain extent, they often ignore the dynamic changes in the activity status of people in the dormitory and environmental conditions, resulting in a large contradiction between energy-saving effects and living comfort.

[0003] However, the existing dormitory air-conditioning electricity energy-saving technology still has many shortcomings. On the one hand, the existing technology lacks in-depth analysis of the activity patterns and environmental parameters of people in the dormitory, and cannot flexibly adjust the energy-saving strategy according to actual needs, resulting in unsatisfactory energy-saving effects. On the other hand, the existing technology fails to effectively combine factors such as seasonal changes and time series, making the adaptability of the energy-saving strategy poor. In addition, the existing technology ignores electrical safety monitoring and anomaly detection, and there are safety hazards. In response to these problems, the present invention proposes a method and system for autonomous energy saving of dormitory air-conditioning electricity. By real-time monitoring of the activity status of people and environmental conditions in the dormitory, the energy-saving strategy is iteratively optimized using machine learning algorithms and genetic algorithms, aiming to achieve a balance between energy saving and comfort while ensuring electrical safety. Summary of the invention

[0004] In view of the above existing problems, the present invention provides a method and system for autonomous energy saving of dormitory air-conditioning electricity, so as to solve the problem that the prior art ignores electrical safety monitoring and abnormality detection, resulting in potential safety hazards.

[0005] In order to solve the above technical problems, a method for autonomous energy saving of dormitory air conditioning electricity is proposed, including: Sensors are used to monitor the activity status and environmental conditions of people in the dormitory in real time, and the obtained data is preprocessed and features are extracted from the preprocessed data; the extracted features are analyzed to identify the activity patterns of people, and combined with seasonal changes, environmental parameters and time series, preliminary energy-saving strategies are generated according to preset rules and conditions; machine learning models are trained based on historical data, machine learning algorithms are used to predict the best energy-saving strategies, and genetic algorithms are used to iteratively optimize energy-saving strategies; according to the optimized strategies, the operating status of electrical equipment is controlled in real time through actuators, and users are provided with monitoring data, adjustment settings and customized strategies, while safety monitoring and anomaly detection are implemented to ensure electrical safety.

[0006] As a preferred solution of the method for autonomous energy saving of dormitory air conditioning electricity described in the present invention, the obtained data includes real-time collection of personnel activity data, environmental condition data, time data and air conditioning equipment status data in the dormitory through sensors.

[0007] The personnel activity data includes whether there are people, the intensity of people's exercise, and the breathing and heart rate of people; the environmental condition data includes indoor temperature, indoor humidity, indoor light intensity, outdoor temperature and humidity; the time data includes current time and historical energy consumption data; the air-conditioning equipment status data includes air-conditioning switch status, air-conditioning set temperature and air-conditioning operation mode.

[0008] The preprocessing includes denoising, removing outliers, filling missing values, data normalization and data conversion.

[0009] As a preferred solution of the method for autonomous energy saving of dormitory air conditioning electricity described in the present invention, the feature extraction includes real-time monitoring of the activity status of people and environmental conditions in the dormitory through sensors, preprocessing the obtained data, and extracting features from the preprocessed data.

[0010] The feature extraction also includes human activity recognition feature extraction, environmental parameter feature extraction and time series feature extraction.

[0011] As a preferred solution of the method for autonomous energy saving of dormitory air-conditioning electricity described in the present invention, the generation of a preliminary energy-saving strategy includes analyzing the extracted features, identifying personnel activity patterns, and combining seasonal changes, environmental parameters and time series to generate a preliminary energy-saving strategy according to preset rules and conditions.

[0012] The preset rules and conditions generate a preliminary energy-saving strategy including automatically shutting down air conditioners and large electrical equipment when the sensor detects that there is no one in the dormitory.

[0013] As a preferred solution of the method for autonomous energy saving of dormitory air-conditioning electricity described in the present invention, the training of the machine learning model includes selecting a random forest algorithm to build a model, training the random forest model with historical data, constructing a loss function, and optimizing the random forest model with the loss function, and evaluating the predictive performance of the random forest model.

[0014] The formula of the random forest algorithm is: , in, is the prediction result of the random forest algorithm, T is the number of decision trees in the random forest, is the prediction result of the t-th decision tree for the input feature vector x, where x is the input feature vector.

