Intelligent electric water heater remote regulation and control and energy efficiency management system based on Internet of Things

Abstract

The invention relates to an intelligent electric water heater remote regulation and control and energy efficiency management system based on the Internet of Things, and relates to the field of intelligent management. In response to a terminal starting instruction, a geographic position data set is obtained, the home distance between the terminal nodes and nearest neighbor terminal nodes is counted, and a user arrival time prediction value is generated according to a preset speed constant parameter; when the starting instruction does not comprise a first temperature setting constant of the nearest terminal node of temperature value statistics and a second temperature setting constant of the request equipment terminal, the larger value is extracted and set as a target temperature value, and the arrival time prediction value is used as a heating period target value and is combined with the target temperature value to be sent to the request equipment terminal to obtain a feedback instruction; and when the instruction is confirmed, the energy consumption optimization model is executed to solve output power time sequence information, and the output power time sequence information is applied to a PID control loop of the electric water heater. The problem that the intelligent electric water heater is poor in remote regulation and control intellectualization and energy efficiency management performance is solved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent management, and in particular to an intelligent electric water heater remote control and energy efficiency management system based on the Internet of Things. Background Art

[0002] With the continuous development and popularization of Internet of Things technology, smart home products have gradually become an important part of modern families. Among them, electric water heaters, as an indispensable hot water supply device in family life, have become the focus of industry attention in terms of intelligence and energy efficiency management. Traditional electric water heaters usually require users to manually set the heating time and temperature when in use. This operation method is not only cumbersome, but also often cannot be intelligently adjusted according to the actual needs of users. In addition, due to the different habits of users in using hot water, there is also a lack of unified standards for the heating time and temperature settings of electric water heaters, resulting in high energy consumption and serious waste of resources. However, most of the existing intelligent electric water heater remote control systems can only realize simple remote control functions, and lack in-depth research on user behavior, temperature settings, and energy consumption management. Summary of the invention

[0003] The present invention aims to solve the technical problems in the prior art that the intelligent electric water heater remote control system is insufficient in user behavior prediction accuracy, temperature setting rationality and energy consumption management efficiency, and has poor intelligence and energy efficiency management performance, and provides an intelligent electric water heater remote control and energy efficiency management system based on the Internet of Things to solve the problems.

[0004] The technical solution of the present invention to solve the above technical problems is as follows:

[0005] The present invention provides an intelligent electric water heater remote control and energy efficiency management system based on the Internet of Things, and the execution steps include: in response to a startup instruction of a device terminal, obtaining a geographic location data set of an authorized device terminal cluster; based on the geographic location data set, counting the home distance between the nearest neighbor terminal node, and generating a user arrival time prediction value according to a preset speed constant parameter; when the startup instruction does not include a temperature value, counting the first temperature setting constant of the nearest neighbor terminal node and the second temperature setting constant of the requesting device terminal, extracting the larger value of the first temperature setting constant and the second temperature setting constant, and setting it as a target temperature value; taking the user arrival time prediction value as a heating cycle target value, sending it to the requesting device terminal in combination with the target temperature value, obtaining a feedback instruction, and when the feedback instruction is a confirmation instruction, executing an energy consumption optimization model solution, outputting power timing information and applying it to an electric water heater PID control loop.

[0006] The beneficial effects of the present invention are: by predicting the user's return home time, intelligently setting the target temperature, and performing energy consumption optimization after confirmation, intelligent preheating and energy-saving control of the electric water heater are achieved, thereby improving the convenience of use and the level of energy efficiency management. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Figure 1 A schematic flow chart of the execution steps of the smart electric water heater remote control and energy efficiency management system based on the Internet of Things provided by the present invention.

[0008] Figure 2 A flowchart of the execution steps for setting the target temperature value in the smart electric water heater remote control and energy efficiency management system based on the Internet of Things provided by the present invention. DETAILED DESCRIPTION

[0009] 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0010] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0011] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present invention.

[0012] Example:

[0013] like Figure 1As shown, the embodiment of the present invention provides an intelligent electric water heater remote control and energy efficiency management system based on the Internet of Things, and the execution steps include:

[0014] S10: In response to a start-up instruction of a device terminal, a geographic location data set of an authorized device terminal cluster is obtained.

[0015] S20: Based on the geographic location data set, the home distance between the nearest neighbor terminal node is counted, and a user arrival time prediction value is generated according to a preset speed constant parameter.

[0016] S30: When the startup instruction does not include a temperature value, count the first temperature setting constant of the nearest neighbor terminal node and the second temperature setting constant of the requesting device terminal, extract the larger value of the first temperature setting constant and the second temperature setting constant, and set it as the target temperature value.

[0017] S40: Taking the predicted value of the user arrival time as the target value of the heating cycle, combined with the target temperature value, it is sent to the requesting device terminal to obtain a feedback instruction. When the feedback instruction is a confirmation instruction, the energy consumption optimization model is solved, the power timing information is output and applied to the electric water heater PID control loop.

