Household air conditioner energy consumption prediction method, device, storage medium and program product

Abstract

The application discloses a kind of occupant air conditioner energy consumption prediction method, equipment, storage medium and program product, it is related to air conditioner energy consumption simulation technical field.In the present application, by constructing resident agent, air conditioner agent and indoor thermal environment agent, the occupant behavior with high random characteristics including the interaction behavior with air conditioner is individualized and finely simulated, the synergistic influence mechanism of environmental factors such as building characteristics, climate conditions to occupant behavior model is quantified, the modeling of occupant-air conditioner equipment-environment real-time interaction is realized, so as to capture the dynamic adjustment process of occupant behavior with environmental change, so as to finally realize the accurate prediction of building air conditioner energy consumption.

Description

Methods, equipment, storage media and program products for predicting residential air conditioning energy consumption Technical Field

[0001] This application relates to the technical field of air conditioning energy consumption simulation, and in particular to residential air conditioning energy consumption prediction methods, residential air conditioning energy consumption prediction equipment, storage media, and computer program products. Background Technology

[0002] Most current research on building air conditioning energy consumption prediction focuses on deterministic factors, such as the thermal performance of the building envelope and air conditioning system design or control strategies. In contrast, the impact of highly stochastic resident behavior remains to be further explored. Even within the same residential building, air conditioning energy consumption varies significantly among different residents.

[0003] While existing research has considered the impact of resident behavior on air conditioning energy consumption, several shortcomings remain. Most studies rely on monitoring data, which can only characterize average group levels or typical patterns, failing to capture significant individual differences. Secondly, there is a lack of modeling for real-time interactions between people, equipment, and the environment, making it impossible to capture the dynamic adjustments in behavior as the environment changes. Furthermore, the collaborative influence mechanisms of building characteristics and climatic conditions on behavioral models have not been systematically quantified.

[0004] The above content is only used to help understand the technical solution of this application and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main purpose of this application is to provide a method, device, storage medium and computer program product for predicting residential air conditioning energy consumption, in order to solve the technical problem of inaccurate prediction of building air conditioning energy consumption.

[0006] To achieve the above objectives, this application proposes a method for predicting residential air conditioning energy consumption, the method comprising:

[0007] Obtain information on residents' air conditioning energy consumption behavior, building information, and meteorological data for the target households;

[0008] Based on the building information and meteorological data, a three-dimensional geometric model is constructed, and energy consumption simulation software is used to simulate the indoor thermal environment of the resident under the condition of no air conditioning operation to obtain the indoor temperature and humidity time series of the target resident. This series is used as the benchmark thermal environment input for the subsequent behavior model to judge the air conditioning operation, and as the content of the indoor thermal environment intelligent agent.

[0009] Based on the information on residents’ air conditioning energy consumption behavior, a resident intelligent agent and an air conditioning intelligent agent for the target household are established through intelligent agent modeling software. The resident intelligent agent senses the input from the baseline thermal environment or the coupling result from the previous time step at each time step, and triggers the air conditioning intelligent agent to perform start-stop operations and set the temperature according to the behavior decision rules, thereby obtaining the air conditioning start-stop and set temperature time series of the target household generated on the same time scale.

[0010] A bidirectional data transmission mechanism is established between the intelligent agent modeling software and the energy consumption simulation software, enabling them to interact in real time at a unified time step: the behavioral model outputs the air conditioning operation sequence as the control signal for energy consumption simulation at each time step, and the energy consumption simulation software updates the indoor temperature and humidity for the next time step according to the control signal and sends it back to the intelligent agent model in real time. Through the bidirectional coupling process of time-by-time cycle, dynamic feedback between indoor thermal environment and residents' behavior is realized, and the simulation of air conditioning energy consumption is completed.

[0011] In one embodiment, the steps of the resident agent sensing the input from the baseline thermal environment or the coupling result from the previous time step at each time step, and triggering the air conditioning agent to perform start / stop operations and set the temperature according to the behavioral decision rules, include:

[0012] The resident intelligent agent obtains the indoor air temperature, humidity, and airflow speed of the target household from the energy consumption simulation;

[0013] The effective indoor temperature is obtained by measuring the indoor air temperature, humidity, and airflow speed.

[0014] Based on the effective indoor temperature, the preset preferred temperature of the resident agent, and the resident agent's sensitivity to temperature, a temperature discomfort score is calculated.

[0015] Based on the temperature discomfort score, the air conditioning agent is triggered to perform start / stop operations and set the temperature.

[0016] In one embodiment, the step of obtaining the effective indoor temperature using the indoor air temperature, the humidity, and the airflow velocity includes:

[0017] Obtain the humidity correction factor and airflow speed correction factor ;

[0018] Based on humidity correction factor A linear mapping of humidity (RH) yields the humidity effect term. ;

[0019] Based on airflow correction factor airflow velocity Perform a linear mapping to obtain the airflow velocity influence term. ;

[0020] The effective indoor temperature is calculated based on the humidity effect, the airflow velocity effect, and the indoor air temperature.

[0021] In one embodiment, the step of calculating the temperature discomfort score based on the effective indoor temperature, the preset preferred temperature of the resident agent, and the resident agent's sensitivity to temperature includes:

[0022] Determine a first difference and a first degree of heat sensitivity corresponding to the first difference, wherein the first difference is the effective indoor temperature minus the preset preferred temperature of the resident smart agent and minus half of the preset comfort dead zone width;

[0023] Determine the second difference and the corresponding second sensitivity to cold, wherein the second difference is the preset preferred temperature of the resident agent minus the effective indoor temperature and half of the preset comfort dead zone width;

[0024] The first discomfort score of the first sensitivity and the second discomfort score of the second sensitivity are calculated using the logistic function, wherein the logistic function is used to nonlinearly map the first difference and the second difference according to the first sensitivity and the second sensitivity.

[0025] The larger of the first discomfort score and the second discomfort score is taken as the temperature discomfort score.

[0026] In one embodiment, the step of triggering the air conditioning agent to perform start / stop operations and set the temperature based on the temperature discomfort score includes:

[0027] When a user is detected entering the target air-conditioned room, the current operating status of the air conditioner is determined; if the air conditioner is on, and the temperature is unsuitable... Greater than the preset activation threshold And when the duration exceeds a preset duration threshold, the air conditioner's intelligent agent is triggered to either turn on or remain on; when the temperature is unsuitable... Less than or equal to the preset activation threshold If the air conditioner is off, the air conditioner operation will not be performed.

