Energy-saving control method and system for smart home
By building a general middleware platform and analyzing the performance sharing relationship between smart home devices, and building an adaptive regulation strategy, the problem of poor interoperability between smart home devices is solved, collaborative energy-saving control is achieved, and energy consumption is reduced.
Patent Information
- Application Number
- CN202411147309.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-21
- Publication Date
- 2024-11-12
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The interoperability between smart home devices is poor, making it difficult to achieve coordinated energy saving control, resulting in waste of energy consumption.
Build a general middleware platform, including open standards and communication protocol layer, device access connection layer, data exchange and processing layer, device driver adaptation layer, obtain smart home data, analyze performance sharing relationships between devices, and build adaptive control strategies , optimize operating parameters to reduce energy consumption.
It improves interoperability between smart home devices, realizes collaborative optimization control, reduces unnecessary energy waste, and ensures that the equipment is operating normally while minimizing energy consumption.
Smart Images

Figure CN118938701A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of smart home control, and in particular to an energy-saving control method and system for a smart home. Background Art
[0002] Smart homes connect various devices in the home through the Internet of Things technology, providing automated and intelligent services, bringing convenience and comfort to users. However, with the increase in the number of connected devices and the increase in the frequency of use, the energy consumption problem of smart homes has become increasingly prominent. At present, most smart home devices use private protocols and interfaces from different manufacturers, with poor interoperability and difficulty in sharing data, resulting in the inability to interoperate and work together between devices of different brands and types. The devices operate independently, lack comprehensive considerations, and are difficult to realize energy-saving potential.
[0003] Taking the temperature control system and lighting system as an example, the two are often controlled independently in the existing technology. It is not considered that when cooling, if the indoor light intensity is high and the lighting system maintains high brightness, it will generate additional heat, which will become an additional load for the air conditioner. The air conditioner needs to consume more energy to offset this heat, resulting in waste. It can be seen that the interoperability of smart home devices of different brands and types in the existing technology is poor, and it is difficult to achieve collaborative energy-saving control. Summary of the invention
[0004] The present application provides an energy-saving control method and system for smart homes, aiming to solve the technical problem in the prior art that smart home devices of different brands and types have poor interoperability and are difficult to achieve collaborative energy-saving control.
[0005] In view of the above problems, the present application provides an energy-saving control method and system for a smart home.
[0006] The first aspect disclosed in the present application provides an energy-saving control method for smart homes, the method comprising: building a general middleware platform, including an open standard and communication protocol layer, a device access connection layer, a data exchange and processing layer, and a device driver adaptation layer; based on the general middleware platform, obtaining smart home data, including historical usage data, connection status, operating parameters, and energy consumption monitoring data; obtaining data sharing relationships of smart homes, the data sharing relationships characterizing the existence of performance feature similarities between smart homes that reach a similarity threshold; based on the data sharing relationships, traversing smart homes with an online connection status to obtain online collaborative devices, the online collaborative devices are smart home devices with data sharing relationships; mining control relationships based on the data sharing relationships to construct an adaptive control strategy; taking the energy consumption monitoring data of the online collaborative devices as the optimization object, taking the minimum constrained energy consumption as the goal, optimizing and adjusting the operating parameters based on the adaptive control strategy, and obtaining control adjustment information, the constrained energy consumption being the necessary energy consumption of the online collaborative devices under normal operating conditions; and adjusting and controlling the operating parameters using the control adjustment information.
[0007] Another aspect disclosed in the present application provides an energy-saving control system for smart homes, the system comprising: a middleware building module for building a general middleware platform, including an open standard and communication protocol layer, a device access connection layer, a data exchange and processing layer, and a device driver adaptation layer; a data acquisition module for acquiring smart home data based on the general middleware platform, including historical usage data, connection status, operating parameters, and energy consumption monitoring data; a correlation mining module for acquiring data sharing relationships of smart homes, the data sharing relationships representing the characteristics of the performance characteristics between smart homes reaching a similarity threshold; a collaborative object determination module for determining the performance characteristics of smart homes based on the data; and a collaborative object determination module for determining the performance characteristics of smart homes based on the data. The sharing relationship traverses the smart homes with an online connection status to obtain online collaborative devices, where online collaborative devices are smart home devices with a data sharing relationship; a control relationship mining module is used to mine control relationships based on data sharing relationships and build an adaptive control strategy; an operating parameter optimization module is used to optimize the energy consumption monitoring data of online collaborative devices, with the goal of minimizing constrained energy consumption, and optimize and adjust the operating parameters based on an adaptive control strategy to obtain control adjustment information, where the constrained energy consumption is the necessary energy consumption of the online collaborative devices to ensure normal operation; an energy-saving control module is used to adjust and control the operating parameters using the control adjustment information.
[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:
[0009] Due to the adoption of building a universal middleware platform, including open standards and communication protocol layer, device access connection layer, data exchange and processing layer, and device driver adaptation layer, by building a unified universal middleware platform, the differences in communication protocols and interface standards among devices of different manufacturers are shielded, and the interconnection and interoperability of devices of different brands and types is realized; based on the universal middleware platform, smart home data is obtained, including historical usage data, connection status, operating parameters, and energy consumption monitoring data, and the device access and data processing capabilities of the middleware platform are utilized to collect and aggregate the operating status data of each smart home device, providing a data basis for subsequent data analysis and energy-saving control; the data sharing relationship of the smart home is obtained, and the data sharing relationship represents the characteristics that the similarity of performance characteristics between smart homes reaches a similarity threshold. By analyzing the collected device data, the performance correlation characteristics between different devices are mined to provide a basis for collaborative control; based on the data sharing relationship, the smart homes with an online connection status are traversed to obtain online collaborative devices, and the online collaborative devices are smart home devices with data sharing relationships. , screen out online equipment combinations that have performance associations and can work together, and determine the scope of objects for collaborative energy-saving control; mine the control relationship based on the data sharing relationship, and build an adaptive control strategy. On the basis of determining the collaborative equipment, further analyze the influence rules between the equipment, generate a collaborative control strategy, and provide a decision-making basis for energy-saving optimization; take the energy consumption monitoring data of the online collaborative equipment as the optimization object, and take the minimum constrained energy consumption as the goal, optimize and adjust the operating parameters based on the adaptive control strategy, and obtain control adjustment information. The constrained energy consumption is the necessary energy consumption of the online collaborative equipment under normal operating conditions, so as to optimize the equipment operating parameters; use the control adjustment information to adjust and control the operating parameters, work together, and realize the technical solution of energy-saving control, which solves the technical problems of poor interoperability of smart home devices of different brands and types in the existing technology and difficulty in realizing collaborative energy-saving control, and achieves the goal of improving the interoperability between different smart home devices. Through collaborative optimization control between devices, the energy consumption is minimized while ensuring the normal operation of the equipment, and the technical effect of energy-saving control of smart homes is achieved.
