Building energy efficiency intelligent regulation and control method and device based on dynamic carbon perception

Abstract

The invention provides a building energy efficiency intelligent regulation and control method and device based on dynamic carbon perception, and relates to the field of building energy system regulation and control and carbon emission monitoring intelligent optimization, and the method comprises the steps: obtaining the real-time consumption data and environment state data of various energy sources in a target building; determining a dynamic carbon emission factor based on real-time consumption data and the environmental state data; based on the dynamic carbon emission factors and the real-time consumption data, comprehensive real-time carbon emission of the target building is determined; determining a control strategy of the energy equipment based on the comprehensive real-time carbon emission, the environment state data and a preset regulation and control target; and regulating and controlling the operation state of the energy equipment based on the control strategy. According to the method, through dynamic carbon perception and multi-step closed-loop regulation and control, building multi-energy collaborative optimization is achieved, and operation carbon emission is remarkably reduced.

Description

Technical Field

[0001] This application relates to the field of intelligent optimization of building energy system regulation and carbon emission monitoring, specifically to a method and device for intelligent regulation of building energy efficiency based on dynamic carbon sensing. Background Technology

[0002] Building operation energy consumption accounts for approximately 40% of total societal energy consumption, with a comparable share of carbon emissions, making it a key area for achieving dual-carbon goals. Existing building energy management largely relies on static models or manual control, exhibiting significant shortcomings: carbon emission factors use fixed values, failing to adapt to real-time carbon intensity fluctuations from the grid, natural gas, and other energy sources; multi-source sensor data lacks standardized preprocessing, making it susceptible to outlier interference leading to distorted control; control strategies exhibit lag in response and are prone to failure during network outages; simultaneously, it struggles to balance carbon reduction with indoor comfort, lacking a dynamic optimization mechanism that couples human factors with environmental factors. Furthermore, traditional systems lack equipment early warning and robustness verification capabilities, and long-term operation is prone to energy efficiency degradation, failing to meet the low-carbon, refined operation requirements throughout the building's entire lifecycle. Summary of the Invention

[0003] The purpose of this application is to provide a method and device for intelligent control of building energy efficiency based on dynamic carbon sensing, which solves the above-mentioned problems existing in the prior art and can realize real-time accurate calculation and dynamic control of building carbon emissions.

[0004] Firstly, a method for intelligent control of building energy efficiency based on dynamic carbon sensing is provided, which may include: Acquire real-time energy consumption data and environmental status data within the target building; Based on the real-time consumption data and the environmental status data, a dynamic carbon emission factor is determined; Based on the dynamic carbon emission factor and the real-time consumption data, the comprehensive real-time carbon emissions of the target building are determined. Based on the comprehensive real-time carbon emissions, environmental status data, and preset control targets, the control strategy for energy equipment is determined. Based on the control strategy, the operating status of the energy equipment is regulated.

[0005] In one possible implementation, after acquiring real-time consumption data of various energy sources and environmental status data within the target building, the method further includes: Edge preprocessing is performed on the consumption data and environmental data to generate an energy and environment dataset.

[0006] In one possible implementation, the dynamic carbon emission factor is determined based on the real-time consumption data and environmental status data, including: The regional power grid's carbon emission intensity can be obtained in real time through the configured interface; Based on the fluctuations in methane concentration and calorific value detected by the gas composition analyzer, the carbon emission coefficient of the gas is calibrated. Based on the operating power and cooling / heating output of air conditioning and heat pump equipment, the energy efficiency ratio is determined, and the cooling and heating energy consumption is converted into equivalent electricity consumption.

[0007] In one possible implementation, the method further includes: When real-time grid carbon intensity is unavailable, a temporary carbon intensity value is generated based on historical data and weather forecasts using a moving average algorithm.