[0028] Specifically, when the air conditioner is on, the set temperature is determined based on the real-time number of people in the room and their age groups: when there is only one user in the room, the set temperature is adjusted to that user's preferred temperature; when there are multiple users in the room, the user with the highest priority is selected based on a preset priority strategy, and the air conditioner's set temperature is adjusted to that user's preferred temperature; when a user is detected leaving the room, the number of people in the room after leaving is determined; when the number of people in the room after leaving is 0, the air conditioner's intelligent agent is triggered to perform a shutdown operation; when the number of people in the room after leaving is greater than 0, the air conditioner is not shut down.

[0029] In one embodiment, the activation threshold The steps involved in obtaining information through subjective heat surveys include:

[0030] By conducting a questionnaire survey on users' subjective feelings of heat or heat preferences, the effective temperature feedback from users is mapped to a temperature discomfort score, and the corresponding temperature discomfort score is determined as the activation threshold. .

[0031] In one embodiment, the step of establishing a resident intelligent agent and an air conditioning intelligent agent for the target household based on the resident's air conditioning energy consumption behavior information using intelligent agent modeling software includes:

[0032] Based on the resident attributes in the resident air conditioning energy consumption behavior information, the mobile and air conditioning operation logic is modeled to construct the resident intelligent agent of the target household;

[0033] Based on the air conditioning attributes and control strategies in the information on residents' air conditioning energy consumption behavior, an air conditioning intelligent agent for the target household is constructed.

[0034] Furthermore, to achieve the above objectives, this application also proposes a residential air conditioning energy consumption prediction device, which includes:

[0035] The first module is used to obtain information on residents' air conditioning energy consumption behavior, building information, and meteorological data for the target households.

[0036] The second module is used to construct a three-dimensional geometric model based on the building information and the meteorological data, and to use energy consumption simulation software to simulate the indoor thermal environment of the resident under the condition of no air conditioning operation, so as to obtain the indoor temperature and humidity time series of the target resident. This series is used as the benchmark thermal environment input for the subsequent behavior model to judge the air conditioning operation, and as the content of the indoor thermal environment intelligent agent.

[0037] The third module is used to establish the resident intelligent agent and air conditioning intelligent agent of the target household based on the resident air conditioning energy consumption behavior information through intelligent agent modeling software. The resident intelligent agent senses the input from the reference thermal environment or the coupling result of the previous time step at each time step, and triggers the air conditioning intelligent agent to perform start-stop operation and set temperature according to the behavior decision rules, so as to obtain the air conditioning start-stop and set temperature time series of the target household generated on the same time scale.

[0038] The fourth module is used to establish a two-way data transmission mechanism between the intelligent agent modeling software and the energy consumption simulation software, enabling them to interact in real time at a unified time step: the behavior model outputs the air conditioning operation sequence as the control signal for energy consumption simulation at each time step, and the energy consumption simulation software updates the indoor temperature and humidity for the next time step according to the control signal and sends it back to the intelligent agent model in real time. Through the time-by-time bidirectional coupling process, dynamic feedback between the indoor thermal environment and residents' behavior is realized, and the simulation of air conditioning energy consumption is completed.

[0039] In addition, to achieve the above objectives, this application also proposes a residential air conditioning energy consumption prediction device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the residential air conditioning energy consumption prediction method described above.

[0040] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the residential air conditioning energy consumption prediction method described above.

[0041] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the residential air conditioning energy consumption prediction method described above.

[0042] One or more technical solutions proposed in this application have at least the following technical effects:

[0043] This application proposes a method for predicting residential air conditioning energy consumption. First, a three-dimensional geometric model is constructed based on the building information and meteorological data corresponding to the target household. Energy simulation software is then used to simulate the indoor thermal environment of the household under conditions without air conditioning operation, obtaining the indoor temperature and humidity time series for the target household. This series serves as the baseline thermal environment input for subsequent behavioral models to determine air conditioning operation and is also used as the content of the indoor thermal environment intelligent agent. Then, based on the residential air conditioning energy consumption behavior information corresponding to the target household, a resident intelligent agent and an air conditioning intelligent agent are established for the target household using intelligent agent modeling software. The resident intelligent agent perceives the coupling results from the baseline thermal environment input or the previous time step at each time step and, based on the behavior... To trigger the air conditioning agent to perform start / stop operations and set temperatures according to decision rules, a time series of air conditioning start / stop and set temperatures for the target resident is generated on the same time scale. Finally, a bidirectional data transmission mechanism is established between the agent modeling software and the energy consumption simulation software, enabling them to interact in real time at a unified time step: the behavior model outputs the air conditioning operation sequence as the control signal for energy consumption simulation at each time step, and the energy consumption simulation software updates the indoor temperature and humidity for the next time step based on the control signal and sends it back to the agent model in real time. Through this time-cycle bidirectional coupling process, dynamic feedback between the indoor thermal environment and resident behavior is achieved, and the simulation of air conditioning energy consumption is completed. In other words, in this application, by constructing resident agents, air conditioning agents, and indoor thermal environment agents, highly random resident behaviors, including interactions with air conditioning, are personalized and simulated in detail. The system quantifies the collaborative influence mechanism of environmental factors such as building characteristics and climate conditions on the resident behavior model, realizing the modeling of real-time interaction between residents, air conditioning equipment, and the environment. This captures the dynamic adjustment process of resident behavior as the environment changes, ultimately achieving accurate prediction of building air conditioning energy consumption. Attached Figure Description

[0044] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0045] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1 is a flowchart of the first embodiment of the household air conditioning energy consumption prediction method of this application;

[0047] Figure 2 is a schematic diagram of the first detailed process of step S30 provided in the first embodiment of the household air conditioning energy consumption prediction method of this application;

[0048] Figure 3 is a schematic diagram of the second detailed process of step S30 provided in the first embodiment of the household air conditioning energy consumption prediction method of this application;

[0049] Figure 4 is a schematic diagram of the module structure of the household air conditioning energy consumption prediction device according to an embodiment of this application;

[0050] Figure 5 is a schematic diagram of the equipment structure of the hardware operating environment involved in the residential air conditioning energy consumption prediction method in this application embodiment.

[0051] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0052] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0053] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0054] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device capable of performing the above functions, such as a residential air conditioning energy consumption prediction device. The following description uses a residential air conditioning energy consumption prediction device as an example to illustrate this embodiment and the subsequent embodiments.