[0018] Exemplarily, first, when the electric water heater is in standby or inactive state, it waits to receive a start-up instruction from the user device terminal or system, which can be activated by pressing a physical button, clicking on a touch screen, sending a remote signal, or by some preset trigger condition, such as a specific time, environmental conditions, etc. Once the electric water heater receives the start-up instruction, it will immediately enter the initialization phase. At this stage, the device will perform a series of self-check operations to ensure that all hardware and software components are in normal working condition. At the same time, the device will load the necessary configuration information and security settings to ensure the accuracy and security of subsequent operations. Next, the user device terminal will verify whether it belongs to an authorized device cluster, which usually involves communication with a server or central control system, and confirming the authorization status of the device by comparing the device ID, serial number or other unique identifier. Only verified devices can continue to perform subsequent operations to ensure that data access and transmission are limited to legal and authorized devices. Once the user device is confirmed to be authorized, it starts to collect geographic location data, which usually involves using a built-in GPS module, network positioning services (such as base station positioning, Wi-Fi positioning, etc.) or other positioning technologies to determine the current location of the user device. The device will organize this location information into a data set for subsequent analysis and processing. In the process of collecting geographic location data, the device terminal may perform multiple measurements and calibrations to improve the accuracy and reliability of the data. At the same time, the device will also consider privacy and security factors to ensure compliance with relevant regulations and privacy policies when collecting, storing and transmitting geographic location data. Finally, the device terminal will send the collected geographic location data set to the designated server or central control system for further processing and analysis. This data can be used for a variety of purposes, such as monitoring the distribution of device clusters, optimizing resource allocation, and providing location-related services or functions. In summary, obtaining the geographic location data set of the authorized device terminal cluster in response to the startup instruction of the device terminal is a coherent process involving multiple steps such as initialization, verification of authorization, data collection, and data processing. This process ensures the accuracy, security and legality of the data, and provides strong support for subsequent decision-making and services.

[0019] Furthermore, the data points in the data set containing the geographic locations of multiple device terminals represent the current locations of each terminal in the cluster. The goal at this time is to calculate the distance from each terminal node to its home, which can be understood as a preset destination or reference point, such as the user's residence, workplace, etc., especially the home distance between the nearest neighbor terminal node. A neighbor terminal node refers to another terminal node that is relatively closest to a specific terminal node in the geographic location data set. The close here is relative, and is usually determined by calculating the distance between two nodes. The distance can be a straight-line distance or an actual driving distance considering factors such as road networks. When looking for the nearest neighbor terminal node, a nearest neighbor search operation is actually performed. The purpose is to find a node with the smallest distance to a specific node in a given geographic location data set. The node found is the nearest neighbor terminal node of the specific node. The determination of the neighbor terminal node is crucial for the subsequent calculation of the home distance and the generation of the user arrival time prediction value, because it narrows the search range and makes the calculation more efficient and accurate. Next, the user arrival time prediction value is generated using the preset speed constant parameter. This speed constant represents the average moving speed of the user under specific conditions, such as walking, cycling, driving, etc. A rough estimate of the arrival time can be obtained by dividing the distance home by the speed constant. It should be noted that this prediction is based on a series of assumptions and simplifications. For example, it ignores the impact of factors such as traffic congestion, weather conditions, and changes in user behavior on the actual driving time. Therefore, in practical applications, the prediction value may need to be adjusted and optimized in combination with real-time traffic data, user historical behavior patterns and other information. Finally, the generated arrival time prediction values ​​are stored for subsequent analysis, reporting or reminder functions. These prediction values ​​are of great significance for users to plan their trips, arrange time or make decisions.

[0020] Optionally, when the electric water heater receives a start-up instruction and the instruction does not contain a temperature value, the system will start a series of processes to set a target temperature value. First, after receiving a start-up instruction that does not contain a temperature value, it will enter the initialization phase and verify whether it belongs to an authorized device cluster. Once the verification is passed, it will prepare to collect necessary configuration information and status data for subsequent operations. Next, the system will determine the nearest neighbor terminal node, which involves analyzing the geographic location data set to find another authorized terminal node that is closest to the requesting device terminal. The selection of this nearest neighbor terminal node is crucial for the subsequent acquisition of temperature setting constants. Once the nearest neighbor terminal node is determined, the system will query the first temperature setting constant of the node, which represents the expected temperature value of the node under specific conditions (such as default settings, user preferences, energy-saving mode, etc.). At the same time, the system will also query the second temperature setting constant of the requesting device terminal to obtain the temperature setting preference of the terminal itself. After obtaining the two temperature setting constants, a comparison operation is performed to extract the larger value between them. The purpose of this step is to ensure that the target temperature value will not be lower than the expected temperature of any node to meet possible temperature requirements or preferences. Finally, the extracted larger value is set as the target temperature value and stored in an appropriate location for subsequent use. This target temperature value can be used to control the temperature setting of the electric water heater, such as the operating status of the heater and other equipment, to achieve the desired indoor temperature. It should be noted that the temperature setting constant in this process may be a preset default value, or it may be dynamically adjusted based on the user's historical behavior, preferences, or current environmental conditions. In addition, the system may consider other factors such as energy-saving requirements, equipment performance limitations, etc. to further optimize the setting of the target temperature value. In summary, when the startup instruction does not include a temperature value, the system will query the temperature setting constants of the nearest neighbor terminal node and the requesting device terminal, and extract the larger value among them to set the target temperature value. This process provides users with flexible temperature control options and ensures temperature comfort and energy saving.