[0015] , in, is the final prediction result of the random forest model. is the majority voting function, T is the number of decision trees in the random forest, The prediction results of all random forest algorithms.

[0016] The use of historical data to train the model includes feature selection, sample data, self-service sampling, decision tree construction, random forest aggregation and energy-saving strategy prediction; The loss function formula is: , in, is the loss function, M is the number of historical data samples, is the actual energy-saving label of the jth sample, j is the current sample, T is the number of decision trees in the random forest, is the parameter set of all decision trees in the random forest, is the parameter of the t-th decision tree, The feature vector x of the jth sample is obtained by passing the parameter of the tth decision tree Calculate the predicted value obtained, The historical energy saving effect of the jth sample affects the function, x is the input feature vector, is the historical data vector of the jth sample, e is the base of the natural logarithm, ln is the natural logarithm function, and S is the Sigmoid function.

[0017] The specific formula of the Sigmoid function is: , Where S is the Sigmoid function, The feature vector x of the jth sample is obtained by passing the parameter of the tth decision tree Calculate the predicted value obtained, The historical energy saving effect of the jth sample affects the function, x is the input feature vector, is the historical data vector of the jth sample, e is the base of the natural logarithm, and T is the number of decision trees in the random forest.

[0018] The historical energy saving effect impact function formula is: , in, The historical energy saving effect influence function of the jth sample, is the number of time periods for historical data, is the weight of the kth time period, is the energy saving effect of the jth sample in the kth time period.

[0019] As a preferred solution of the method for autonomous energy saving of dormitory air-conditioning electricity consumption described in the present invention, the iterative optimization of the energy-saving strategy includes: optimizing the energy-saving strategy using a genetic algorithm, balancing energy saving and comfort, and controlling the operating status of the air conditioner and remaining electrical equipment in real time through the actuator according to the generated energy-saving strategy, and providing a user-friendly interface to allow the user to view energy consumption data, adjust set parameters and customize personal energy-saving strategies. The system learns the user's preferences based on the user's adjustments and feedback and optimizes the energy-saving strategy.

[0020] The genetic algorithm construction framework includes encoding, fitness evaluation, selection, crossover, mutation, new generation population and optimization results.

[0021] As a preferred solution of the method for autonomous energy saving of dormitory air-conditioning electricity described in the present invention, the safety monitoring and abnormality detection include an algorithm that continuously monitors the status of electrical equipment, promptly detects abnormal conditions such as overload and overheating, and when potential safety issues are detected, the system will automatically take emergency measures to cut off power supply and notify management personnel; and adopt redundant design and failover mechanism to ensure the availability of key components, implement data encryption and access control, and prevent unauthorized access and network attacks.

[0022] Another object of the present invention is to provide a system for autonomous energy saving of electricity for dormitory air conditioners. The system of the present invention solves the current problem of energy saving of electricity in workers' dormitories and employee dormitories. The system of the present invention realizes intelligent control of air conditioners and remaining electrical equipment in dormitories through real-time monitoring and data processing, thereby improving energy saving efficiency and comfort. The user-friendly interface and customized strategy functions enhance the interactivity between users and the system, allowing users to monitor and adjust equipment operation more conveniently. The system's safety monitoring and abnormality detection functions ensure electrical safety and improve the reliability of the overall system.

[0023] As a preferred solution of the system for autonomous energy saving of dormitory air conditioning electricity described in the present invention, it is characterized by including a sensor data acquisition module, a data preprocessing module, a preliminary energy-saving strategy generation module, a machine learning module, a genetic algorithm iterative optimization module and a safety monitoring and anomaly detection module.

[0024] The sensor data acquisition module is used to monitor the activity status of personnel, environmental conditions, time data and air conditioning equipment status in the dormitory in real time.

[0025] The data preprocessing module is used for denoising, removing outliers, filling missing values, data normalization, data conversion and feature extraction.

[0026] The preliminary energy-saving strategy generation module is used to analyze the extracted features, identify personnel activity patterns, combine seasonal changes, environmental parameters and time series, and generate a preliminary energy-saving strategy according to preset rules and conditions.

[0027] The machine learning module is used to construct a random forest algorithm to build a model, use historical data to train the random forest model, construct a loss function, use the loss function to optimize the random forest model, and evaluate the prediction performance of the random forest model.