[0055] In residential building air conditioning energy consumption research, some studies have incorporated resident behavioral factors into the analysis. For example, using questionnaires, electricity usage records, and IoT monitoring data, probabilistic models of air conditioning operation or typical set temperature curves are established and combined with building energy consumption simulation tools. These methods, to some extent, improve upon the limitations of modeling solely based on physical parameters, making energy consumption predictions closer to actual usage. However, these methods have significant shortcomings:

[0056] 1. Insufficient characterization of individual differences. Existing models mostly use group average data or typical user patterns, which are difficult to reflect the significant differences among residents in terms of air conditioner activation temperature, set temperature, and usage time.

[0057] 2. Lack of real-time interaction mechanisms. Most studies treat residents' behavior as static or independent events, lacking real-time interaction modeling between different people, between people and equipment, and between people and the environment, thus failing to capture the dynamic adjustment process of behavior as the environment changes.

[0058] 3. The synergistic mechanisms among environment, behavior, and building characteristics have not been systematically quantified. For example, key coupling relationships such as how differences in building thermal environment affect residents' temperature perception and air conditioning operation behavior, and how behavioral feedback further affects building energy performance, have not yet formed a systematic quantitative framework in existing research.

[0059] 4. Poor feasibility for engineering implementation. The lack of a real-time two-way data exchange interface between the behavioral model and the building energy consumption simulation platform makes it difficult to directly apply the research results to engineering design, operation optimization, or intelligent control systems.

[0060] To address the above shortcomings, this application proposes a method for predicting residential air conditioning energy consumption based on differentiated thermal comfort needs using ABM (Agent-Based Modeling). This method can be roughly divided into four steps: First, data collection and construction. Two core datasets are established for each household, and meteorological data is collected simultaneously: (1) Residents' air conditioning energy consumption behavior information, including residents' movement trajectory data (i.e., the daily entry and exit time patterns of family members and their movement to various rooms), air conditioning usage habits records, and family population structure, etc. It should be noted that the data related to personal information involved in this application have been authorized and agreed to by the users when applied to the specific methods or products of this application, and the collection, use, and processing of relevant personal information data have complied with the relevant laws, regulations, and standards of the relevant countries and regions; (2) Building information, including residential unit type, thermal parameters of building envelope, and performance parameters of air conditioning equipment, etc. (3) Meteorological data, including outdoor temperature and humidity and solar radiation obtained from meteorological station data. Thus, high-resolution, multi-dimensional data can provide real and calibrable input conditions for subsequent models, avoiding errors caused by a single data source. Second, simulation of building and indoor thermal environment. After creating a 3D building geometry model using SketchUp (a 3D design software), the EnergyPlus computing engine was invoked through OpenStudio (a SketchUp plugin) to simulate the indoor thermal environment. The EnergyPlus computing engine is an energy consumption simulation software, and the time step for the indoor thermal environment simulation was set to 10 minutes. Furthermore, the creation of the 3D building geometry model and the indoor thermal environment simulation were based on the building data and weather data from the first step. Finally, the indoor temperature and humidity data were output to a database in SQLite format. The initial simulation assumed no air conditioning intervention. Thus, by quantifying the natural temperature and humidity changes of the building itself and the environmental conditions, a baseline reference was provided for subsequent judgments on air conditioning control behavior. The third step involved constructing a multi-agent model. A multi-agent model was constructed in Anylogic (a modeling and simulation tool), with the time step also set to 10 minutes. Based on a multi-agent modeling approach, three agents—resident agent, air conditioning agent, and indoor thermal environment agent—are constructed. The attributes of the resident agent are assigned from previously acquired resident information. The indoor thermal environment agent uses EnergyPlus to simulate indoor environmental data at unit time steps (10 minutes) under conditions without air conditioning intervention, and outputs the data in SQLite format. Furthermore, interaction rules for the three types of agents are defined to generate time series of air conditioning on / off states and temperature settings for each room, stored in XML format. The fourth step is bidirectional feedback collaborative simulation. A bidirectional feedback mechanism is established to achieve multi-platform collaborative simulation.The Building Controls Virtual Test Bed (BCVTB) is used as an intermediate coupling platform to achieve data interconnection and synchronous operation between Anylogic and EnergyPlus. Through BCVTB, the air conditioning start / stop status and time series with temperature settings obtained from multi-agent simulation in Anylogic are transmitted to EnergyPlus in real time at 10-minute time steps, thereby driving its hourly air conditioning energy consumption simulation. Simultaneously, to form a closed-loop control logic, indoor thermal environment parameters calculated in EnergyPlus are fed back to Anylogic in real time, allowing the resident agent to make thermal comfort judgments and determine air conditioning control behavior.

[0061] The residential air conditioning energy consumption prediction method proposed in this application has the following expected application scenarios: 1. Residential energy-saving design and renovation: Optimizing air conditioning system design and building envelope schemes for different apartment types and family structures. 2. Building energy consumption prediction: Providing prediction results with higher accuracy and closer resemblance to reality than traditional models. 3. Smart air conditioning and smart homes: Providing dynamic setting strategies for air conditioning controllers based on behavior-environment feedback to reduce energy waste. 4. Providing simulation data based on real behavior for energy-saving rules, air conditioning energy efficiency evaluation indicators, and building design codes.

[0062] This application provides a method for predicting household air conditioning energy consumption. Referring to Figure 1, Figure 1 is a flowchart of the first embodiment of the method for predicting household air conditioning energy consumption.

[0063] In this embodiment, the residential air conditioning energy consumption prediction method includes steps S10 to S40:

[0064] Step S10: Obtain information on residents' air conditioning energy consumption behavior, building information, and meteorological data corresponding to the target households;

[0065] Establish information on residents' air conditioning energy consumption behavior, building information, and meteorological data, and collect relevant data simultaneously. Specifically, residents' air conditioning energy consumption behavior information includes occupation, activity time information, preferred temperature, and temperature sensitivity. It may also include residents' movement trajectories (time patterns of family members entering and leaving the residence and indoor room movement), air conditioning usage habits records, and family population structure information, etc. Building information includes residential unit type, building area, thermal parameters of the building envelope, number of floors, construction year, structural type, and air conditioning equipment performance parameters, etc. Meteorological data includes measured data from local meteorological stations, such as outdoor air temperature and humidity, wind speed, and solar radiation. The data collection time step is 1 second, and the data is stored and transmitted in CSV format.