[0021] For example, suppose there is a smart home system that includes multiple smart devices, including a smart water heater. Users can remotely control these devices through a mobile phone app. Now, the user presses the button to start the smart water heater by pressing the preset key, but does not enter a specific temperature value. The system verifies whether the user's device (mobile phone app) belongs to the authorized device cluster. Then, the relevant configuration information of the smart water heater, such as device ID, model, current status, etc., is initialized. Then, the geographic location data set is analyzed to find another authorized terminal node that is closest to the requesting device, such as the user's smartphone at an authorized location. The system queries the first temperature setting constant of the nearest neighbor terminal node (smartphone). Assume that a comfortable bathing water temperature of 42°C is preset on the user's smartphone, and this value is used as the first temperature setting constant. At the same time, the system also queries the second temperature setting constant of the requesting device terminal (smart water heater). Assume that a default water temperature of 40°C is preset on the smart water heater, and this value is used as the second temperature setting constant. The first temperature setting constant (42°C) and the second temperature setting constant (40°C) are compared, and the larger value 42°C is extracted. The system sets 42°C as the target temperature value and prepares to send it to the smart electric water heater for heating control. The system sends a confirmation request for the target temperature value to the user, and the user clicks the confirmation button on the mobile phone APP. After that, the system starts to solve the energy consumption optimization model and calculates the optimal heating power timing information based on factors such as the user's historical water usage habits and current environmental conditions. The system applies the calculated power timing information to the PID control loop of the smart electric water heater and starts the smart heating process. The smart electric water heater heats according to the target temperature value of 42°C set by the system and the optimized power timing information, ensuring that users can enjoy a comfortable water temperature when they return home, while also achieving energy-saving effects.

[0022] Specifically, the process of predicting the user's arrival time for feedback control heating is as follows. The predicted user arrival time will be used as the target value of the heating cycle and sent to the requesting device terminal (i.e., the user's mobile phone) together with the target temperature value. The system sets the predicted value of the user's arrival time as the target value of the heating cycle, which means that the electric water heater needs to complete the heating before the user is expected to arrive to ensure that the water temperature reaches the target temperature value. The target temperature value and the heating cycle target value (i.e., the predicted value of the user's arrival time) are packaged into an instruction and sent to the control system of the electric water heater. This step is to let the electric water heater know what heating state it needs to achieve and when to start or end the heating process. After receiving this information, the control system of the electric water heater will send a feedback instruction to the user, asking the user whether to confirm these settings. This confirmation step is to ensure that the user is satisfied with the settings, or that the user has the opportunity to make final adjustments to the settings. The user clicks the confirmation button on the mobile phone APP and then sends a feedback instruction to the system. This feedback instruction is usually a confirmation signal, indicating that the electric water heater has understood the instruction and is ready to start executing. After receiving the confirmation instruction of the smart electric water heater, the system will start the solution process of the energy consumption optimization model. This model takes into account a variety of factors, such as the heating efficiency of the electric water heater, the water temperature retention time, and the user's water use habits, to calculate the optimal heating power timing information. The solution of the energy consumption optimization model is a set of power timing information, which indicates the power that the electric water heater should output in different time periods. This information is used to optimize the heating process to reduce energy consumption and improve heating efficiency. The system applies the calculated power timing information to the PID (proportional-integral-differential) control loop of the smart electric water heater. The PID control loop is a commonly used control algorithm that adjusts the size of the heating power based on the difference between the current water temperature and the target temperature value and the trend of the water temperature change. Through the application of the PID control loop, the smart electric water heater can accurately control the change of water temperature to ensure that the water temperature gradually approaches and reaches the target temperature value during the heating cycle. When the smart electric water heater completes heating according to the power timing information, it will keep the water temperature fluctuating around the target temperature value (usually within a very small range) until the user arrives and starts using hot water. This process provides great convenience for users because there is no need to manually set the heating time and temperature value of the electric water heater. At the same time, the application of energy consumption optimization models and PID control loops can also achieve energy saving and improve heating efficiency.