[0028] The genetic algorithm iterative optimization module is used to use genetic algorithms to optimize energy-saving strategies, balance energy saving and comfort, and control the operating status of air conditioners and remaining electrical equipment in real time through actuators based on the generated energy-saving strategies. It provides a user-friendly interface that allows users to view energy consumption data, adjust setting parameters, and customize personal energy-saving strategies. The system learns user preferences based on user adjustments and feedback and optimizes energy-saving strategies.

[0029] The full monitoring and anomaly detection module is used to continuously monitor the status of electrical equipment and promptly detect abnormal conditions such as overload and overheating. When a potential safety problem is detected, the system will automatically take emergency measures to cut off the power supply and notify the management personnel. It adopts redundant design and failover mechanism to ensure the availability of key components, implements data encryption and access control, and prevents unauthorized access and network attacks.

[0030] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, the steps of a method for autonomous energy saving of dormitory air conditioning are implemented.

[0031] A computer-readable storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the steps of a method for autonomous energy saving of dormitory air conditioning electricity.

[0032] Beneficial effects of the present invention: The present invention realizes autonomous energy-saving control of air conditioners and remaining electrical equipment in dormitories by real-time monitoring of environmental conditions and personnel activity status, combined with historical data and machine learning algorithms. The system can predict and optimize the operation mode of the air conditioner to achieve a balance between energy saving and comfort, while providing a user-friendly interface that allows users to monitor data, adjust settings and customize strategies. In addition, the system also implements safety monitoring and anomaly detection to ensure electrical safety, including improved energy efficiency, optimized comfort, enhanced user interaction, improved safety, automated control, historical data utilization, flexibility and scalability, cost-effectiveness, environmental protection contribution, and improved intelligence level. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work, among which: Figure 1 An overall flow chart of a method for autonomous energy saving of dormitory air conditioning electricity provided by an embodiment of the present invention.

[0034] Figure 2 An overall layout diagram of a method for autonomous energy saving of dormitory air conditioning electricity provided by an embodiment of the present invention.

[0035] Figure 3 A software flow overview diagram of a method for autonomous energy saving of dormitory air conditioning electricity provided by an embodiment of the present invention.

[0036] Figure 4 A system solution flow chart of a system for autonomous energy saving of dormitory air conditioning electricity provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0037] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0038] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0039] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it an embodiment that is mutually exclusive with other embodiments, either individually or selectively.

[0040] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0041] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0042] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0043] Example 1, reference Figure 1-Figure 3 , which is the first embodiment of the present invention, provides a method for autonomous energy saving of dormitory air conditioning electricity, comprising: S1: Use sensors to monitor the activity status and environmental conditions of people in the dormitory in real time, preprocess the obtained data, and extract features from the preprocessed data.

[0044] The data obtained include personnel activity data, environmental condition data, time data and air conditioning equipment status data in the dormitory collected in real time through sensors.

[0045] The personnel activity data includes whether there are people, the intensity of people's exercise, and the breathing and heart rate of people; the environmental condition data includes indoor temperature, indoor humidity, indoor light intensity, outdoor temperature and humidity; the time data includes current time and historical energy consumption data; the air-conditioning equipment status data includes air-conditioning switch status, air-conditioning set temperature and air-conditioning operation mode.

[0046] The preprocessing includes denoising, removing outliers, filling missing values, data normalization and data conversion; the outlier removal includes setting an abnormal threshold, comparing the collected data with the threshold, and determining the data with an absolute value higher than the threshold as abnormal and removing it. The threshold calculation formula is: , in, is the threshold value, is the data point, is the average value, is the standard deviation.

[0047] The missing value filling formula is: , in, is a missing value, is the data point before the missing value, is the data point after the missing value.

[0048] The data normalization formula is: , in, is the normalized data, is the data point, is the minimum value of the data, is the maximum value of the data.

[0049] The data conversion formula is: , in, is the logarithmic transformed data, is the data point.

[0050] The feature extraction includes monitoring the activity status of personnel and environmental conditions in the dormitory in real time through sensors, preprocessing the obtained data, and extracting features from the preprocessed data.