[0066] Step S20: Based on building information and meteorological data, construct a three-dimensional geometric model and use energy consumption simulation software to simulate the indoor thermal environment of the resident under the condition of no air conditioning operation to obtain the indoor temperature and humidity time series of the target resident. This series is used as the benchmark thermal environment input for the subsequent behavior model to judge the air conditioning operation and as the content of the indoor thermal environment intelligent agent.

[0067] Initialization is performed according to the following initialization conditions: the indoor temperature is the same as the outdoor temperature at the initial moment, and the air conditioner is initially set to off; the residents' initial locations are randomly assigned to bedrooms, living rooms or other spaces according to their daily routines; the thermal comfort threshold, preferred temperature, etc. of each resident are generated according to attributes such as age, occupation and gender derived from questionnaire surveys and statistical distributions; the energy efficiency ratio and minimum running time of the air conditioning equipment are initially set.

[0068] A 3D building geometry model of the target resident was constructed using SketchUp based on building information and meteorological data. The EnergyPlus computing engine in OpenStudio was then used to simulate the indoor thermal environment corresponding to the 3D building geometry model, with a time step of 10 minutes. Input data included building information and meteorological data. The output was the initial indoor temperature and humidity time series for each room under conditions of no air conditioning intervention and no windows open, stored in an SQLite format database. It should be noted that the smallest unit of the model simulation can be a resident, or the simulation can be of the entire building.

[0069] Step S30: Based on the residents' air conditioning energy consumption behavior information, the residents' intelligent agent and the air conditioning intelligent agent of the target household are established through intelligent agent modeling software. The residents' intelligent agent senses the input from the reference thermal environment or the coupling result of the previous time step at each time step, and triggers the air conditioning intelligent agent to perform start-stop operation and set temperature according to the behavior decision rules, so as to obtain the air conditioning start-stop and set temperature time series of the target household generated on the same time scale.

[0070] Step S40: Establish a two-way data transmission mechanism between the intelligent agent modeling software and the energy consumption simulation software, enabling them to interact in real time at a unified time step: the behavior model outputs the air conditioning operation sequence as the control signal for energy consumption simulation at each time step, and the energy consumption simulation software updates the indoor temperature and humidity for the next time step according to the control signal and sends it back to the intelligent agent model in real time. Through the time-by-time bidirectional coupling process, dynamic feedback between the indoor thermal environment and residents' behavior is realized, and the simulation of air conditioning energy consumption is completed.

[0071] In other words, based on residents' air conditioning energy consumption behavior information, a resident intelligent agent and an air conditioning intelligent agent for the target household are constructed through intelligent agent modeling software. The resident intelligent agent senses the input from the baseline thermal environment or the coupling result from the previous time step at each time step, and triggers the air conditioning intelligent agent to perform start-stop operations and set the temperature according to the behavior decision rules, thereby changing the indoor temperature and humidity to achieve the thermal comfort of the resident intelligent agent, resulting in the air conditioning start-stop and set temperature time series of the target household generated on the same time scale. The initial coupling result is the baseline indoor thermal environment input of the target household before the air conditioning is turned on and without the intervention of the air conditioning. After the air conditioning starts running, it is the coupling result based on the previous time step.

[0072] ABM is a bottom-up simulation technique that allows individuals to be represented as agents with personal attributes and behavioral possibilities. By assigning interaction rules to these agents and other agents and the surrounding environment, it is possible to observe how the macroscopic phenomena of the system are affected by the microscopic interactions of these agents.

[0073] In one feasible implementation, referring to Figure 2, the step of establishing the resident intelligent agent and air conditioning intelligent agent for the target household based on resident air conditioning energy consumption behavior information using intelligent agent modeling software includes:

[0074] Step S30A1: Based on the resident attributes in the resident air conditioning energy consumption behavior information, perform mobile and air conditioning operation logic modeling to construct the resident intelligent agent of the target household;

[0075] Step S30A2: Based on the air conditioning attributes and control strategies in the residents' air conditioning energy consumption behavior information, construct the air conditioning intelligent agent for the target household.

[0076] For constructing a resident intelligent agent, resident attributes include demographic characteristics such as age, gender, occupation, and family role; air conditioning operation logic includes behavioral characteristics such as daily schedule, movement probability matrix, thermal comfort threshold, and preferred temperature; and state variables such as location (room), activity state (rest / study / work / sleep), and perceived comfort. Mobility modeling employs a combination of Markov chains and event-driven mechanisms. The state set includes bedroom, living room, kitchen, bathroom, and outdoors. Transition probabilities are obtained based on questionnaire / survey data, and forced state switching is triggered by events such as waking up, leaving home, returning home, and sleeping.

[0077] For building an intelligent air conditioner, the air conditioner attributes include installation location (e.g., living room / bedroom), operating status (on / off), set temperature (triggered by residents), and device characteristics (e.g., minimum running time of 20 minutes); the behavioral logic includes receiving resident commands (e.g., on / off / temperature adjustment) and device status changes (delayed start / stop / restricted frequent start / stop, etc.); the control strategy includes setting the temperature to the individual's preferred temperature in single-person scenarios, and adopting the principle of prioritizing heat-sensitive groups when setting the temperature in multi-person scenarios.

[0078] Furthermore, the modeling unit takes households as the modeling boundary for modeling. The types of intelligent agents can include resident agent (active subject), air conditioning agent (controlled execution subject), and indoor thermal environment agent (environmental background conditions). The interaction logic is: resident perceives the environment → judges comfort → operates the air conditioner → the air conditioner changes the indoor environment → feedback to the resident → loop. Among them, the set attributes of the indoor thermal environment agent include indoor temperature and humidity (updated over time). Its data source includes hourly indoor thermal environment data obtained through EnergyPlus simulation, and can be corrected in real time by the air conditioner operation signal. Furthermore, the interaction rules between resident agent, air conditioning agent and indoor thermal environment agent can be designed: (1) resident → air conditioner. At each time step, the resident agent perceives the current indoor temperature and humidity data provided by the indoor thermal environment agent, calculates the effective temperature and obtains the temperature discomfort score; when the discomfort score exceeds the preset threshold or the set temperature needs to be adjusted, the resident agent triggers the air conditioning agent to perform the corresponding start-stop operation or set temperature adjustment, and outputs the time sequence of air conditioner start-stop status and set temperature. (2) air conditioner → indoor environment. The air conditioning agent updates its own operating status (on / off) and set temperature according to the resident agent's operation decision, and transmits these control parameters to the indoor thermal environment agent; the indoor thermal environment agent calculates the indoor temperature and humidity changes for the next time step based on the air conditioning operating status, set temperature, and current meteorological and building thermal parameters. (3) Environment → Resident. The indoor thermal environment agent updates indoor air temperature, humidity and other environmental parameters according to the air conditioning operating conditions and external meteorological conditions at each time step, and transmits the updated indoor environmental data back to the resident agent, so that it can re-determine thermal discomfort and make air conditioning decisions in the next time step, thereby forming a dynamic feedback loop between resident behavior, air conditioning operation and indoor environment.