[0023] In a preferred embodiment, based on the geographic location data set, the home distance between the nearest neighbor terminal node is counted, and a user arrival time prediction value is generated according to a preset speed constant parameter, including: counting the home path set of the nearest neighbor terminal node; traversing the home path set to perform usage frequency statistics of the nearest neighbor terminal node to obtain a usage frequency set; extracting the home path with the highest frequency in the usage frequency set from the home path set, setting it as the selected home path, extracting the distance of the selected home path, setting it as the home distance, and generating a user arrival time prediction value according to the preset speed constant parameter.

[0024] In detail, the geographic location dataset contains information such as the user's current location, the locations visited in the past, and the possible home location. This dataset is the basis for subsequent analysis. In the geographic location dataset, it is necessary to find the terminal node closest to the user's current location. This terminal node may be a place that the user frequently visits, such as home, company, or a store that he often goes to. In this process, it is assumed that this terminal node is the user's home, that is, the home node closest to the user is to be found. Once the nearest neighbor home terminal node is determined, it is necessary to count all possible paths from the user's current location to the terminal node. These paths may include different roads, bus routes, subway lines, etc. The set of these paths is the home path set. Next, traverse the home path set and count the frequency of each path used by the user. This can be achieved by analyzing the user's historical location data. For example, you can check the number of times a user has chosen a certain path to go home in the past period of time to obtain the frequency of use of the path. Finally, you will get a set containing the frequency of use of all paths, that is, the frequency of use set. After obtaining the frequency of use set, you need to select the path with the highest frequency of use as the user's selected home path. This path is most likely the path that the user will choose to go home in the current situation. After selecting the home path, extract the actual distance of the path, which is the home distance, which can be obtained through the map API or geographic information system (GIS). Finally, calculate the predicted time of the user's arrival home based on the preset speed constant parameter and the home distance. The speed constant parameter can be set according to the actual situation, such as the average walking speed, average driving speed, etc. By dividing the home distance by the speed constant parameter, a rough arrival time prediction value can be obtained.

[0025] In a preferred embodiment, the homeward path with the highest frequency in the usage frequency set is extracted from the homeward path set and set as the selected homeward path; the distance of the selected homeward path is extracted and set as the homeward distance; and a user arrival time prediction value is generated according to a preset speed constant parameter, including: obtaining a timestamp tag of the start instruction; retrieving the walking speed constant, bicycle speed constant, electric vehicle speed constant, motorcycle speed constant and car speed constant of the selected homeward path at the timestamp tag; extracting the maximum value of the walking speed constant, the bicycle speed constant, the electric vehicle speed constant, the motorcycle speed constant and the car speed constant, and setting it as the preset speed constant parameter.

[0026] Optionally, after obtaining the home distance, the predicted value of the time when the user arrives home is calculated. To this end, the timestamp tag of the start command is obtained, which represents the specific time when the user issues the home command. Then, the speed constants of the selected home path under various transportation modes corresponding to the timestamp tag are retrieved. These speed constants include walking speed constants, bicycle speed constants, electric vehicle speed constants, motorcycle speed constants and car speed constants. These speed constants represent the average speed that the user may reach on the selected home path under different transportation modes. After obtaining these speed constants, the maximum value is extracted and set as the preset speed constant parameter, which represents the fastest speed that the user may reach on the selected home path. Finally, the home distance is divided by the preset speed constant parameter to obtain the predicted value of the time when the user arrives home. This time prediction value combines multiple aspects such as geographic location analysis, user behavior analysis, time prediction and transportation mode speed constant, and provides an accurate and reliable arrival time prediction value for the water heater, thereby meeting the task requirements.

[0027] In a preferred embodiment, retrieving the walking speed constant, bicycle speed constant, electric vehicle speed constant, motorcycle speed constant and car speed constant of the selected home-returning path at the timestamp tag comprises: retrieving the walking speed monitoring value set of the selected home-returning path at the timestamp tag via the Internet; removing outliers from the walking speed monitoring value set to obtain concentrated walking speed monitoring values; extracting the maximum value of the concentrated walking speed monitoring values ​​and setting it as the walking speed constant; wherein the bicycle speed constant, the electric vehicle speed constant, the motorcycle speed constant and the car speed constant have the same determination process as the walking speed constant.