[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS
[0011] Figure 1 A flow chart of an energy-saving control method for a smart home is provided for an embodiment of the present application;
[0012] Figure 2A structural schematic diagram of an energy-saving control system for a smart home is provided for an embodiment of the present application.
[0013] Explanation of the accompanying drawings: middleware construction module 11, data collection module 12, correlation mining module 13, collaborative object determination module 14, regulation relationship mining module 15, operation parameter optimization module 16, energy-saving control module 17. DETAILED DESCRIPTION
[0014] The overall idea of the technical solution provided by this application is as follows:
[0015] The embodiments of the present application provide an energy-saving control method and system for smart homes, which solve the intercommunication problem of smart home devices through a universal middleware platform; explore the performance correlation characteristics between devices and determine the collaborative energy-saving control objects; analyze the device regulation relationship and adaptively generate energy-saving strategies; and achieve energy saving by collaborative optimization control while ensuring device availability and minimizing energy consumption.
[0016] Specifically, first, a general middleware platform including open standards and communication protocol layer, device access connection layer, data exchange and processing layer, and device driver adaptation layer is built to shield the differences between device manufacturers and achieve interoperability. Then, the general middleware platform is used to collect historical usage data, connection status, operating parameters, energy consumption monitoring data, etc. of smart homes, and analyze and mine the performance correlation between devices to obtain online device combinations that can collaborate to save energy. Next, the control relationship between collaborative devices is analyzed and an adaptive control strategy is constructed. Finally, the energy consumption data of collaborative devices is used as the optimization object, and the minimum energy consumption constraint is used as the goal. The adaptive control strategy is used to adjust the device operating parameters, and the control instructions are sent to the device for execution to achieve the effect of energy-saving control.
[0017] In summary, this application fully considers the heterogeneous characteristics and interoperability requirements of smart home devices. By introducing a unified platform, exploring device correlations, adaptively generating energy-saving strategies, and collaboratively optimizing control, it not only ensures the availability of equipment, but also maximizes the energy-saving potential, improves the energy efficiency of smart homes, reduces unnecessary energy waste, and realizes energy-saving control of smart homes.
[0018] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically described below in conjunction with the drawings in the specification.
[0019] Embodiment 1, as Figure 1 As shown, the embodiment of the present application provides an energy-saving control method for a smart home, the method comprising:
[0020] S1: Build a general middleware platform, including open standards and communication protocol layer, device access connection layer, data exchange and processing layer, and device driver adaptation layer.
[0021] Specifically, first, a general middleware platform is built, which includes an open standard and communication protocol layer, a device access connection layer, a data exchange and processing layer, and a device driver adaptation layer. Among them, the open standard and communication protocol layer is used to define the standard protocol for communication and interaction between smart home devices, ensuring that devices of different manufacturers and brands can exchange data based on a unified language; the device access connection layer is responsible for providing multiple access methods, compatible with the connection requirements of different smart home devices, such as Wi-Fi, ZigBee, Bluetooth, etc., and at the same time authenticates the access device to ensure that only legally authorized devices can access the platform; the data exchange and processing layer is the core of the general middleware platform, responsible for collecting, storing, and analyzing data from various smart home devices, and sending the processed control instructions to the corresponding devices for execution according to the control strategy. At the same time, this layer also provides services such as data sharing and data mining to provide data support for energy-saving optimization; the device driver adaptation layer is located at the bottom layer of the middleware platform, providing a unified driver interface for smart home devices of different brands and models, shielding device differences, and facilitating upper-layer applications to quickly access and control devices.
[0022] By building a universal middleware platform with a multi-layer architecture, the interoperability of smart home devices of different brands and types can be improved, laying the foundation for subsequent data collection, relationship establishment, and energy-saving strategy formulation.
[0023] S2: Based on the universal middleware platform, smart home data is obtained, including historical usage data, connection status, operating parameters, and energy consumption monitoring data.
[0024] Specifically, after the smart home device is connected to the general middleware platform, the data generated during its operation will be reported to the data exchange and processing layer through the standard interface to obtain smart home data. Smart home data covers multiple dimensions such as historical usage data, real-time connection status, operating parameters and energy consumption monitoring data of smart home devices. Among them, historical usage data reflects the user's usage preferences and patterns of the device, such as the temperature setting of the air conditioner, the switching time of the lighting, etc. Analyzing these data can provide insight into user needs and provide support for the formulation of personalized energy-saving strategies; connection status data reflects the online status of the device in real time, which is the premise for whether the device can be included in the collaborative control, so as to timely grasp the controllability of the device and dynamically optimize the control range; operating parameter data includes the current working status of the device, such as the cooling capacity of the air conditioner, the ventilation volume of the fresh air system, etc. These data are closely related to the energy consumption level of the device. Through real-time collection and analysis, the energy-saving potential of the device can be accurately grasped; energy consumption monitoring data is the direct basis for carrying out energy-saving control. By deploying special energy consumption monitoring devices or using the metering function of the device itself, the general middleware platform can obtain the real-time power, accumulated power and other data of the device, so as to evaluate the effect of energy-saving measures and guide the dynamic optimization of control strategies.
[0025] Through the data collection and aggregation capabilities provided by the general middleware platform, centralized management of multi-source heterogeneous data is completed, so that data scattered on various devices can be associated and integrated, characterizing the energy consumption behavior of smart homes from multiple angles, providing a data basis for collaborative energy-saving control.
[0026] S3: Acquire a data sharing relationship of smart homes, where the data sharing relationship indicates that there is a characteristic that the similarity of performance characteristics between smart homes reaches a similarity threshold.
[0027] Specifically, data sharing relationship means that there is a certain correlation between different smart home devices, and there is a significant statistical correlation between their performance parameters. This correlation may be due to the physical proximity of the devices, such as air conditioning and lighting in the same room; it may also be due to the functional complementarity of the devices, such as the synergy between the fresh air system and air conditioning in regulating indoor air quality. When the correlation between the performance parameters of two devices exceeds a certain threshold, a data sharing relationship is formed. Traditional energy-saving control is often limited to a single device, ignoring the coupling effect between devices, resulting in poor energy-saving effects. For example, simply raising the air-conditioning temperature can save energy, but it may cause stuffiness in the room, which in turn increases the ventilation frequency of the fresh air system, and the actual energy consumption increases. By obtaining the data sharing relationship of smart homes, support is provided for achieving collaborative energy saving.