[0079] In another feasible implementation, referring to FIG3, the steps of the resident intelligent agent sensing the target indoor temperature and humidity and triggering the air conditioning intelligent agent to change the indoor temperature and humidity to achieve the thermal comfort of the resident intelligent agent include:

[0080] Step S30B1: The resident agent obtains the indoor air temperature, humidity and airflow speed of the target household from the energy consumption simulation.

[0081] Step S30B2: Obtain the effective indoor temperature by measuring indoor air temperature, humidity, and airflow speed;

[0082] Step S30B3: Based on the effective indoor temperature, the resident's preferred temperature, and the resident's sensitivity to temperature, calculate the temperature discomfort score.

[0083] Step S30B4: Based on the temperature discomfort score, the air conditioning intelligent agent is triggered to perform start / stop operations and set the temperature.

[0084] First, the resident agent obtains the indoor air temperature of the target household from the indoor temperature and humidity data obtained from energy consumption simulation. ,humidity and airflow speed Then, through indoor air temperature ,humidity and airflow speed Obtain the effective indoor temperature In one embodiment, humidity can be used. and airflow speed Indoor air temperature After correction, the effective indoor temperature is obtained. Next, based on the effective indoor temperature Residents' smart agents' preset preferred temperature In addition, the temperature discomfort score is calculated based on the sensitivity of the resident's intelligent agent to temperature. Finally, based on the temperature discomfort score The system triggers the air conditioning intelligent agent to perform start / stop operations and set the temperature to change the indoor temperature and humidity, thereby achieving thermal comfort for the residents.

[0085] In one embodiment, step S30B2 includes:

[0086] Obtain the humidity correction factor and airflow speed correction factor ;

[0087] Based on humidity correction factor A linear mapping of humidity (RH) yields the humidity effect term. ;

[0088] Based on airflow correction factor airflow velocity Perform a linear mapping to obtain the airflow velocity influence term. ;

[0089] The effective indoor temperature is calculated based on the effects of humidity, airflow velocity, and indoor air temperature.

[0090] In this embodiment, a humidity correction factor is used. (Typical values ​​are 0.03–0.06 ℃ / %) for humidity Perform a linear mapping to obtain the humidity effect term. In one embodiment, the humidity effect term is the amount by which humidity corrects for air temperature: ; through airflow correction coefficient (Typical values ​​are 1.0–1.5 ℃ / (m / s)) for airflow velocity Perform a linear mapping to obtain the airflow velocity influence term. In one embodiment, the airflow velocity effect term is the correction amount of airflow velocity to air temperature: The correction for air temperature based on humidity, the correction for air temperature based on airflow speed, and indoor air temperature are calculated as described above. The effective indoor temperature can be calculated: .

[0091] In one embodiment, step S30B3 includes:

[0092] Determine the first difference and the corresponding first sensitivity to heat, wherein the first difference is the indoor effective temperature minus the resident's smart agent's preset preferred temperature and minus half of the preset comfort dead zone width;

[0093] Determine the second difference and the corresponding second sensitivity to cold, wherein the second difference is the preset preferred temperature of the resident agent minus the effective indoor temperature and half of the preset comfort dead zone width;

[0094] The first unsuitable score for the first sensitivity level and the second unsuitable score for the second sensitivity level are calculated using the logistic function, where the logistic function is used to perform a nonlinear mapping between the first and second differences according to the first and second sensitivity levels.

[0095] The larger of the first and second unsuitable fractions is taken as the temperature unsuitable fraction.

[0096] In this embodiment, the first difference is determined as follows: The first difference corresponds to the first sensitivity to heat. Second difference: The second difference corresponds to the second sensitivity to cold. The first unsuitable score for the first sensitivity level is calculated using the logistic function. The second ill-fitting fraction of the second sensitivity is calculated using the logistic function. The larger of the first and second unsuitability fractions is taken as the temperature unsuitability fraction.

[0097] Among them, the logistic function , The preset comfort temperature range is typically 0.6–1.0 ℃, with the preset target comfort temperature typically set at 0.8 ℃.

[0098] In one embodiment, step S30B4 includes:

[0099] When a user is detected entering the target air-conditioned room, the current operating status of the air conditioner is determined; if the air conditioner is on, and the temperature is unsuitable... Greater than the preset activation threshold And when the duration exceeds a preset duration threshold, the air conditioner's intelligent agent is triggered to either turn on or remain on; when the temperature is unsuitable... Less than or equal to the preset activation threshold If the air conditioner is off, the air conditioner operation will not be performed.

[0100] Specifically, when the air conditioner is on, the set temperature is determined based on the real-time number of people in the room and their age groups: when there is only one user in the room, the set temperature is adjusted to that user's preferred temperature; when there are multiple users in the room, the user with the highest priority is selected based on a preset priority strategy, and the air conditioner's set temperature is adjusted to that user's preferred temperature; when a user is detected leaving the room, the number of people in the room after leaving is determined; when the number of people in the room after leaving is 0, the air conditioner's intelligent agent is triggered to perform a shutdown operation; when the number of people in the room after leaving is greater than 0, the air conditioner is not shut down.

[0101] In one embodiment, the temperature discomfort score ranges from 0 to 1, representing the degree of comfort from complete comfort to severe discomfort. This score not only reflects an individual's dynamic perception of environmental changes but also facilitates energy consumption optimization and sensitivity analysis by the model. Therefore, when a resident is in a room and the temperature discomfort score S > a preset temperature discomfort score θon (e.g., 0.45) for a certain period of time (i.e., the duration is greater than a preset duration threshold), it is determined to be thermal discomfort, triggering the air conditioner to turn on, and the air conditioning agent changes the indoor temperature and humidity.