[0028] Furthermore, for the selected home path and a specific timestamp tag, that is, the time when the user issues a home command, the relevant speed monitoring values ​​are retrieved online. This process is not limited to walking speed, but also includes bicycle speed, electric vehicle speed, motorcycle speed and car speed. For each mode of transportation, a set of speed monitoring values ​​is retrieved. Taking walking speed as an example, the set of walking speed monitoring values ​​of the selected home path under the timestamp tag is retrieved online. This set may contain multiple speed values, which represent the actual speed of the user walking on the selected home path under different time periods, different weather conditions or different traffic conditions. However, these speed monitoring values ​​may contain some outliers, that is, speed values ​​that are far from other values ​​and do not conform to the actual situation. These outliers may be caused by data recording errors, equipment failures or other reasons. Therefore, it is necessary to delete outliers from the walking speed monitoring value set to obtain a more accurate and concentrated speed monitoring value set, that is, the concentrated walking speed monitoring value. Next, the maximum value is extracted from the concentrated walking speed monitoring value and set as the walking speed constant, which represents the fastest speed that the user can reach when walking on the selected home path. The same process is also applicable to determining the speed constants of bicycles, electric vehicles, motorcycles, and cars. For each mode of transportation, the corresponding speed monitoring value set is retrieved online, outliers are removed, and the maximum value is extracted as the speed constant of the mode of transportation. Through this process, the speed constants of different modes of transportation under the timestamp label of the selected home path are obtained. These speed constants will be used in the subsequent calculation of the predicted value of the user's arrival time, providing users with more accurate and reliable prediction results to ensure the fastest warming speed.

[0029] In a preferred embodiment, Figure 2 As shown, when the startup instruction does not include a temperature value, the first temperature setting constant of the nearest neighbor terminal node and the second temperature setting constant of the requesting device terminal are counted, and the larger value of the first temperature setting constant and the second temperature setting constant is extracted and set as the target temperature value, including: obtaining a cache temperature setting value set of the nearest neighbor terminal node; when the number of the cache temperature setting value sets is less than or equal to the fitting number threshold, the cache temperature setting value at the end moment of the cache temperature setting value set is used as the first temperature setting constant; when the number of the cache temperature setting value sets is greater than the fitting number threshold, the cache temperature setting value set is evaluated for a centralized value to obtain the first temperature setting constant; the configuration process of the second temperature setting constant is the same as that of the first temperature setting constant.

[0030] Preferably, the system will locate the user's nearest neighbor terminal node and retrieve the historical temperature setting records stored in the node to form a cached temperature setting value set. This set records the user's various temperature settings in the past period of time and is an important basis for analyzing the user's temperature preference. Next, check the number of this cached temperature setting value set. If the number of records in the set is small, that is, less than or equal to the preset fitting number threshold, it means that the user's historical temperature setting data is not rich enough. At this time, the system will directly use the latest (i.e., the end time) cached temperature setting value in the set as the first temperature setting constant. This is based on the assumption that the user's recent temperature preference can represent his current needs. However, if the number of cached temperature setting value sets exceeds the fitting number threshold, it means that the user has enough temperature setting history for analysis, and the system will process this set more deeply. Specifically, the system will perform a centralized value evaluation, which may include calculating statistical indicators such as the mean, median, or mode, in order to determine a value that best represents the user's temperature preference and set it as the first temperature setting constant. This process aims to extract the user's temperature preference trend from rich historical data. At the same time, for the user requesting device terminal, which may be the user's current mobile phone, smart watch or other smart home control device, the system will also execute the same process as the nearest neighbor terminal node to determine the second temperature setting constant, which includes retrieving the historical temperature setting records of the device terminal and evaluating a suitable temperature value based on the quantity and quality of the records. After obtaining the first temperature setting constant and the second temperature setting constant, the two values ​​are compared and the larger one is selected as the target temperature value. This decision is based on the assumption that the user may prefer a slightly higher indoor temperature. In summary, by comprehensively considering the user's historical temperature setting records and the information of the device terminal, a suitable target temperature value can be intelligently determined for the user, thereby providing a more personalized experience.

[0031] In a preferred embodiment, the predicted value of the user arrival time is used as the target value of the heating cycle, and is sent to the requesting device terminal in combination with the target temperature value to obtain a feedback instruction. When the feedback instruction is a confirmation instruction, the energy consumption optimization model is solved, and the power timing information is output and applied to the electric water heater PID control loop, including: through a heating simulator, the heating cycle target value and the target temperature value are processed several times to obtain several initial power timing information, wherein the heating simulator is generated based on machine learning training through multiple groups of data, and any group of the multiple groups of data includes: heating cycle target value recording data that meets the electric water heater model, target temperature value recording data and label data that identifies the power timing information; in combination with the electric water heater model and the service life of the electric water heater, several power consumptions that meet the several initial power timing information are analyzed respectively; the initial power timing information of the minimum value of the several power consumptions is extracted and set as the power timing information.