[0028] First, through the historical usage data of smart home devices, the significant correlation between the energy consumption level of the device and the state parameters of other devices is extracted, and then the energy-saving mechanisms such as complementarity and substitution between different devices may be inferred. Specifically, the collected smart home device data is preprocessed, including data cleaning, data format conversion, data normalization and other operations, in order to improve data quality, eliminate the interference of noise and outliers, and lay the foundation for subsequent analysis. Secondly, the device performance characteristics are extracted from the preprocessed data. The device performance characteristics are key indicators reflecting the operating status of the equipment, such as the cooling capacity of the air conditioner and the brightness of the lighting. Then, the correlation between the device performance characteristics is calculated using the big data association analysis algorithm, such as the Pearson correlation coefficient and mutual information. Among them, the Pearson correlation coefficient measures the degree of linear correlation between two continuous variables, and its value is between -1 and 1. The larger the absolute value, the stronger the correlation; the mutual information measures the degree of mutual dependence between the two variables and can capture nonlinear correlation characteristics. Finally, the data sharing relationship matrix is constructed based on the results of the association analysis. The rows and columns of the matrix correspond to different smart home devices, and the values of the matrix elements represent the degree of correlation between the two devices. When the element value exceeds the preset similarity threshold, it is considered that there is a significant data sharing relationship between the two corresponding devices. The similarity threshold is determined by empirical values or data statistical methods. After obtaining the data sharing relationship, the collaborative ability between devices is mastered, laying a solid foundation for formulating an overall energy-saving strategy.
[0029] S4: Based on the data sharing relationship, traverse the smart home devices with online connection status to obtain online collaborative devices, where the online collaborative devices are smart home devices with data sharing relationship.
[0030] Specifically, after obtaining the data sharing relationship between smart home devices, the smart home devices with online connection status are traversed based on the data sharing relationship to obtain the online collaborative devices that can be included in the collaborative optimization control scope, thereby clearly defining the device resources that can currently participate in energy-saving optimization, which is a necessary prerequisite for implementing collaborative control.
[0031] First, access the connection status data of smart home devices. The connection status reflects the online status of the device. Only when the device is online can its data be obtained in real time and its operating parameters be adjusted dynamically. This is the basis for collaborative optimization control. For devices with an online connection status, traverse the corresponding elements in the data sharing relationship matrix, find other online devices that have a sharing relationship with the current device (that is, the matrix element value exceeds the similarity threshold), include them in the online collaborative devices, and include all devices that can currently participate in collaborative optimization.
[0032] Through data sharing relationships and equipment online status, online collaborative devices that can currently participate in energy-saving optimization collaborative control are screened out to ensure that the equipment combination can continue to produce significant energy-saving synergy effects, providing a reliable equipment foundation for subsequent strategy formulation and execution.
[0033] S5: Mining the control relationship based on the data sharing relationship and constructing an adaptive control strategy.
[0034] Specifically, after clarifying the online collaborative devices that can participate in collaborative optimization control, we further explore the intrinsic connections between their energy usage behaviors based on the data sharing relationship between these devices, and build an adaptive collaborative control strategy to lay a strategic foundation for achieving the overall energy-saving goal.
[0035] First, data analysis is performed on each device in the online collaborative device, focusing on the correspondence between the key performance parameters of the device (such as the cooling temperature of the air conditioner, the brightness of the lighting, etc.) and the energy consumption level, and a single device energy consumption model is established through data fitting and other methods to characterize its energy efficiency performance under different working parameters. Further, based on the data sharing relationship matrix, the energy consumption correlation between devices with data sharing relationships is analyzed, and by comparing the historical energy consumption data of these devices under different operating conditions, it is found how they influence and restrict each other during actual use. For example, increasing the brightness setting of lighting fixtures may cause the indoor temperature to rise, increase the cooling load of the air conditioner, and thus increase the energy consumption level of the air conditioner; conversely, the rational use of natural lighting can reduce lighting electricity consumption while meeting lighting needs, reduce the burden on air conditioners, and achieve energy saving.
[0036] Based on the energy consumption mode of a single device and the energy consumption correlation between related devices, an adaptive control strategy for the collaborative operation of multiple devices can be constructed. Taking the overall energy efficiency optimization as the goal, the optimal working parameter combination of each device under different time periods and different external environments is solved under the premise of considering the constraints such as the energy consumption upper limit of each device and the user's comfort requirements, and the adaptive control strategy is obtained. The adaptive control strategy can adjust the optimization target and decision boundary in real time according to the dynamic changes of the physical environment conditions of the device (such as weather, temperature and humidity, etc.) and the personalized needs of users (such as preferences for light intensity and temperature) to ensure that the best energy-saving effect can be achieved in different application scenarios; at the same time, since the number and type of online collaborative devices may change at any time in actual operation (such as some devices are offline and new devices are connected), the adaptive control strategy can perceive this change, automatically adjust the optimization object and granularity, and generate new collaborative solutions in time, so as to have better robustness.
[0037] By utilizing the data sharing relationship of online collaborative devices, through data association analysis and correlation mining, we can form an understanding of the energy consumption behavior of different devices and their internal connections. The adaptive collaborative control strategy built on this basis can not only fully tap the energy-saving potential between different devices and achieve overall energy efficiency optimization, but also respond to various dynamic changing factors in actual applications in a timely manner and automatically adjust.
[0038] S6: Taking the energy consumption monitoring data of the online collaborative device as the optimization object and minimizing the constrained energy consumption as the goal, the operating parameters are optimized and adjusted based on the adaptive control strategy to obtain control adjustment information. The constrained energy consumption is the necessary energy consumption of the online collaborative device to ensure normal operation.
[0039] Specifically, by using intelligent algorithms within the framework of adaptive control strategies to dynamically optimize the combination of equipment operating parameters, each device can operate collaboratively in the most energy-efficient way while ensuring normal operating conditions, thereby achieving the best balance between overall energy efficiency and user experience.
[0040] Among them, constrained energy consumption refers to the energy that online collaborative devices must consume under the premise of meeting their predetermined functions and user comfort requirements, that is, ensuring normal operation, which is the basic constraint in the optimization process. While pursuing the minimization of energy consumption, ensure that the equipment operates within the user's acceptable comfort range to avoid damaging the user experience due to excessive energy saving. In the process of parameter optimization, make full use of the data perception capabilities in the Internet of Things environment, continuously collect equipment energy consumption data and influencing factors such as environmental parameters and user feedback, and establish a real-time mapping between energy consumption and influencing factors to form a dynamic understanding of equipment energy efficiency characteristics and user comfort preferences, and then construct a quantitative optimization objective function. While minimizing energy consumption, this function takes user comfort requirements as an important evaluation indicator and constraint to ensure the availability of the optimization results. Subsequently, the optimal energy consumption solution that meets the constraints is obtained through an intelligent optimization algorithm. The optimization result is control adjustment information, which is a quantified multi-device collaborative control instruction set that specifies the optimal operating parameter sequence for each device in the future.
[0041] S7: Using the control adjustment information to adjust and control the operating parameters.