[0102] Furthermore, this application proposes a modeling method for air conditioning usage behavior that considers the interaction of family members. Unlike current methods that only focus on individual behavior, this method incorporates social interactions among family members (such as temperature setting negotiations), i.e., multi-resident interactions, into the air conditioning energy consumption prediction model. This can more realistically reflect the energy decision-making process in the residential environment, making air conditioning energy consumption prediction more accurate. In one specific implementation: 1. When a person enters an air-conditioned room, it is determined whether the air conditioner is turned on. If the air conditioner is turned on, a judgment is made regarding heat discomfort. If S≥θon, the air conditioner is turned on; if S≤θon, the air conditioner is not operated. If the air conditioner is not turned on, it is not operated. 2. When setting the temperature after the air conditioner is turned on, the number of people in the room is determined. If there is only one person in the room, the preferred temperature for that person can be set individually. If there are two or more people in the room, the age group of the people in the room is further determined, and the temperature is set according to the age group. Specifically, if there are multiple age groups, the priority of different age groups is determined, and the preferred temperature of each priority group is set; if there is a single age group, the preferred temperature of that group can be set directly. 3. When a person leaves the air-conditioned room, further determine the number of people in the room after they leave. If the number of people is 0, then turn off the air conditioner; if the number of people is greater than 0, then the person's departure will not affect the operation of the air conditioner, that is, do not operate the air conditioner.

[0103] In one embodiment, the activation threshold The steps involved in obtaining information through subjective heat surveys include:

[0104] By conducting a questionnaire survey on users' subjective feelings of heat or heat preferences, the effective temperature feedback from users is mapped to a temperature discomfort score, and the corresponding temperature discomfort score is determined as the activation threshold. .

[0105] For example, by conducting a questionnaire survey on users' subjective feelings of heat or heat preferences, the effective temperature that users reported as "significantly uncomfortable" or "needs to turn on the air conditioner" can be mapped to a discomfort score. And the corresponding discomfort score is determined as the activation threshold. .

[0106] In step S30 above, based on ABM technology, a differentiated air conditioning usage behavior model for household residents is established. The model focuses on quantifying the behavioral differences of family members (considering characteristics such as age and occupation) in terms of thermal comfort preferences and equipment operation habits, providing more accurate human behavior input parameters for building air conditioning energy consumption prediction.

[0107] In this embodiment, BCVTB is used as the coupling interface to achieve bidirectional collaboration between AnyLogic and EnergyPlus: AnyLogic transmits the air conditioner start / stop and set temperature sequence to EnergyPlus; EnergyPlus performs energy consumption simulation based on the input signals and outputs indoor temperature, humidity, and energy consumption results; the simulation results from EnergyPlus are fed back to AnyLogic in real time, allowing the resident agent to use them for subsequent thermal comfort assessment and air conditioner operation decisions. This bidirectional feedback mechanism forms a closed-loop control logic, enabling the model to dynamically adapt to environmental changes and accurately reflect the impact of resident behavior differences on air conditioner energy consumption.

[0108] In step S30 above, an integrated framework for ABM and building air conditioning energy consumption simulation tools is developed, namely the ABM-EnergyPlus collaborative simulation framework. Taking into account the influence of human behavior and environmental factors, a new residential air conditioning energy consumption prediction model is constructed. Through BCVTB, bidirectional real-time coupling is achieved, enabling the behavior model to directly drive energy consumption calculation and receive real-time feedback from the indoor thermal environment, forming a closed-loop decision-making process, and ultimately effectively reducing the difference between simulated and actual values.

[0109] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the household air conditioning energy consumption prediction method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0110] This application also provides a residential air conditioning energy consumption prediction device. Please refer to Figure 4. The residential air conditioning energy consumption prediction device includes:

[0111] The first module 10 is used to obtain information on residents’ air conditioning energy consumption behavior, building information and meteorological data for the target households;

[0112] The second module 20 is used to construct a three-dimensional geometric model based on the building information and the meteorological data, and to use energy consumption simulation software to simulate the indoor thermal environment of the resident under the condition of no air conditioning operation, so as to obtain the indoor temperature and humidity time series of the target resident. This series is used as the benchmark thermal environment input for the subsequent behavior model to judge the air conditioning operation, and as the content of the indoor thermal environment intelligent agent.

[0113] The third module 30 is used to establish the resident intelligent agent and air conditioning intelligent agent of the target household based on the resident air conditioning energy consumption behavior information through intelligent agent modeling software. The resident intelligent agent senses the input from the reference thermal environment or the coupling result of the previous time step at each time step, and triggers the air conditioning intelligent agent to perform start-stop operation and set temperature according to the behavior decision rules, so as to obtain the air conditioning start-stop and set temperature time series of the target household generated on the same time scale.

[0114] The fourth module 40 is used to establish a two-way data transmission mechanism between the intelligent agent modeling software and the energy consumption simulation software, enabling the two to interact in real time at a unified time step: the behavior model outputs the air conditioning operation sequence as the control signal for energy consumption simulation at each time step, and the energy consumption simulation software updates the indoor temperature and humidity for the next time step according to the control signal and sends it back to the intelligent agent model in real time. Through the time-by-time bidirectional coupling process, dynamic feedback between the indoor thermal environment and residents' behavior is realized, and the simulation of air conditioning energy consumption is completed.

[0115] In one embodiment, the third module 30 is further configured to:

[0116] The resident intelligent agent obtains the indoor air temperature, humidity, and airflow speed of the target household from the energy consumption simulation;

[0117] The effective indoor temperature is obtained by measuring the indoor air temperature, humidity, and airflow speed.

[0118] Based on the effective indoor temperature, the preset preferred temperature of the resident agent, and the resident agent's sensitivity to temperature, a temperature discomfort score is calculated.

[0119] Based on the temperature discomfort score, the air conditioning agent is triggered to perform start / stop operations and set the temperature.

[0120] In one embodiment, the third module 30 is further configured to:

[0121] Obtain the humidity correction factor and airflow speed correction factor ;

[0122] Based on humidity correction factor A linear mapping of humidity (RH) yields the humidity effect term. ;

[0123] Based on airflow correction factor airflow velocity Perform a linear mapping to obtain the airflow velocity influence term. ;

[0124] The effective indoor temperature is calculated based on the humidity effect, the airflow velocity effect, and the indoor air temperature.

[0125] In one embodiment, the third module 30 is further configured to:

[0126] Determine a first difference and a first degree of heat sensitivity corresponding to the first difference, wherein the first difference is the effective indoor temperature minus the preset preferred temperature of the resident smart agent and minus half of the preset comfort dead zone width;

[0127] Determine the second difference and the corresponding second sensitivity to cold, wherein the second difference is the preset preferred temperature of the resident agent minus the effective indoor temperature and half of the preset comfort dead zone width;

[0128] The first discomfort score of the first sensitivity and the second discomfort score of the second sensitivity are calculated using the logistic function, wherein the logistic function is used to nonlinearly map the first difference and the second difference according to the first sensitivity and the second sensitivity.