[0008] In one possible implementation, based on the comprehensive real-time carbon emissions, environmental status data, and preset control targets, a control strategy for energy equipment is determined, including: Construct a state space that includes energy, environment, and time parameters; Based on a reinforcement learning framework, a control strategy is generated with the comprehensive real-time carbon emissions, energy consumption costs, and indoor comfort as optimization objectives. The control strategy includes adjusting the start / stop priority of the equipment, continuously adjusting the speed of the variable frequency equipment, and offsetting the temperature setpoint.

[0009] In one possible implementation, the optimization objective is achieved through a reward function, the expression of which is:

[0010] in, As a reward value, As a baseline carbon emission, This represents actual carbon emissions. As the first weighting coefficient, This is the second weighting coefficient. To set the temperature, For the actual temperature, Δ This represents the maximum permissible temperature deviation.

[0011] In one possible implementation, the weighting coefficient is determined based on the population density within the target building; When the personnel density is lower than the configured quantity threshold, λ takes a first value; when the personnel density is higher than the quantity threshold, λ takes a second value; wherein the second value is greater than the first value.

[0012] Secondly, a building energy efficiency intelligent control device based on dynamic carbon sensing is provided, the device may include: The acquisition unit is used to acquire real-time consumption data of various energy sources and environmental status data within the target building; The determining unit is used to determine the dynamic carbon emission factor based on the real-time consumption data and the environmental status data; Furthermore, based on the dynamic carbon emission factor and the real-time consumption data, the comprehensive real-time carbon emissions of the target building are determined; Furthermore, based on the comprehensive real-time carbon emissions, environmental status data, and preset control targets, a control strategy for energy equipment is determined; The control unit is used to control the operating status of the energy equipment based on the control strategy.

[0013] Thirdly, an electronic device is provided, which includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; When a processor executes a program stored in memory, it implements any of the steps described in the first aspect above.

[0014] Fourthly, a computer-readable storage medium is provided, wherein a computer program is stored therein, and when executed by a processor, the computer program implements the steps of any of the methods described in the first aspect above.

[0015] This application provides a method and apparatus for intelligent building energy efficiency control based on dynamic carbon sensing. The method includes: acquiring real-time consumption data of multiple energy sources and environmental status data within a target building; determining a dynamic carbon emission factor based on the real-time consumption data and the environmental status data; determining the comprehensive real-time carbon emissions of the target building based on the dynamic carbon emission factor and the real-time consumption data; determining a control strategy for energy equipment based on the comprehensive real-time carbon emissions, environmental status data, and a preset control target; and controlling the operating status of the energy equipment based on the control strategy. This method achieves multi-energy synergistic optimization in buildings through dynamic carbon sensing and multi-step closed-loop control, significantly reducing operational carbon emissions. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This application provides an embodiment of a building energy efficiency intelligent control method applied to dynamic carbon sensing; Figure 2 A flowchart illustrating a building energy efficiency intelligent control method based on dynamic carbon sensing, provided for an embodiment of this application; Figure 3A schematic diagram of a building energy efficiency intelligent control device based on dynamic carbon sensing provided in this application embodiment; Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0018] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0019] The intelligent building energy efficiency control method based on dynamic carbon sensing provided in this application embodiment can be applied to... Figure 1 In the system architecture shown, such as Figure 1 As shown, the system may include: a server in the enterprise's backend and terminals for enterprise employees. The server can be a physical server, a server cluster consisting of multiple physical servers, or a distributed system. It can also be a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms. The terminal may be a user equipment (UE) such as a mobile phone, smartphone, laptop, digital radio receiver, personal digital assistant (PDA), tablet computer (PAD), handheld device, in-vehicle device, wearable device, computing device, or other processing device connected to a wireless modem, mobile station (MS), or mobile terminal. The terminal and server can be directly or indirectly connected via wired or wireless communication methods; this application does not limit the connection.

[0020] The terminal is used to acquire real-time consumption data of various energy sources and environmental status data within the target building, and then send this data to the server.

[0021] The server is used to receive real-time consumption data of various energy sources and environmental status data within the target building in order to execute the intelligent building energy efficiency control method based on dynamic carbon sensing provided in this application.