[0051] The feature extraction also includes human activity recognition feature extraction, environmental parameter feature extraction and time series feature extraction; the human activity recognition feature extraction includes activity frequency extraction and activity intensity extraction; the environmental parameter feature extraction includes temperature feature extraction, humidity feature extraction and light intensity feature extraction; the time series feature extraction includes daily cycle feature extraction, cycle feature extraction and seasonal feature extraction; the activity intensity extraction formula is: , in, is the activity signal strength and, is the activity intensity of the ath signal, is the signal strength in the static state, and N is the number of signals.

[0052] S2: Analyze the extracted features, identify the activity patterns of people, and generate preliminary energy-saving strategies based on preset rules and conditions in combination with seasonal changes, environmental parameters and time series.

[0053] Furthermore, the generating of the preliminary energy-saving strategy includes analyzing the extracted features, identifying the activity patterns of personnel, and generating the preliminary energy-saving strategy according to preset rules and conditions in combination with seasonal changes, environmental parameters and time series.

[0054] The preset rules and conditions generate a preliminary energy-saving strategy, including automatically shutting down the air conditioner and large electrical equipment when the sensor detects that there is no one in the dormitory; maintaining or adjusting the operating status of the air conditioner and large electrical equipment when the sensor detects that there is someone in the dormitory; in summer, adjusting the air conditioner shutdown delay time according to the outdoor temperature; in winter, adjusting the air conditioner usage time according to the outdoor temperature; setting environmental parameter thresholds, when the indoor temperature is higher than the preset threshold, the system automatically starts the air conditioner cooling mode; when the indoor temperature is lower than the preset threshold, the system automatically stops the air conditioner; between 10 pm and 6 am, the system will recommend shutting down the air conditioner to save energy; during the daytime on weekdays, the system will adjust the air conditioner operation mode according to the outdoor temperature; by collecting and analyzing the activity data of people in the dormitory, the system automatically shuts down the air conditioner when the person leaves the dormitory, and turns on the air conditioner in advance before the person returns to the dormitory.

[0055] S3: Train the machine learning model based on historical data, use the machine learning algorithm to predict the optimal energy-saving strategy, and use the genetic algorithm to iteratively optimize the energy-saving strategy.

[0056] Furthermore, the training of the machine learning model includes selecting a random forest algorithm to build a model, training the random forest model using historical data, building a loss function, optimizing the random forest model using the loss function, and evaluating the predictive performance of the random forest model.

[0057] The formula of the random forest algorithm is: , in, is the prediction result of the random forest algorithm, T is the number of decision trees in the random forest, is the prediction result of the t-th decision tree for the input feature vector x, where x is the input feature vector.

[0058] , in, is the final prediction result of the random forest model. is the majority voting function, T is the number of decision trees in the random forest, and is used in classification problems to select the category with the most occurrences from the prediction results of all decision trees as the final prediction. The prediction results of all random forest algorithms.

[0059] The model training using historical data includes feature selection, sample data, self-service sampling, decision tree construction, random forest aggregation and energy-saving strategy prediction; the feature selection includes selecting features associated with energy saving, such as current temperature, humidity, air conditioning set temperature and historical energy consumption; the sample data includes extracting samples from historical data, and the feature vectors contained in the samples and the corresponding actual energy consumption and energy-saving efficiency labels; the self-service sampling includes self-service sampling of the original data set, and each sampling obtains a sub-data set; the decision tree construction includes constructing a decision tree for each sub-data set, and randomly selecting a feature subset at each node of the tree for segmentation; the random forest aggregation includes voting on the prediction results of all decision trees to obtain the final prediction of the random forest; the energy-saving strategy prediction includes using the trained random forest model to predict the energy-saving strategy of the new input feature vector; wherein, for classification problems, The value range of is [0,1], which indicates the probability of the energy-saving strategy being adopted.

[0060] The loss function formula is: , in, is the loss function used to evaluate the overall prediction performance of the random forest model, M is the number of historical data samples, is the actual energy-saving label of the jth sample, j is the current sample, T is the number of decision trees in the random forest, is the parameter set of all decision trees in the random forest, is the parameter of the t-th decision tree, The feature vector x of the jth sample is obtained by passing the parameter of the tth decision tree Calculate the predicted value obtained, The historical energy saving effect of the jth sample affects the function, x is the input feature vector, is the historical data vector of the jth sample, e is the base of the natural logarithm, ln is the natural logarithm function, and S is the Sigmoid function.