[0129] The larger of the first discomfort score and the second discomfort score is taken as the temperature discomfort score.

[0130] In one embodiment, the third module 30 is further configured to:

[0131] When a user is detected entering the target air-conditioned room, the current operating status of the air conditioner is determined; if the air conditioner is on, and the temperature is unsuitable... Greater than the preset activation threshold And when the duration exceeds a preset duration threshold, the air conditioner's intelligent agent is triggered to either turn on or remain on; when the temperature is unsuitable... Less than or equal to the preset activation threshold If the air conditioner is off, the air conditioner operation will not be performed.

[0132] Specifically, when the air conditioner is on, the set temperature is determined based on the real-time number of people in the room and their age groups: when there is only one user in the room, the set temperature is adjusted to that user's preferred temperature; when there are multiple users in the room, the user with the highest priority is selected based on a preset priority strategy, and the air conditioner's set temperature is adjusted to that user's preferred temperature; when a user is detected leaving the room, the number of people in the room after leaving is determined; when the number of people in the room after leaving is 0, the air conditioner's intelligent agent is triggered to perform a shutdown operation; when the number of people in the room after leaving is greater than 0, the air conditioner is not shut down.

[0133] In one embodiment, the third module 30 is further configured to:

[0134] By conducting a questionnaire survey on users' subjective feelings of heat or heat preferences, the effective temperature feedback from users is mapped to a temperature discomfort score, and the corresponding temperature discomfort score is determined as the activation threshold. .

[0135] In one embodiment, the third module 30 is further configured to:

[0136] Based on the resident attributes in the resident air conditioning energy consumption behavior information, the mobile and air conditioning operation logic is modeled to construct the resident intelligent agent of the target household;

[0137] Based on the air conditioning attributes and control strategies in the information on residents' air conditioning energy consumption behavior, an air conditioning intelligent agent for the target household is constructed.

[0138] The residential air conditioning energy consumption prediction device provided in this application, employing the residential air conditioning energy consumption prediction method in the above embodiments, can solve the technical problem of inaccurate building air conditioning energy consumption prediction. Compared with the prior art, the beneficial effects of the residential air conditioning energy consumption prediction device provided in this application are the same as those of the residential air conditioning energy consumption prediction method provided in the above embodiments, and other technical features in the residential air conditioning energy consumption prediction device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0139] This application provides a residential air conditioning energy consumption prediction device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the residential air conditioning energy consumption prediction method in the above embodiment 1.

[0140] Referring to Figure 5 below, a schematic diagram of a residential air conditioning energy consumption prediction device suitable for implementing embodiments of this application is shown. The residential air conditioning energy consumption prediction device in embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. The residential air conditioning energy consumption prediction device shown in Figure 5 is merely an example and should not impose any limitations on the functionality and scope of use of embodiments of this application.

[0141] As shown in Figure 5, the residential air conditioning energy consumption prediction device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory 1002 or a program loaded from a storage device 1003 into a random access memory 1004. The random access memory 1004 also stores various programs and data required for the operation of the residential air conditioning energy consumption prediction device. The processing unit 1001, the read-only memory 1002, and the random access memory 1004 are interconnected via a bus 1005. An input / output interface 1006 is also connected to the bus. Typically, the following systems can be connected to the input / output interface 1006: input devices 1007 including, for example, a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 allows the residential air conditioning energy consumption prediction device to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows residential air conditioning energy consumption prediction devices with various systems, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0142] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from read-only memory 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0143] The residential air conditioning energy consumption prediction device provided in this application, employing the residential air conditioning energy consumption prediction method in the above embodiments, can solve the technical problem of inaccurate building air conditioning energy consumption prediction. Compared with the prior art, the beneficial effects of the residential air conditioning energy consumption prediction device provided in this application are the same as those of the residential air conditioning energy consumption prediction method provided in the above embodiments, and other technical features of the residential air conditioning energy consumption prediction device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0144] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0145] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0146] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the residential air conditioning energy consumption prediction method in the above embodiments.

[0147] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0148] The aforementioned computer-readable storage medium may be included in a household air conditioning energy consumption prediction device; or it may exist independently and not installed in a household air conditioning energy consumption prediction device.

[0149] The aforementioned computer-readable storage medium carries one or more programs that, when executed by the residential air conditioning energy consumption prediction device, cause the device to: acquire information on the resident's air conditioning energy consumption behavior, building information, and meteorological data corresponding to the target resident; construct a three-dimensional geometric model based on the building information and meteorological data, and use energy consumption simulation software to simulate the indoor thermal environment of the resident under conditions without air conditioning operation, obtaining the indoor temperature and humidity time series of the target resident, which serves as the baseline thermal environment input for subsequent behavior models to judge air conditioning operation, and as the content of the indoor thermal environment intelligent agent; and establish the resident intelligent agent and air conditioning intelligent agent of the target resident based on the resident's air conditioning energy consumption behavior information through intelligent agent modeling software. The intelligent agent senses the input from the baseline thermal environment or the coupling result from the previous time step at each time step, and triggers the air conditioning agent to perform start-stop operations and set the temperature according to the behavioral decision rules, thus obtaining the air conditioning start-stop and set temperature time series of the target household at the same time scale; a two-way data transmission mechanism is established between the intelligent agent modeling software and the energy consumption simulation software, so that the two can interact in real time at a unified time step: the behavioral model outputs the air conditioning operation sequence as the control signal for energy consumption simulation at each time step, and the energy consumption simulation software updates the indoor temperature and humidity for the next time step according to the control signal and sends it back to the intelligent agent model in real time. Through the time-by-time cyclical two-way coupling process, the dynamic feedback of indoor thermal environment and residents' behavior is realized, and the simulation of air conditioning energy consumption is completed.

[0150] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0151] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0152] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0153] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described residential air conditioning energy consumption prediction method, thereby solving the technical problem of inaccurate building air conditioning energy consumption prediction. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the residential air conditioning energy consumption prediction method provided in the above embodiments, and will not be repeated here.

[0154] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the residential air conditioning energy consumption prediction method described above.

[0155] The computer program product provided in this application can solve the technical problem of inaccurate prediction of building air conditioning energy consumption. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the residential air conditioning energy consumption prediction method provided in the above embodiments, and will not be repeated here.