[0032] Specifically, the system will calculate the predicted time of the user's arrival home through a complex algorithm based on the user's homeward route, transportation mode, current time and other information, and use this as the target value of the heating cycle. At the same time, a target temperature value will be determined based on the user's preference or current environment. These two parameters together constitute the hot water conditions that the electric water heater needs to prepare in advance. Then these two key parameters (heating cycle target value and target temperature value) are sent to the user's request device terminal (such as a mobile phone or smart watch) to wait for the user's confirmation. If the user is satisfied with this and issues a confirmation instruction, the system enters the next stage of solving the energy consumption optimization model. In the process of solving the energy consumption optimization model, the system uses a heating simulator based on machine learning training. This simulator can predict the power timing information required by the electric water heater under different combinations of heating cycle target values ​​and target temperature values ​​by learning from multiple sets of historical data. These historical data include heating cycle target value records, target temperature value records and corresponding power timing information labels for electric water heaters of various models and different service years under specific conditions. The system uses this simulator to simulate the current heating cycle target value and target temperature value several times. Each time, an initial power timing information is generated. These initial information represent the power adjustment schemes that the electric water heater may adopt under different simulation conditions. Next, the power loss corresponding to each initial power timing information is analyzed according to the specific model and service life of the electric water heater. This step takes into account the influence of factors such as the aging degree and energy efficiency ratio of the electric water heater on energy consumption, so that the energy efficiency of different schemes can be evaluated more accurately. Finally, the scheme with the smallest power loss is extracted from several initial power timing information, determined as the final power timing information, and applied to the PID (proportional-integral-differential) control loop of the electric water heater. In this way, the electric water heater will heat according to this optimized power timing information, ensuring that hot water of the preset temperature can be provided when the user arrives home, while maximizing the use of energy. The whole process not only reflects the intelligent and personalized service characteristics of the smart home system, but also realizes the refined management of energy use through the introduction of the energy consumption optimization model, which helps to improve the user experience and environmental awareness.

[0033] In a preferred embodiment, in combination with the electric water heater model and the service life of the electric water heater, several power losses that meet the several initial power timing information are analyzed separately, including: constructing a type constraint rule: when the model of the sample electric water heater is the same as the model of the electric water heater, and the service life of the sample electric water heater is the same as the service life of the electric water heater, the type constraint rule is satisfied; constructing a control mode constraint condition: when the dynamic time warping DWT similarity between the sample power timing information and the initial power timing information is greater than or equal to the similarity threshold, it is deemed to satisfy the control mode constraint condition; extracting the first initial power timing information based on the several initial power timing information, collecting a first sample set that satisfies both the type constraint rule and the control mode constraint condition for the first initial power timing information, counting the concentrated value of the loss record power of the first sample set, setting it as the first loss power, and adding it to the several loss powers.

[0034] Exemplarily, in the process of determining the optimal power timing information of the electric water heater, in order to accurately evaluate the energy consumption corresponding to different initial power timing information, it is necessary to conduct a detailed power loss analysis on each initial scheme in combination with the model and service life of the electric water heater. First, a set of type constraint rules is constructed according to the current model and service life of the electric water heater to be controlled. This set of rules requires that the model of the sample electric water heater (i.e., the electric water heater data used for training or testing in history) must be the same as the model of the electric water heater to be controlled, and the service life of the sample electric water heater must also match the service life of the electric water heater to be controlled. Only when these two conditions are met at the same time, the sample data is considered valid and can be used for subsequent power loss analysis. Next, a control mode constraint condition is constructed to ensure that the sample power timing information and the initial power timing information have similarity in dynamic behavior. Here, the dynamic time warping (DWT) similarity is used as the evaluation criterion. When the DWT similarity of the sample power timing information and a certain initial power timing information is greater than or equal to the preset similarity threshold, the sample is considered to meet the control mode constraint condition. The purpose of this step is to filter out the sample set that is closest to the initial power timing information in terms of dynamic behavior, so as to more accurately evaluate the energy consumption of the initial solution. Then, all the initial power timing information is traversed, and for each initial solution, a sample set that satisfies the above-mentioned type constraint rules and control mode constraint conditions is extracted. The sample data in this set is the same as the model and service life of the electric water heater to be controlled and is highly similar to the initial power timing information in terms of dynamic behavior. For each such sample set, the system will count the concentrated value of the loss record electricity (which may be the average, median or other statistical indicators) as the first loss electricity corresponding to the initial power timing information. This concentrated value reflects the energy consumption that may be generated when the initial power timing information is used for heating under similar conditions. Finally, all these first loss electricity are added to the loss electricity set for subsequent comparison and selection. Through this process, the electric water heater model, service life and dynamic behavior characteristics of the power timing information can be comprehensively considered, and the energy consumption of each initial solution can be accurately evaluated, so as to select the optimal power timing information for the actual control of the electric water heater, ensuring energy optimization.

[0035] In a preferred embodiment, the heating cycle target value and the target temperature value are processed several times by a heating simulator to obtain several initial power timing information, and also includes: according to the heating simulator, the heating cycle target value and the target temperature value are processed to obtain first initial power timing information; the dynamic time warping DWT similarity set between the first initial power timing information and the generated initial power timing information is calculated; when any one of the dynamic time warping DWT similarity sets is less than a similarity threshold, the first initial power timing information is regenerated.