[0061] The specific formula of the Sigmoid function is: , Where S is the Sigmoid function, The feature vector x of the jth sample is obtained by passing the parameter of the tth decision tree Calculate the predicted value obtained, The historical energy saving effect of the jth sample affects the function, x is the input feature vector, is the historical data vector of the jth sample, e is the base of the natural logarithm, and T is the number of decision trees in the random forest.

[0062] The historical energy saving effect impact function formula is: , in, The historical energy saving effect influence function of the jth sample, is the number of time periods for historical data, is the weight of the kth time period, is the energy saving effect of the jth sample in the kth time period.

[0063] Furthermore, the iterative optimization of the energy-saving strategy includes using a genetic algorithm to optimize the energy-saving strategy, balancing energy saving and comfort, and according to the generated energy-saving strategy, controlling the operating status of the air conditioner and remaining electrical equipment in real time through the actuator, and providing a user-friendly interface, allowing the user to view energy consumption data, adjust set parameters and customize personal energy-saving strategies. The system learns the user's preferences based on the user's adjustments and feedback and optimizes the energy-saving strategy.

[0064] The genetic algorithm construction framework includes encoding, fitness evaluation, selection, crossover, mutation, new generation population and optimization results; the encoding includes individual representation and population initialization; the fitness evaluation includes fitness function and evaluation process; the selection includes selection mechanism and diversity maintenance; the individual representation includes each energy-saving strategy represented by an individual, the individual's gene is encoded as binary and real number, and each gene represents a parameter in the strategy; the population initialization includes randomly generating a set of initial energy-saving strategies as the starting point of the population; the fitness function includes defining a fitness function to evaluate the energy-saving effect and user comfort of each individual, and the fitness function should comprehensively consider the energy saving amount, user satisfaction and safety. Comprehensive factors; the evaluation process includes simulating each individual in the population and calculating the fitness score according to the fitness function; the selection mechanism includes selecting from high to low according to the fitness score of the individual, and the individual with the highest fitness will be selected to enter the next generation; the diversity maintenance includes introducing randomness to avoid premature convergence and maintain population diversity; the crossover includes the selected individuals generating new offspring through single-point crossover, multi-point crossover and uniform crossover, setting a crossover probability, and controlling the way new individuals are generated in the population to balance exploration and utilization; the optimization result includes selecting the individual with the highest fitness from the final population as the optimal energy-saving strategy, and adjusting the actual energy-saving system parameters according to the optimal strategy.

[0065] S4: Based on the optimized strategy, the operating status of the electrical equipment is controlled in real time through the actuator, and the user is provided with monitoring data, adjustment settings and customized strategies. At the same time, safety monitoring and anomaly detection are implemented to ensure electrical safety.

[0066] like Figure 3The safety monitoring and anomaly detection include algorithms that continuously monitor the status of electrical equipment and promptly detect abnormal conditions such as overload and overheating. When potential safety issues are detected, the system will automatically take emergency measures to cut off power supply and notify management personnel; and adopt redundant design and failover mechanism to ensure the availability of key components, implement data encryption and access control, and prevent unauthorized access and network attacks.

[0067] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0068] Example 2, reference Figure 4 , which is the second embodiment of the present invention, and this embodiment provides a system for autonomous energy saving of dormitory air conditioning electricity consumption, including a sensor data acquisition module 100, a data preprocessing module 200, a preliminary energy saving strategy generation module 300, a machine learning module 400, a genetic algorithm iterative optimization module 500 and a safety monitoring and anomaly detection module 600.

[0069] The sensor data acquisition module 100 is used to monitor the activity status of personnel, environmental conditions, time data and air conditioning equipment status in the dormitory in real time.

[0070] The data preprocessing module 200 is used for denoising, removing outliers, filling missing values, data normalization, data conversion and feature extraction.

[0071] The preliminary energy-saving strategy generation module 300 is used to analyze the extracted features, identify personnel activity patterns, and generate a preliminary energy-saving strategy according to preset rules and conditions in combination with seasonal changes, environmental parameters and time series.

[0072] The machine learning module 400 is used to construct a random forest algorithm model, train the random forest model using historical data, construct a loss function, optimize the random forest model using the loss function, and evaluate the prediction performance of the random forest model.