[0156] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A method for predicting household air conditioning energy consumption, characterized in that, The method for predicting household air conditioning energy consumption includes: acquiring information on the air conditioning energy consumption behavior, building information, and meteorological data of the target household; constructing a three-dimensional geometric model based on the building information and meteorological data, and using energy consumption simulation software to simulate the indoor thermal environment of the household under conditions without air conditioning operation, obtaining the indoor temperature and humidity time series of the target household, which serves as the baseline thermal environment input for subsequent behavior model judgments on air conditioning operation, and as the content of the indoor thermal environment intelligent agent; based on the information on the air conditioning energy consumption behavior, establishing a resident intelligent agent and an air conditioning intelligent agent for the target household through intelligent agent modeling software, wherein the resident intelligent agent perceives the coupling result from the baseline thermal environment input or the previous time step at each time step, and triggers the air conditioning intelligent agent to perform start-stop operations and set the temperature according to the behavior decision rules, thereby obtaining the air conditioning start-stop and set temperature time series of the target household generated on the same time scale; establishing a bidirectional data transmission mechanism between the intelligent agent modeling software and the energy consumption simulation software, enabling the two to interact in real time at a unified time step: the behavior model outputs the air conditioning operation sequence at each time step as the control of energy consumption simulation. The energy consumption simulation software updates the indoor temperature and humidity for the next time step based on the control signal and sends it back to the intelligent agent model in real time. Through a time-by-time bidirectional coupling process, dynamic feedback between the indoor thermal environment and residents' behavior is achieved, and the simulation of air conditioning energy consumption is completed. The intelligent agent model includes a resident intelligent agent, an air conditioning intelligent agent, an indoor thermal environment intelligent agent, and interaction rules between the resident intelligent agent, the air conditioning intelligent agent, and the indoor thermal environment intelligent agent. The steps for the resident intelligent agent to sense the input from the baseline thermal environment or the coupling result of the previous time step at each time step and trigger the air conditioning intelligent agent to perform start-stop operations and set the temperature according to the behavioral decision rules include: the resident intelligent agent obtains the indoor air temperature, humidity, and airflow speed of the target resident from the energy consumption simulation; obtains the effective indoor temperature through the indoor air temperature, humidity, and airflow speed; calculates the temperature discomfort score based on the effective indoor temperature, the resident intelligent agent's preset preferred temperature, and the resident intelligent agent's sensitivity to temperature; and triggers the air conditioning intelligent agent to perform start-stop operations and set the temperature based on the temperature discomfort score.

2. The residential air conditioning energy consumption prediction method as described in claim 1, characterized in that, The step of obtaining the effective indoor temperature using the indoor air temperature, humidity, and airflow speed includes: obtaining a humidity correction coefficient. and airflow speed correction factor Based on humidity correction factor A linear mapping of humidity (RH) yields the humidity effect term. Based on airflow correction coefficient airflow velocity Perform a linear mapping to obtain the airflow velocity influence term. The effective indoor temperature is calculated based on the humidity effect, the airflow velocity effect, and the indoor air temperature.

3. The residential air conditioning energy consumption prediction method as described in claim 1, characterized in that, The step of calculating the temperature discomfort score based on the effective indoor temperature, the resident agent's preset preferred temperature, and the resident agent's sensitivity to temperature includes: determining a first difference and a first sensitivity to heat corresponding to the first difference, wherein the first difference is the effective indoor temperature minus the resident agent's preset preferred temperature minus half of the preset comfort dead zone width; determining a second difference and a second sensitivity to cold corresponding to the second difference, wherein the second difference is the resident agent's preset preferred temperature minus the effective indoor temperature minus half of the preset comfort dead zone width; calculating a first discomfort score for the first sensitivity and a second discomfort score for the second sensitivity using a logistic function, wherein the logistic function is used to nonlinearly map the first difference and the second difference according to the first sensitivity and the second sensitivity; and taking the larger of the first discomfort score and the second discomfort score as the temperature discomfort score.

4. The residential air conditioning energy consumption prediction method as described in claim 1, characterized in that, The steps of triggering the air conditioner's intelligent agent to perform start / stop operations and set the temperature based on the temperature discomfort score include: when a user is detected entering the target air-conditioned room, determining the current operating status of the air conditioner; if the air conditioner is on, when the temperature discomfort score is... Greater than the preset activation threshold And when the duration exceeds a preset duration threshold, the air conditioner's intelligent agent is triggered to either turn on or remain on; when the temperature is unsuitable... Less than or equal to the preset activation threshold When the air conditioner is on, the start-up operation is not performed; if the air conditioner is off, the air conditioner operation is not performed. Specifically, when the air conditioner is on, the set temperature is determined based on the real-time number of people in the room and the age group of the users: when there is only one user in the room, the set temperature is adjusted to that user's preferred temperature; when there are multiple users in the room, the user with the highest priority is selected based on a preset priority strategy, and the air conditioner set temperature is adjusted to that user's preferred temperature; when a user is detected leaving the room, the number of people in the room after leaving is determined; when the number of people in the room after leaving is 0, the air conditioner intelligent agent is triggered to perform the shut-off operation; when the number of people in the room after leaving is greater than 0, the air conditioner shut-off operation is not performed.

5. The residential air conditioning energy consumption prediction method as described in claim 4, characterized in that, The opening threshold The steps involved in obtaining information through a subjective thermal survey include: conducting a questionnaire survey on users' subjective thermal sensations or thermal preferences, mapping the effective temperature feedback from users to a temperature discomfort score, and determining the corresponding temperature discomfort score as the activation threshold. 。 6. The method for predicting residential air conditioning energy consumption as described in claim 1, characterized in that, The step of establishing a resident intelligent agent and an air conditioning intelligent agent for the target household based on the resident's air conditioning energy consumption behavior information using intelligent agent modeling software includes: modeling the movement and air conditioning operation logic based on the resident attributes in the resident's air conditioning energy consumption behavior information to construct the resident intelligent agent for the target household; and constructing the air conditioning intelligent agent for the target household based on the air conditioning attributes and control strategies in the resident's air conditioning energy consumption behavior information.

7. A residential air conditioning energy consumption prediction device, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the residential air conditioning energy consumption prediction method as described in any one of claims 1 to 6.

8. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the residential air conditioning energy consumption prediction method as described in any one of claims 1 to 6.

9. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the steps of the residential air conditioning energy consumption prediction method as described in any one of claims 1 to 6.

Images