[0036] Specifically, according to the heating cycle target value (i.e., the expected hot water usage time range) and the target temperature value (the expected hot water temperature) set by the user, a pre-trained heating simulator is used for preliminary processing. This simulator is built based on a large amount of historical data and machine learning algorithms, and can simulate the power adjustment strategy of the electric water heater in different time periods according to different input conditions, thereby generating an initial power timing information, i.e., the first initial power timing information. However, in actual applications, there may be multiple different power timing information that can meet the needs of users, and these schemes may have large differences in energy consumption, heating efficiency, etc. Therefore, the system needs to ensure that the generated power timing information has sufficient diversity and distribution range so as to select the best scheme from it. In order to achieve this goal, the dynamic time warping (DWT) similarity between the first initial power timing information and all the initial power timing information that have been generated before is calculated. DWT is an algorithm for measuring the similarity between two time series. It can take into account the expansion and bending of the time series on the time axis, so it is very suitable for evaluating the similarity between different power timing information. These similarity values ​​are grouped into a set, namely the dynamic time warping DWT similarity set, and each value in this set is checked. If any similarity value in the set is less than the preset similarity threshold, it means that the first initial power timing information has a large difference in dynamic behavior from a certain (or some) initial power timing information generated previously, that is, it provides a new and different heating strategy. In this case, the system will consider this first initial power timing information to be valuable and retain it as one of the candidate solutions. However, if all similarity values ​​in the set are greater than or equal to the similarity threshold, it means that the first initial power timing information is too similar to the initial power timing information generated previously in dynamic behavior, that is, it does not provide a new heating strategy. In this case, in order to avoid generating repeated and redundant power timing information, the system will reprocess the heating cycle target value and target temperature value, generate a new first initial power timing information, and perform similarity calculation again. Through this process, it can be ensured that the generated power timing information not only meets the needs of users, but also has a certain diversity and distribution range in dynamic behavior, thereby increasing the possibility of selecting the best solution from the candidate solutions. This strategy helps to maximize the utilization of energy.

[0037] The intelligent electric water heater remote control and energy efficiency management system based on the Internet of Things provided by the embodiment of the present invention has at least the following technical effects:

[0038] 1. By considering the usage frequency and home path of the nearest neighbor terminal node, and retrieving the speed constants of different transportation tools based on the timestamp tag to determine the user's preset speed, the user's homecoming time is accurately predicted. In addition, when the startup instruction does not contain a temperature value, the larger value of the temperature setting constant of the nearest neighbor terminal node and the requesting device terminal can be automatically extracted as the target temperature value, thereby providing a more personalized and intelligent heating service, which not only improves the convenience of the user, but also effectively avoids insufficient heating or energy waste caused by the user forgetting to set or setting the temperature incorrectly.

[0039] 2. Use the heating simulator to process the heating cycle target value and target temperature value multiple times to generate multiple initial power timing information. These initial power timing information are generated by the heating simulator trained by the machine learning algorithm, ensuring that they can provide accurate heating strategies based on the model and service life of the electric water heater. By combining the model and service life of the electric water heater, the power loss corresponding to these initial power timing information can be analyzed and compared, so as to select the power timing information with the lowest energy consumption and apply it to the PID control loop of the electric water heater, which not only improves the heating efficiency, but also effectively reduces energy costs and maximizes energy efficiency management.

[0040] 3. In the process of generating the initial power timing information, a dynamic time warping similarity detection mechanism is adopted to ensure that each newly generated initial power timing information has a difference in dynamic behavior from the previously generated initial power timing information. When it is detected that the DWT similarity between the newly generated initial power timing information and the generated initial power timing information is higher than the preset threshold, new initial power timing information will be regenerated to increase the diversity and practicality of the heating strategy, which not only avoids the redundancy and duplication of the heating strategy, but also provides users with more diversified heating options, improving the overall heating effect and user experience.

[0041] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. Intelligent electric water heater remote control and energy efficiency management system based on the Internet of Things, characterized by: The implementation steps include: In response to a start-up instruction of a device terminal, obtaining a geographic location data set of an authorized device terminal cluster; Based on the geographic location data set, the home distance between the nearest neighbor terminal node is counted, and the user arrival time prediction value is generated according to the preset speed constant parameter; When the startup instruction does not include a temperature value, counting the first temperature setting constant of the nearest neighbor terminal node and the second temperature setting constant of the requesting device terminal, extracting the larger value of the first temperature setting constant and the second temperature setting constant, and setting it as the target temperature value; The predicted value of the user arrival time is used as the target value of the heating cycle, and combined with the target temperature value, it is sent to the requesting device terminal to obtain a feedback instruction. When the feedback instruction is a confirmation instruction, the energy consumption optimization model is solved, and the power timing information is output and applied to the electric water heater PID control loop.