[0042] Specifically, the control adjustment information describes the optimal operating parameter settings for each online collaborative device in the future, such as the target temperature and wind speed of the air conditioner, the brightness and color temperature of the lighting, etc.
[0043] First, the control adjustment information is converted into a format and encapsulated into a protocol. Since the control protocols and data formats used by smart devices of different types and brands vary greatly, the unified control adjustment information is converted into an instruction format that the device can understand and execute according to the device's protocol specifications to ensure the accuracy and effectiveness of the regulation. Once the control instruction is generated, the smart gateway transmits it to the corresponding smart home control terminal, such as smart sockets and smart switches, through the home LAN. These terminals are directly connected to specific execution devices, such as air conditioners and lighting fixtures, and directly manipulate the operating status and parameter settings of the device according to the received control instructions. When the execution device completes the parameter adjustment according to the instruction, its operating data, status information, etc. change, realizing the adjustment and control of the smart home.
[0044] Furthermore, the embodiment of the present application also includes:
[0045] Set a connection range, where the connection range is the boundary location of the target control space; configure a dual verification mechanism for the platform access identification password and the connection range; fit the dual verification mechanism into the universal middleware platform for locating and verifying the access device.
[0046] In a feasible implementation, in the process of building a universal middleware platform, an access device verification method is provided to improve security and reliability through a dual verification mechanism of connection range and platform access identification password.
[0047] First, set the connection range. The connection range refers to the physical space boundary where devices that are allowed to access the general middleware platform are located, corresponding to the target control area of the smart home system, such as a house, a floor, etc. By limiting the connection range, it is effective to avoid devices in non-target areas from mistakenly accessing the system, and reduce the occupation of network resources and interference with the control process by irrelevant devices. For example, by using the spatial attenuation characteristics of wireless signal strength, by setting a signal strength threshold, only devices within the threshold range are allowed to access. Then, introduce the platform access identification password. The identification password is a unique identity authentication credential for each legal access device, which is used to verify the authenticity and legitimacy of the device, and is combined with the connection range to establish a double verification mechanism. Unlike traditional static passwords, the identification password is a dynamically generated encryption token, which is regularly issued to legal devices by the smart home management server, and each token is valid only within a specific time period. The security strength of the password can be improved through the dynamic token mechanism. For example, an encryption algorithm (such as AES, RSA, etc.) is used to combine multiple random factors such as device hardware characteristics (such as MAC address, serial number, etc.) and timestamps to generate a highly complex dynamic password. Legitimate devices periodically obtain the latest identification password from the server and submit it to the general middleware platform for verification during access authentication.
[0048] Subsequently, the dual verification mechanism is integrated into the general middleware platform. When a smart device requests access, the general middleware platform first determines whether the device is within the preset connection range. If so, it enters the identification password verification stage and requires the device to submit the current valid access token. Only when both verification links are passed can the device finally access the platform and start data interaction and control processes. Through the dual verification mechanism, the security factors of two different dimensions, physical space and digital keys, are fully utilized to form a depth defense system. On the one hand, the connection range verification restricts the access of illegal devices at the physical level; on the other hand, the identification password verification ensures that only devices holding legal tokens can pass the authentication at the digital level. Through the combination of the two verification dimensions, the reliability of access authentication is improved, and various forms of network attacks and malicious access are effectively prevented.
[0049] Furthermore, the embodiment of the present application also includes:
[0050] Determine shared relationship performance, including lighting performance, temperature control performance, ventilation performance, and illumination performance; extract the operation characteristics of the smart home, and perform feature clustering with the lighting performance, temperature control performance, ventilation performance, and illumination performance as clustering centers to obtain a performance clustering set; generate performance labels according to the performance clustering sets, and identify the performance type of the smart home; obtain the shared combination relationship of the shared relationship performance, match the smart home according to the shared combination relationship and the performance type identification, and determine the data sharing relationship of the smart home.
[0051] In a preferred embodiment, when determining the data sharing relationship between smart home devices, a method based on performance clustering and sharing combination analysis is proposed to form a sharing relationship determination mechanism by mining the mutual influence rules between devices in different performance dimensions.
[0052] First, the shared relationship performance is determined to characterize the key performance indicators of smart home devices in the energy-saving optimization process. Through extensive research and expert experience summary, four shared relationship performances are determined, namely lighting performance, temperature control performance, ventilation performance and illumination performance, covering the core functions of smart home devices in lighting, temperature regulation, air quality control, etc. Then, the operation characteristics of the connected smart home devices are extracted. Operation characteristics are a set of key parameters that describe the state and behavior of the device during actual operation, such as the power and brightness of lighting equipment, the set temperature and energy consumption of temperature control equipment, the air volume and ventilation times of ventilation equipment, and the light intensity of illumination equipment. Through the analysis of the historical operation data of the equipment and feature engineering processing, a set of the most representative and discriminative feature vectors are extracted from the massive raw data to characterize the performance of the equipment in different performance dimensions. Based on the extracted operating characteristics, a clustering algorithm is further used to perform feature clustering on the equipment with lighting performance, temperature control performance, ventilation performance and lighting performance as clustering centers. By calculating the distance between the equipment feature vector and each performance clustering center, devices with similar characteristics are classified into the same performance cluster, and a performance cluster set that reflects the performance characteristics of the equipment is obtained. Each cluster set represents a typical performance pattern.
[0053] Subsequently, based on the performance clustering set, a unique performance label is generated for each clustering set as the performance attribute identifier of this type of equipment. The performance label consists of two parts of information: performance type and clustering result, such as "efficient lighting" and "energy-saving temperature control", which intuitively expresses the typical performance characteristics of the equipment. By semantically abstracting and refining the original equipment data, the performance label enables the subsequent shared relationship analysis and optimization control strategy formulation to be carried out at a higher semantic level, reducing the complexity of the problem. After that, a shared combination relationship knowledge base is pre-constructed, which summarizes the potential influence rules between different performance labels based on expert experience and prior data. For example, there is usually a significant negative correlation between lighting performance and temperature control performance, that is, the higher the brightness of the lighting equipment, the more indoor heat accumulation, and the greater the cooling load of the temperature control equipment. Similarly, there is a complementary relationship between lighting performance and lighting performance. The more sufficient natural lighting during the day, the lower the demand for lighting equipment. The shared combination relationship in the knowledge base reveals the energy conversion and interaction rules of different types of equipment in actual operation, which is an important basis for optimization control. After obtaining the shared combination relationship, the equipment is matched pairwise according to its performance label. For any two devices, if their performance labels happen to satisfy a certain shared combination relationship in the knowledge base, it is determined that there is a data sharing relationship between the two devices, that is, the operating status and energy consumption level of the two devices have an intrinsic correlation, and the overall energy saving effect can be improved through collaborative optimization. On the contrary, if the performance label combination of the two devices cannot find a corresponding entry in the knowledge base, it is considered that there is no (or a weak) sharing relationship between the two devices. By performing an exhaustive pairing analysis on all devices, a complete device data sharing relationship matrix is obtained, which quantitatively describes the data sharing relationship between any two devices in the smart home.