[0022] Building operation energy consumption accounts for approximately 40% of total societal energy consumption, with a comparable share of carbon emissions, making it a key area for achieving dual-carbon goals. Existing building energy management largely relies on static models or manual control, exhibiting significant shortcomings: carbon emission factors use fixed values, failing to adapt to real-time carbon intensity fluctuations from the grid, natural gas, and other energy sources; multi-source sensor data lacks standardized preprocessing, making it susceptible to outlier interference leading to distorted control; control strategies exhibit lag in response and are prone to failure during network outages; simultaneously, it struggles to balance carbon reduction with indoor comfort, lacking a dynamic optimization mechanism that couples human factors with environmental factors. Furthermore, traditional systems lack equipment early warning and robustness verification capabilities, and long-term operation is prone to energy efficiency degradation, failing to meet the low-carbon, refined operation requirements throughout the building's entire lifecycle.

[0023] Therefore, this application provides a building energy efficiency intelligent control method based on dynamic carbon sensing, which solves the above-mentioned problems in the prior art and can realize real-time accurate calculation and dynamic control of building carbon emissions.

[0024] The preferred embodiments of this application are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit this application. Furthermore, the embodiments and features in the embodiments of this application can be combined with each other without conflict.

[0025] Figure 2 This is a flowchart illustrating a method for intelligent control of building energy efficiency based on dynamic carbon sensing, provided as an embodiment of this application. Figure 2 As shown, the method may include: Step S210: Obtain real-time consumption data of various energy sources and environmental status data within the target building.

[0026] Specifically, real-time consumption data includes: deploying smart meters in building power distribution circuits to monitor core parameters such as current, voltage, and power factor in real time; configuring smart sockets at key electrical equipment (such as air conditioning units and lighting systems) to achieve refined collection of equipment-level power consumption data and accurately locate key energy-consuming units; installing high-precision gas flow meters on main gas pipelines, which integrate methane leak detection modules to collect instantaneous gas flow and cumulative consumption in real time, while simultaneously monitoring methane leak risks, thus combining energy consumption metering and safety monitoring; deploying pipeline flow meters in the supply and return water pipelines of the hot and cold water circulation system to monitor the circulation flow of hot and cold water; and deploying distributed temperature and humidity sensors in key indoor and outdoor areas to collect indoor and outdoor temperature difference data in real time, providing basic parameters for calculating heating and cooling energy consumption; and installing ultrasonic water meters in the building water supply network to distinguish between domestic water and recycled water through flow characteristic recognition technology, separately calculating real-time consumption data for the two types of water use, avoiding the lumped statistics of water resource consumption. Carbon dioxide concentration sensors and PM2.5 monitors are deployed in indoor office areas, meeting rooms and other areas where people are active. Carbon dioxide concentration data is directly linked to the carbon emission accounting of the ventilation system, while PM2.5 concentration data is used to help judge indoor air quality and provide a basis for subsequent comfort control.

[0027] In some embodiments, edge preprocessing is performed on consumption data and environmental data to generate an energy and environment dataset.

[0028] Specifically, to eliminate abnormal interference in the raw data and ensure that the data quality meets the needs of subsequent dynamic carbon emission calculation and control decisions, edge preprocessing operations are performed on the collected consumption data and environmental data in the local gateway. The specific process is as follows: Using the local gateway as the execution entity, the normal fluctuation range of various types of data is established based on historical operating data: For energy data such as power consumption, gas flow, and water consumption, as well as environmental data such as temperature, humidity, and carbon dioxide concentration, if the data at a certain collection time exceeds the historical average ± 3 times the standard deviation, it is judged as abnormal data (such as extreme values ​​caused by sensor failure or instantaneous interference), and the abnormal data is automatically removed to avoid distorting the subsequent calculation results.