[0073] The genetic algorithm iterative optimization module 500 is used to use genetic algorithms to optimize energy-saving strategies, balance energy saving and comfort, and control the operating status of air conditioners and remaining electrical equipment in real time through actuators based on the generated energy-saving strategies. It provides a user-friendly interface that allows users to view energy consumption data, adjust setting parameters and customize personal energy-saving strategies. The system learns user preferences based on user adjustments and feedback and optimizes energy-saving strategies.

[0074] The full monitoring and anomaly detection module 600 is used to continuously monitor the status of electrical equipment and promptly detect abnormal conditions such as overload and overheating. When a potential safety problem is detected, the system will automatically take emergency measures to cut off the power supply and notify the management personnel. It adopts redundant design and failover mechanism to ensure the availability of key components, implements data encryption and access control, and prevents unauthorized access and network attacks.

[0075] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0076] Embodiment 3, the third embodiment of the present invention, is different from the first two embodiments in that: If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0077] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0078] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0079] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

Claims

1. A method for autonomous energy saving of dormitory air conditioning electricity, characterized in that: include, The sensors are used to monitor the activity status and environmental conditions of people in the dormitory in real time, and the acquired data is preprocessed and features are extracted from the preprocessed data; Analyze the extracted features, identify the activity patterns of people, and generate preliminary energy-saving strategies based on preset rules and conditions in combination with seasonal changes, environmental parameters and time series; Select the random forest algorithm to build a machine learning model, train the machine learning model based on historical data, use the machine learning algorithm to predict the best energy-saving strategy, and use the genetic algorithm to iteratively optimize the energy-saving strategy; The formula of the random forest algorithm is: , in, is the prediction result of the random forest algorithm, T is the number of decision trees in the random forest, is the prediction result of the t-th decision tree for the input feature vector x, where x is the input feature vector; According to the optimized strategy, the operating status of electrical equipment is controlled in real time through the actuator, and users are provided with monitoring data, adjustment settings and customized strategies. At the same time, safety monitoring and anomaly detection are implemented to ensure electrical safety.

2. The method for autonomous energy saving of dormitory air conditioning electricity as claimed in claim 1, characterized in that: The data obtained includes real-time data of personnel activities, environmental conditions, time and air conditioning equipment status in the dormitory collected by sensors; The preprocessing includes denoising, removing outliers, filling missing values, data normalization and data conversion.

3. The method for autonomous energy saving of dormitory air conditioning electricity as claimed in claim 2, characterized in that: The feature extraction includes monitoring the activity status and environmental conditions of people in the dormitory in real time through sensors, preprocessing the obtained data, and extracting features from the preprocessed data; The feature extraction also includes human activity recognition feature extraction, environmental parameter feature extraction and time series feature extraction.

4. The method for autonomous energy saving of dormitory air conditioning electricity as claimed in claim 3, characterized in that: The generating of the preliminary energy-saving strategy includes analyzing the extracted features, identifying the activity patterns of personnel, and generating the preliminary energy-saving strategy according to preset rules and conditions in combination with seasonal changes, environmental parameters and time series.

5. The method for autonomous energy saving of dormitory air conditioning electricity as claimed in claim 4, characterized in that: The training machine learning model includes selecting a random forest algorithm to build a model, using historical data to train the random forest model, building a loss function, optimizing the random forest model using the loss function, and evaluating the prediction performance of the random forest model. The formula is expressed as: , in, is the final prediction result of the random forest model. is the majority voting function, T is the number of decision trees in the random forest, is the prediction result of all random forest algorithms; The use of historical data to train the model includes feature selection, sample data, self-service sampling, decision tree construction, random forest aggregation and energy-saving strategy prediction; The loss function formula is: , in, is the loss function, M is the number of historical data samples, is the actual energy-saving label of the jth sample, j is the current sample, T is the number of decision trees in the random forest, is the parameter set of all decision trees in the random forest, is the parameter of the t-th decision tree, The feature vector x of the jth sample is obtained by passing the parameter of the tth decision tree Calculate the predicted value obtained, The historical energy saving effect of the jth sample affects the function, x is the input feature vector, is the historical data vector of the jth sample, e is the base of the natural logarithm, ln is the natural logarithm function, and S is the Sigmoid function; The specific formula of the Sigmoid function is: , Where S is the Sigmoid function, The feature vector x of the jth sample is obtained by passing the parameter of the tth decision tree Calculate the predicted value obtained, The historical energy saving effect of the jth sample affects the function, x is the input feature vector, is the historical data vector of the jth sample, e is the base of the natural logarithm, and T is the number of decision trees in the random forest; The historical energy saving effect impact function formula is: , in, The historical energy saving effect influence function of the jth sample, is the number of time periods for historical data, is the weight of the kth time period, is the energy saving effect of the jth sample in the kth time period.