[0054] Furthermore, the embodiment of the present application also includes:
[0055] Acquire the performance coverage and the space where the smart home is located; configure sharing constraints according to the performance coverage and the space where the smart home is located; and use the sharing constraints to screen the data sharing relationship of the smart home to determine the data sharing relationship.
[0056] In a feasible implementation, when determining the data sharing relationship between smart home devices, in addition to considering the performance characteristics of the device itself and the mutual influence between performances, the spatial environment and scope of the device are also important factors that cannot be ignored. In order to further improve the accuracy and availability of sharing relationship mining, the data sharing relationship between devices is screened and optimized in a more fine-grained manner through performance coverage, space and sharing constraints.
[0057] First, obtain the performance coverage and space of each smart home device. Performance coverage refers to the physical area that the device can influence in terms of its performance attributes. For example, for lighting equipment, the coverage of its lighting performance usually depends on factors such as the power of the lamp, the material of the lampshade and the layout of the room, and is estimated by spatial modeling of light intensity distribution; while for temperature control equipment, the coverage of its temperature control performance is closely related to the cooling / heating capacity of the equipment, the thermal insulation performance of the room, etc., and is characterized by a temperature field distribution model. The space refers to the specific location and belonging area of the device in the building, such as the living room, bedroom, kitchen, etc. By identifying and dividing the space where the device is located, the scattered devices are organized into several spatial device clusters, providing a clearer and more orderly structural basis for further constraint analysis. The acquisition of the space is achieved by using Internet of Things technologies, such as indoor positioning and semantic modeling, and by semantic fusion and reasoning analysis of the collected environmental data and context information, an accurate description of the spatial belonging of the device is formed.
[0058] After that, sharing constraints are configured according to the performance coverage of the equipment and the space where it is located. Sharing constraints are essentially further limitations and refinements of the applicable scenarios of the sharing combination relationship between performances. Through the factors of performance dimension and space dimension, the establishment of sharing relationship is closer to the physical environment where the equipment actually operates. For example, for the sharing combination relationship of lighting performance and illumination performance, a sharing constraint can be: there is a significant spatial overlap in the performance coverage of the two sharing parties, and the spaces are the same or adjacent. Only for the equipment pair that meets this sharing constraint, the correlation between its lighting state and lighting state has energy-saving control value. Otherwise, even if the two parties are complementary in performance, they cannot work together due to spatial isolation. For another example, for the sharing combination relationship of ventilation performance and temperature control performance, the corresponding sharing constraint can be: there is a certain temperature gradient difference and airflow channel in the space between the two sharing parties. Only when there is a significant interactive influence on temperature and airflow in the area where the ventilation equipment and temperature control equipment are located, can the coordinated control of the two truly improve the indoor environment quality and achieve the purpose of energy saving and efficiency improvement.
[0059] After that, the obtained data sharing relationship matrix is further screened and optimized based on the configured sharing constraints. For each non-zero element in the matrix, that is, each pair of devices with potential sharing relationships, it is determined whether the corresponding sharing constraints are met according to their performance coverage and the space they are in. If the conditions are met, the data sharing relationship of the device pair is retained; otherwise, the corresponding matrix elements are set to zero and removed from the data sharing relationship matrix, thereby realizing the screening of the data sharing relationship of the smart home and determining the screened data sharing relationship. Through conditional screening, the data sharing relationship matrix is further sparse, and the retained device pairs represent a combination of devices that are not only complementary in performance logic, but also have substantial interactions in spatial physics. They are mining objects and control objects in the energy-saving optimization process of smart homes.
[0060] Furthermore, the embodiment of the present application also includes:
[0061] Obtain member restriction setting information, wherein the member restriction setting information includes setting user information, restricted equipment, restricted space, restricted time, and restricted parameter threshold; obtain overlapping restriction setting information based on the restricted equipment, and extract overlapping user information; set the control priority of the overlapping user information and the set user information in the restricted space, and fit the control priority to the control strategy of the restricted equipment, wherein the control strategy is used to adjust the restriction time and restriction parameter threshold of the restricted equipment according to the control priority.
[0062] In a preferred embodiment, in the energy-saving control process of a smart home, a regional and priority-based strategy adjustment method is proposed for personalized needs. By limiting member setting information and control priorities, the energy-saving control strategy can take into account the differentiated needs of different family members, while improving the overall energy-saving effect and maximizing the user's comfort experience.
[0063] First, obtain member restriction setting information, which is defined and entered by the management user of the smart home system through the human-computer interaction interface according to the actual needs and preferences of family members. Member restriction setting information contains five key elements, namely, setting user information, restricted equipment, restricted space, restricted time and restricted parameter threshold. Among them, setting user information is used to identify the family members targeted by the setting, such as parents, children, and the elderly; restricted equipment indicates the smart devices that the member controls exclusively, such as air conditioning, lighting, curtains, etc. in the room; restricted space further clarifies the spatial boundaries set by the member, corresponding to one or several physical areas in the home; restricted time specifies the timeliness of the setting, which can be a specific period of time within a day or a repeated cycle of several days; restricted parameter threshold is a quantitative expression of the member's preference, defining the acceptable working parameter range of the relevant equipment under the restricted time and space conditions, such as temperature, brightness, etc. Through member restriction setting, it is possible to describe and distinguish the use demands of smart devices for different family members at different times and in different areas in a fine-grained manner, creating conditions for personalized energy-saving control.
[0064] Subsequently, the restriction setting information of multiple members is compared and analyzed for correlation to find potential conflicts and overlaps in the use of devices by different members. Specifically, first, based on the restricted device, the setting information of different members is grouped to identify multiple settings for the same device; then, under the premise that the devices are the same, the overlap of these settings in restricted space and restricted time is further compared and analyzed to find out the situation where different users compete for control over the same device under certain time and space conditions; then, the members with usage conflicts are identified as overlapping users, and their relevant information is extracted to form overlapping user information.
[0065] Next, the identified overlapping restriction settings are coordinated and optimized, and control priorities are introduced, that is, the control weights of different users on the device when there is a conflict in device use. Different default priorities are given to different users based on the identity, role, health status and other factors of overlapping users. For example, the control priority of the elderly and children is higher than that of adults. Based on the control priority, the management user can manually adjust the user priority in a specific space and a specific time period according to actual needs to deal with special situations. After determining the control priority between users, it is mapped to the corresponding device control strategy. Specifically, the control period and control range of different users on the same device are dynamically adjusted according to the level of control priority. The higher the priority of the user, the longer the control time of the device and the looser the parameter threshold range that can be set; conversely, the lower the priority of the user, the more limited the control period and the more restricted the parameter adjustment range. By adjusting the control strategy based on user priority, the personalized needs of different users can be maximized under energy constraints. For example, for the elderly, because they have higher requirements for the comfort of indoor temperature, when allocating the control rights of air conditioners, the preference threshold of the elderly is more inclined.