2. The system according to claim 1, characterized in that Based on the geographic location data set, the home distance between the nearest neighbor terminal node is counted, and according to the preset speed constant parameter, a user arrival time prediction value is generated. The execution steps include: Counting the homeward path set of the nearest neighbor terminal node; Traversing the homeward path set to perform usage frequency statistics of the nearest neighbor terminal nodes to obtain a usage frequency set; The homeward path with the highest frequency in the frequency-of-use set is extracted from the homeward path set and set as the selected homeward path. The distance of the selected homeward path is extracted and set as the homeward distance. A user arrival time prediction value is generated based on a preset speed constant parameter.

3. The system according to claim 2, characterized in that Extracting the homeward path with the highest frequency in the use frequency set from the homeward path set and setting it as the selected homeward path, extracting the distance of the selected homeward path and setting it as the homeward distance, and generating a user arrival time prediction value according to a preset speed constant parameter, the execution steps include: Obtaining a timestamp tag of the start instruction; Retrieving a walking speed constant, a bicycle speed constant, an electric vehicle speed constant, a motorcycle speed constant, and a car speed constant of the selected homeward path at the timestamp tag; The maximum value of the walking speed constant, the bicycle speed constant, the electric vehicle speed constant, the motorcycle speed constant and the car speed constant is extracted and set as the preset speed constant parameter.

4. The system according to claim 3, characterized in that Retrieving the walking speed constant, bicycle speed constant, electric vehicle speed constant, motorcycle speed constant and car speed constant of the selected homecoming path at the timestamp tag, the execution steps include: Retrieve a set of walking speed monitoring values ​​of the selected home-returning path at the timestamp tag through the Internet; Deleting outliers from the walking speed monitoring value set to obtain concentrated walking speed monitoring values; Extracting the maximum value of the concentrated walking speed monitoring values ​​and setting it as the walking speed constant; The bicycle speed constant, the electric vehicle speed constant, the motorcycle speed constant, the car speed constant and the walking speed constant are determined in the same process.

5. The system according to claim 1, wherein: When the startup instruction does not include a temperature value, counting the first temperature setting constant of the nearest neighbor terminal node and the second temperature setting constant of the requesting device terminal, extracting the larger value of the first temperature setting constant and the second temperature setting constant, and setting it as the target temperature value, the execution steps include: Obtaining a cache temperature setting value set of the nearest neighbor terminal node; When the number of the cache temperature setting value sets is less than or equal to the fitting number threshold, the cache temperature setting value at the end point of the cache temperature setting value set is used as the first temperature setting constant; When the number of the cache temperature setting value sets is greater than the fitting number threshold, performing a centralized value evaluation on the cache temperature setting value sets to obtain the first temperature setting constant; The configuration process of the second temperature setting constant is the same as that of the first temperature setting constant.

6. The system according to claim 1, wherein: The predicted value of the user arrival time is used as the target value of the heating cycle, and combined with the target temperature value, it is sent to the requesting device terminal to obtain a feedback instruction. When the feedback instruction is a confirmation instruction, the energy consumption optimization model is solved, the power timing information is output and applied to the electric water heater PID control loop, and the execution steps include: The heating cycle target value and the target temperature value are processed several times by a heating simulator to obtain a number of initial power timing information, wherein the heating simulator is generated by multiple sets of data based on machine learning training, and any one of the multiple sets of data includes: heating cycle target value record data that meets the electric water heater model, target temperature value record data, and label data identifying power timing information; In combination with the model of the electric water heater and the service life of the electric water heater, a plurality of power consumptions satisfying the plurality of initial power time series information are analyzed respectively; The initial power timing information of the minimum values ​​of the plurality of power consumptions is extracted and set as the power timing information.

7. The system according to claim 6, characterized in that In combination with the model of the electric water heater and the service life of the electric water heater, a plurality of power consumptions satisfying the plurality of initial power time series information are analyzed respectively, and the execution steps include: Constructing a type constraint rule: when the model of the sample electric water heater is the same as the model of the electric water heater, and the service life of the sample electric water heater is the same as the service life of the electric water heater, the type constraint rule is satisfied; Constructing a control mode constraint condition: when the dynamic time warping DWT similarity between the sample power time series information and the initial power time series information is greater than or equal to the similarity threshold, it is considered that the control mode constraint condition is satisfied; The first initial power timing information is extracted according to the several initial power timing information, and a first sample set that satisfies the type constraint rule and the control mode constraint condition is collected for the first initial power timing information. The concentrated value of the loss record power of the first sample set is counted and set as the first loss power, which is added to the several loss power.

8. The system according to claim 6, characterized in that The heating cycle target value and the target temperature value are processed several times by a heating simulator to obtain several initial power timing information, and the execution step further includes: According to the heating simulator, the heating cycle target value and the target temperature value are processed to obtain first initial power timing information; Calculate a dynamic time warping (DWT) similarity set between the first initial power timing information and the generated initial power timing information; When any one of the dynamic time warping DWT similarity sets is less than a similarity threshold, the first initial power timing information is regenerated.

Images