6. The method for autonomous energy saving of dormitory air conditioning electricity as claimed in claim 5, characterized in that: The iterative optimization of the energy-saving strategy includes optimizing the energy-saving strategy using a genetic algorithm, balancing energy saving and comfort, and controlling the operating status of the air conditioner and the remaining electrical equipment in real time through an actuator according to the generated energy-saving strategy, and providing a user-friendly interface to allow the user to view energy consumption data, adjust setting parameters and customize personal energy-saving strategies. The system learns the user's preferences based on the user's adjustments and feedback and optimizes the energy-saving strategy; The genetic algorithm construction framework includes encoding, fitness evaluation, selection, crossover, mutation, new generation population and optimization results.

7. A method for autonomous energy saving of dormitory air conditioning electricity as claimed in claim 6, characterized in that: The safety monitoring and anomaly detection include algorithms that continuously monitor the status of electrical equipment and promptly detect abnormal conditions such as overload and overheating. When potential safety issues are detected, the system will automatically take emergency measures to cut off power supply, notify management personnel, implement data encryption and access control, and prevent unauthorized access and network attacks.

8. A system using the method for autonomous energy saving of dormitory air conditioning electricity as claimed in any one of claims 1 to 7, characterized in that: It includes sensor data acquisition module, data preprocessing module, preliminary energy-saving strategy generation module, machine learning module, genetic algorithm iterative optimization module, and safety monitoring and anomaly detection module; The sensor data acquisition module is used to monitor the activity status of personnel, environmental conditions, time data and air conditioning equipment status in the dormitory in real time; The data preprocessing module is used for denoising, removing outliers, filling missing values, data normalization, data conversion and feature extraction; The preliminary energy-saving strategy generation module is used to analyze the extracted features, identify the activity patterns of personnel, combine seasonal changes, environmental parameters and time series, and generate preliminary energy-saving strategies according to preset rules and conditions; The machine learning module is used to construct a model using a random forest algorithm, train the random forest model using historical data, construct a loss function, optimize the random forest model using the loss function, and evaluate the prediction performance of the random forest model; The genetic algorithm iterative optimization module is used to optimize the energy-saving strategy using the genetic algorithm, balance energy saving and comfort, and control the operating status of the air conditioner and the remaining electrical equipment in real time through the actuator according to the generated energy-saving strategy, and provide a user-friendly interface to allow the user to view energy consumption data, adjust setting parameters and customize personal energy-saving strategies. The system learns the user's preferences and optimizes the energy-saving strategy based on the user's adjustments and feedback; The full monitoring and anomaly detection module is used to continuously monitor the status of electrical equipment and promptly detect abnormal conditions such as overload and overheating. When a potential safety problem is detected, the system will automatically take emergency measures to cut off the power supply and notify the management personnel. It adopts redundant design and failover mechanism to ensure the availability of key components, implements data encryption and access control, and prevents unauthorized access and network attacks.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for autonomous energy saving of dormitory air conditioning electricity as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a method for autonomous energy saving of dormitory air conditioning electricity as described in any one of claims 1 to 7 are implemented.

Citation Information

Patent Citations

  • Systems, methods, devices, and platforms for industrial internet of things

    CA3252125A1

  • System for heating, ventilation, air-conditioning

    CN112240626A

  • Energy-saving optimization method and system for air conditioning system

    CN112415924A

  • Remote monitoring system and method for old-age care facilities

    CN117854730A

  • Parking air conditioner control method and parking air conditioner

    CN118306175A

Cited By

  • P2p remote communication method

    CN119892845A

  • Airplane ground air conditioner energy-saving control method combined with environmental parameter prediction

    CN121224993A