[0066] Furthermore, the embodiment of the present application also includes:
[0067] Based on the data sharing relationship, historical performance data of related devices are extracted, including energy consumption, lighting, heat, ventilation, and configuration data points, wherein the data points include a group of energy consumption data and performance data with a sharing relationship; based on the data points, a linear regression model is constructed with the energy consumption of one party of the shared device as the dependent variable and the performance data of the other party of the shared device as the independent variable, and the model parameters are determined by calculating the least squares method through the historical performance data; based on the model parameters, the influence relationship and influence direction are determined, and the influence direction includes the same-direction influence and the reverse influence, and the parameter is a positive number when it is the same-direction influence, and the parameter is a negative number when it is the reverse influence; an adaptive control strategy for shared devices is established based on the linear regression model.
[0068] In a preferred embodiment, when constructing an adaptive control strategy for smart home devices, the historical performance data between shared devices is analyzed, and a linear regression model is used to quantify the influence relationship and influence direction between devices, thereby forming a dynamically adaptive multi-device collaborative control strategy, which effectively reduces the overall energy consumption while improving the intelligence level of the home system.
[0069] First, based on the data sharing relationship, the performance data of the device pairs with shared associations are extracted from the historical database of the smart home, including multiple physical quantities such as energy consumption, light intensity, heat, ventilation, etc., reflecting the operating status and efficiency characteristics of the devices under different external conditions. In order to facilitate subsequent data analysis and association mining, the extracted raw data are pre-processed by cleaning and alignment, and the device data are paired according to the sharing relationship to form a series of data points. Each data point consists of a set of energy consumption data and performance data with data sharing relationships, describing the energy consumption and performance of the shared device pair at a certain historical moment. Then, for each pair of shared devices, the energy consumption data of one device is used as the dependent variable, and the performance data of the other device is used as the independent variable. By performing regression fitting on the data points, a linear association model between the two devices is established. Specifically, the least squares method is used, that is, the model parameters in the regression model are solved by minimizing the sum of squares of the difference between the estimated value and the actual value of the dependent variable. By substituting the historical data points into the established linear model and using the least squares estimation, the model parameters can be obtained, thereby determining the linear regression model that describes the energy consumption-performance relationship between the two devices.
[0070] Afterwards, the regulatory influence relationship between shared devices is analyzed based on the obtained model parameters. The directionality of the influence is determined by observing the sign of the slope parameter of the linear model. When the slope parameter is positive, it indicates that for every unit increase in the independent variable (performance), the dependent variable (energy consumption) will increase accordingly, and the two devices show a unidirectional influence relationship; conversely, when the slope parameter is negative, it indicates that for every unit increase in the independent variable, the dependent variable decreases, and the two devices show an inverse influence relationship. At the same time, the absolute value of the slope parameter reflects the intensity of the influence of the independent variable on the dependent variable. The larger the absolute value, the closer the energy consumption-performance correlation between the two devices, and the more significant the leverage effect of the regulation. Subsequently, based on the linear regression model and the influence relationship analysis, a set of adaptive regulation strategies is established for each pair of shared devices. The strategy dynamically responds to the historical performance and real-time status of the shared device pair, and optimizes the energy consumption level of the other device by actively adjusting the performance parameters of one device, thereby achieving an improvement in the overall energy efficiency of the two devices. Taking air conditioners and lighting fixtures as an example, the adaptive control strategy can be set as follows: Under the premise of meeting the user's lighting comfort, dynamically adjust the lighting brightness setting value according to the actual energy consumption level of the air conditioner to control the air conditioner energy consumption within the expected threshold. When the air conditioner energy consumption exceeds the threshold, the lighting brightness is appropriately increased; otherwise, the lighting brightness is appropriately reduced. Through closed-loop regulation based on energy consumption feedback, the energy consumption-performance state of the two shared devices can always be kept at the optimal balance point, which not only meets the user's comfort requirements for the light environment, but also minimizes the energy consumption of the air conditioner and achieves the energy saving goal.
[0071] Furthermore, the embodiment of the present application also includes:
[0072] The linear regression model is expressed as: Q n,1 =∝·Q n,2 +β, where Solve the model parameters; where Q n,1 , Q n,2 is a shared device in the nth group of data sharing relationships, ∝ and β are model parameters, ∝ represents the basic energy consumption when the performance data is zero, β represents the change in air conditioning energy consumption per unit change in lighting brightness, x i is the performance data of the i-th data point, y i is the energy consumption data of the i-th data point, n is the number of data sharing relationships, and m is the number of data points.
[0073] In the expression of this linear regression model, Q n,1 and Q n,2 They represent a pair of shared devices in the nth group of sharing relationships, and the device whose energy consumption data is the dependent variable is selected as Q n,1 , the performance data of the device as the independent variable is Q n,2 ∝ and β are the model parameters to be solved, where ∝ represents the n,2 Performance data is zero time Q n,1 The basic energy consumption level, β reflects Q n,2 Q per unit performance change n,1 The corresponding change in energy consumption.
[0074] After the form of the model is determined, the least squares method is used to estimate and solve the model parameters. The basic principle of the least squares method is to find a best fitting straight line by minimizing the sum of squared errors so that the difference between the estimated value on the straight line and the actual observed value is minimized. Assume that Q n,1 , Q n,2 There are m paired historical performance-energy consumption data points, denoted as (x1, y1), …, (x i ,y i ),…,(x m ,y m ), where x i is the Q of the i-th data point n,2 Performance data, i The corresponding Q n,1 Energy consumption data. According to the least squares method, the analytical expressions of the optimal estimated values of β and ∝ are derived. Among them, the estimation formula of β reflects the ratio of the covariance of the independent variable and the dependent variable to the variance of the independent variable, and the estimation formula of ∝ reflects the difference between the mean of the dependent variable and the product of β and the mean of the independent variable. i and iSubstituting the values into these two analytical expressions, we can get the specific estimated values of the model parameters β and ∝. Since the sharing relationship is established in a bidirectional manner, for each pair of shared devices Q n,1 and Q n,2 , need to be respectively Q n,1 The energy consumption is the dependent variable, Q n,2 performance as the independent variable, and Q n,2 The energy consumption is the dependent variable, Q n,1 The performance of is taken as the independent variable, and two inverse linear regression models are established, based on which two sets of model parameters that characterize the two-way influence relationship are obtained.
[0075] In summary, the energy-saving control method for smart home provided by the embodiment of the present application has the following technical effects:
[0076] Build a general middleware platform, including an open standard and communication protocol layer, a device access connection layer, a data exchange and processing layer, and a device driver adaptation layer, to solve the differences in communication protocols and interface standards among smart home devices from different manufacturers, and realize the interconnection and unified management of devices. Based on the general middleware platform, obtain smart home data, including historical usage data, connection status, operating parameters, and energy consumption monitoring data. Utilize the device access and data processing capabilities of the general middleware platform to collect and aggregate the operating status data of smart home devices, and provide data support for subsequent data analysis and energy-saving control. Obtain the data sharing relationship of smart homes, the data sharing relationship represents the characteristics that the similarity of performance characteristics between smart homes reaches the similarity threshold, and by analyzing the collected device data, the performance correlation characteristics between different devices are mined to provide a basis for determining the device objects for collaborative energy-saving control. Based on the data sharing relationship, traverse the smart homes with an online connection status to obtain online collaborative devices, which are smart home devices with data sharing relationships, screen out online device combinations with performance associations that can perform collaborative energy-saving work, and determine the scope of objects for collaborative energy-saving control. According to the data sharing relationship, control relationship mining is performed to construct an adaptive control strategy. On the basis of determining the collaborative equipment, the influence rules between the equipment are further analyzed, and the collaborative control strategy is automatically generated to provide a decision-making basis for energy-saving optimization. Taking the energy consumption monitoring data of the online collaborative equipment as the optimization object and the minimum constrained energy consumption as the goal, the operating parameters are optimized and adjusted based on the adaptive control strategy to obtain control adjustment information. The constrained energy consumption is the necessary energy consumption of the online collaborative equipment to ensure normal operation, so as to achieve the optimization of the operating parameters. The control adjustment information is used to adjust and control the operating parameters, improve the interoperability between different smart home devices, minimize energy consumption while ensuring the normal operation of the equipment, and realize energy-saving control of smart homes.
[0077] Embodiment 2, based on the same inventive concept as the energy-saving control method for smart home in the above embodiment, Figure 2 As shown, the embodiment of the present application provides an energy-saving control system for a smart home, the system comprising:
[0078] The middleware building module 11 is used to build a general middleware platform, including an open standard and communication protocol layer, a device access connection layer, a data exchange and processing layer, and a device driver adaptation layer;
[0079] The data acquisition module 12 is used to obtain smart home data based on the universal middleware platform, including historical usage data, connection status, operating parameters, and energy consumption monitoring data;
[0080] A correlation mining module 13 is used to obtain data sharing relationships of smart homes, where the data sharing relationships represent that there is a characteristic that the similarity of performance characteristics between smart homes reaches a similarity threshold;
[0081] A collaborative object determination module 14 is used to traverse the smart home devices in an online connection state based on the data sharing relationship to obtain online collaborative devices, where the online collaborative devices are smart home devices with a data sharing relationship;
[0082] A control relationship mining module 15 is used to mine control relationships according to the data sharing relationship and construct an adaptive control strategy;
[0083] An operation parameter optimization module 16 is used to optimize the energy consumption monitoring data of the online collaborative device and minimize the constrained energy consumption, and optimize and adjust the operation parameters based on the adaptive control strategy to obtain control adjustment information, wherein the constrained energy consumption is the necessary energy consumption of the online collaborative device to ensure normal operation;
[0084] The energy-saving control module 17 is used to adjust and control the operating parameters using the control adjustment information.
[0085] Furthermore, the middleware building module 11 includes the following execution steps:
[0086] Setting a connection range, where the connection range is the boundary positioning of the target control space;
[0087] Configure a dual authentication mechanism for the platform access identification password and the connection scope;
[0088] The dual verification mechanism is integrated into the universal middleware platform to perform location verification on access devices.
[0089] Furthermore, the relevance mining module 13 includes the following execution steps:
[0090] Determine the performance of shared relationships, including lighting performance, temperature control performance, ventilation performance, and lighting performance;
[0091] Extracting the operation characteristics of the smart home, and performing feature clustering with the lighting performance, temperature control performance, ventilation performance, and illumination performance as clustering centers to obtain a performance clustering set;
[0092] Generating performance labels according to the performance cluster sets respectively, and identifying the performance types of the smart homes;
[0093] The sharing combination relationship of the sharing relationship performance is obtained, the smart home is matched according to the sharing combination relationship and the performance type identifier, and the data sharing relationship of the smart home is determined.
[0094] Furthermore, the relevance mining module 13 also includes the following execution steps:
[0095] Obtaining the performance coverage and location of the smart home;
[0096] Configure sharing constraints according to the performance coverage and the space in which it is located;
[0097] The data sharing relationship of the smart home is screened by using the sharing constraint condition to determine the data sharing relationship.
[0098] Furthermore, the embodiment of the present application also includes a priority policy adjustment module, which includes the following execution steps:
[0099] Obtain member restriction setting information, wherein the member restriction setting information includes setting user information, restricted device, restricted space, restricted time, and restricted parameter threshold;
[0100] Acquiring overlapping restriction setting information based on the restriction device, and extracting overlapping user information;
[0101] The control priority of the overlapping user information and the set user information in the restricted space is set, and the control priority is fitted into the control strategy of the restricted device, and the control strategy is used to adjust the restriction time and restriction parameter threshold of the restricted device according to the control priority.
[0102] Furthermore, the regulation relationship mining module 15 includes the following execution steps:
[0103] Based on the data sharing relationship, extract historical performance data of the related equipment, including energy consumption, lighting, heat, ventilation, and configuration data points, wherein the data points include a set of energy consumption data and performance data with a sharing relationship;
[0104] Based on the data points, a linear regression model is constructed with the energy consumption of one party of the shared device as the dependent variable and the performance data of the other party of the shared device as the independent variable, and the model parameters are determined by calculating the least squares method through the historical performance data;
[0105] Determine the influence relationship and influence direction according to the model parameters, wherein the influence direction includes same-direction influence and reverse influence, and the parameter is a positive number when it is same-direction influence, and a negative number when it is reverse influence;
[0106] An adaptive control strategy for shared equipment is established based on the linear regression model.
[0107] Furthermore, the regulation relationship mining module 15 also includes:
[0108] The linear regression model is expressed as: n,1 =∝·Q n,2 +β, where solving the model parameters;
[0109] Among them, Q n,1 , Q n,2 is a shared device in the nth group of data sharing relationships, ∝ and β are model parameters, ∝ represents the basic energy consumption when the performance data is zero, β represents the change in air conditioning energy consumption per unit change in lighting brightness, x i is the performance data of the i-th data point, y i is the energy consumption data of the i-th data point, n is the number of data sharing relationships, and m is the number of data points.
[0110] Any step of the method described above can be stored as a computer instruction or program in an unlimited computer memory, and can be called and recognized by an unlimited computer processor to implement any method in the embodiments of the present application, without any unnecessary restrictions.
[0111] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these modifications and variations.
Claims
1. An energy-saving control method for smart home, characterized in that: The energy-saving control method for smart home comprises: Build a general middleware platform, including open standards and communication protocol layer, device access connection layer, data exchange and processing layer, and device driver adaptation layer; Based on the universal middleware platform, smart home data is obtained, including historical usage data, connection status, operating parameters, and energy consumption monitoring data; Acquire a data sharing relationship of smart homes, where the data sharing relationship indicates that there is a characteristic that the similarity of performance characteristics between the smart homes reaches a similarity threshold; Based on the data sharing relationship, traverse the smart home devices in online connection state to obtain online collaborative devices, where the online collaborative devices are smart home devices with data sharing relationship; Mining the regulatory relationship based on the data sharing relationship and building an adaptive regulatory strategy; Taking the energy consumption monitoring data of the online collaborative device as the optimization object and the minimum constrained energy consumption as the goal, the operating parameters are optimized and adjusted based on the adaptive control strategy to obtain control adjustment information, wherein the constrained energy consumption is the necessary energy consumption of the online collaborative device to ensure normal operation; The operating parameters are adjusted and controlled using the control adjustment information.
2. The energy-saving control method for smart home according to claim 1, characterized in that: The building of the universal middleware platform also includes: Set a connection range, where the connection range is the boundary positioning of the target control space; Configure a dual authentication mechanism for the platform access identification password and the connection scope; The dual verification mechanism is integrated into the universal middleware platform to perform location verification on access devices.
3. The energy-saving control method for smart home according to claim 1, characterized in that: The obtaining of the data sharing relationship of the smart home includes: Determine the performance of shared relationships, including lighting performance, temperature control performance, ventilation performance, and lighting performance; Extracting the operation characteristics of the smart home, and performing feature clustering with the lighting performance, temperature control performance, ventilation performance, and illumination performance as clustering centers to obtain a performance clustering set; Generating performance labels according to the performance cluster sets respectively, and identifying the performance types of the smart homes; The sharing combination relationship of the sharing relationship performance is obtained, the smart home is matched according to the sharing combination relationship and the performance type identifier, and the data sharing relationship of the smart home is determined.
4. The energy-saving control method for smart home according to claim 3, characterized in that: Determining the data sharing relationship of the smart home also includes: Obtaining the performance coverage and location of the smart home; Configure sharing constraints according to the performance coverage and the space in which it is located; The data sharing relationship of the smart home is screened by using the sharing constraint condition to determine the data sharing relationship.
5. The energy-saving control method for smart home according to claim 1, characterized in that: include: Obtain member restriction setting information, wherein the member restriction setting information includes setting user information, restricted device, restricted space, restricted time, and restricted parameter threshold; Acquiring overlapping restriction setting information based on the restriction device, and extracting overlapping user information; The control priority of the overlapping user information and the set user information in the restricted space is set, and the control priority is fitted into the control strategy of the restricted device, and the control strategy is used to adjust the restriction time and restriction parameter threshold of the restricted device according to the control priority.
6. The energy-saving control method for smart home according to claim 3, characterized in that: According to the data sharing relationship, control relationship mining is performed to construct an adaptive control strategy, including: Based on the data sharing relationship, extract historical performance data of the related equipment, including energy consumption, lighting, heat, ventilation, and configuration data points, wherein the data points include a set of energy consumption data and performance data with a sharing relationship; Based on the data points, a linear regression model is constructed with the energy consumption of one party of the shared device as the dependent variable and the performance data of the other party of the shared device as the independent variable, and the model parameters are determined by calculating the least squares method through the historical performance data; Determine the influence relationship and influence direction according to the model parameters, wherein the influence direction includes same-direction influence and reverse influence, and the parameter is a positive number when it is same-direction influence, and a negative number when it is reverse influence; An adaptive control strategy for shared equipment is established based on the linear regression model.
7. The energy-saving control method for smart home according to claim 6, characterized in that: The linear regression model is constructed by taking the energy consumption of one party of the shared device as the dependent variable and the performance data of the other party of the shared device as the independent variable, and the model parameters are determined by calculating through the least squares method through the historical performance data, including: The linear regression model is expressed as: n,1 =∝·Q n,2 +β, where solving the model parameters; Among them, Q n,1 , Q n,2 is a shared device in the nth group of data sharing relationships, ∝ and β are model parameters, ∝ represents the basic energy consumption when the performance data is zero, β represents the change in air conditioning energy consumption per unit change in lighting brightness, x i is the performance data of the i-th data point, y i is the energy consumption data of the i-th data point, n is the number of data sharing relationships, and m is the number of data points.
8. An energy-saving control system for smart home, characterized in that: The energy-saving control method for a smart home according to any one of claims 1 to 7 is used to implement the energy-saving control system for a smart home, comprising: A middleware building module, which is used to build a general middleware platform, including an open standard and communication protocol layer, a device access connection layer, a data exchange and processing layer, and a device driver adaptation layer; A data acquisition module, which is used to obtain smart home data based on the universal middleware platform, including historical usage data, connection status, operating parameters, and energy consumption monitoring data; A correlation mining module, wherein the correlation mining module is used to obtain data sharing relationships of smart homes, wherein the data sharing relationships represent that there is a characteristic that the similarity of performance characteristics between smart homes reaches a similarity threshold; A collaborative object determination module, the collaborative object determination module is used to traverse the smart home devices with an online connection state based on the data sharing relationship, and obtain online collaborative devices, wherein the online collaborative devices are smart home devices with a data sharing relationship; A control relationship mining module, wherein the control relationship mining module is used to mine the control relationship according to the data sharing relationship and construct an adaptive control strategy; An operation parameter optimization module, wherein the operation parameter optimization module is used to optimize the operation parameters based on the adaptive control strategy, taking the energy consumption monitoring data of the online collaborative device as the optimization object, taking the minimum constrained energy consumption as the goal, and obtaining control adjustment information. The constrained energy consumption is the necessary energy consumption of the online collaborative device to ensure normal operation; An energy-saving control module, wherein the energy-saving control module is used to adjust and control the operating parameters using the control adjustment information.
Citation Information
Patent Citations
Unstructured electric power big data analysis method based on deep learning
CN114723583A
Energy-saving control method and system of ultrasonic washing machine
CN117102148A
Energy management control system based on cloud computing and method thereof
US20130066477A1
Processing apparatus, processing method, and related device
WO2022141735A1
Cited By
Acid mist absorption tower intelligent control system based on big data
CN119847027A
Industrial process energy consumption optimization method based on information adaptive fusion
CN120491573A
An information adaptive fusion industrial process energy consumption optimization method
CN120491573B
Intelligent control system for alkalization reaction of cellulose ether
CN120644144A
Smart home load management method and system based on micro energy storage system
CN121615962A