[0029] Because different sensing devices have different acquisition frequencies (e.g., smart meters acquire data at 1 second / time, while gas flow meters acquire data at 5 seconds / time), timestamp alignment processing is required for multi-source data. This application uses a Time Synchronization Protocol (NTP) to calibrate the acquisition clocks of each device, and performs interpolation or extraction processing on all data with a time granularity of 1 second to ensure that the timestamp error of data in different dimensions is less than 1 second, forming a unified dataset in the time dimension, and providing temporal consistency assurance for the correlation analysis of energy consumption and environmental status.

[0030] After data cleaning and time alignment, the local gateway integrates various data into a standardized energy and environmental dataset. This dataset contains two core types of data: first, energy consumption data, covering real-time consumption values, cumulative consumption, and key operating parameters (such as power factor and circulation flow) of electricity, gas, cooling / heating, and water; second, environmental status data, including indoor and outdoor temperature difference, regional carbon dioxide concentration, PM2.5 concentration, and population density correlation data (obtained based on carbon dioxide concentration inversion). This dataset is uniformly formatted, accurate, and time-synchronized, providing high-quality data input for subsequent dynamic carbon emission factor calculation, real-time carbon emission accounting, and the generation of control strategies.

[0031] In some embodiments, the OPC UA protocol can be used to unify communication between heterogeneous devices, and the MQTT protocol can be used to realize data transmission between edge nodes and the cloud, ensuring data mutual recognition and transmission stability among multiple source devices.

[0032] Step S220: Determine the dynamic carbon emission factor based on real-time consumption data and environmental status data.

[0033] Specifically, step 1 involves obtaining the regional power grid's carbon emission intensity in real time through the configured interface. A communication connection can be established directly with the regional power grid dispatching platform through a preset enterprise-level API interface. The carbon emission intensity of the current power supply path can be obtained in real time at a minute-level sampling frequency. This ensures that the carbon emission factor is dynamically matched with the real-time energy structure of the power grid (such as the proportion of thermal power, wind power, and photovoltaic power), avoiding calculation deviations caused by using fixed carbon emission factors.

[0034] In some embodiments, the method may further include: when real-time grid carbon intensity cannot be obtained, generating a temporary carbon intensity value based on historical data and weather forecasts using a moving average algorithm. Specifically, when network communication is interrupted or the grid dispatch platform data interface is abnormal, making it impossible to obtain real-time electricity carbon emission intensity, a backup data generation mechanism for edge computing nodes is activated: the edge node calls locally cached historical electricity carbon emission intensity data (data from the same period in the past 7 days), combines it with the current day's weather parameters obtained from a third-party weather forecast service (such as sunshine duration, wind force level, and associated clean energy output forecasts), and uses a moving average algorithm to weight the historical data to generate a temporary electricity carbon emission intensity value until the network returns to normal. This backup mechanism ensures the continuity of electricity carbon emission factors and avoids the failure of carbon emission accounting and control strategies due to data interruption.

[0035] Step 2: Based on the methane concentration and calorific value fluctuations detected by the gas composition analyzer, calibrate the gas carbon emission coefficient. This means deploying online composition analyzers at key nodes of the main gas pipeline, working in conjunction with the aforementioned high-precision gas flow meters. The online composition analyzers monitor the methane concentration and calorific value fluctuations in the gas in real time and synchronize the results to the edge computing nodes. The edge nodes, combined with the real-time gas flow data collected by the gas flow meters, use the industry standard gas carbon emission coefficient as a benchmark and dynamically correct based on the detected methane concentration and calorific value fluctuations: when the detected gas calorific value is higher than the standard value, the gas carbon emission coefficient is increased proportionally to the excess calorific value; when the detected methane concentration is lower than the standard value (i.e., the proportion of impurities increases), the carbon emission coefficient is adjusted accordingly based on the methane combustion carbon emission characteristic formula, ensuring that the gas carbon emission coefficient accurately matches the actual gas quality, fundamentally avoiding the underestimation or overestimation of carbon emissions due to changes in the gas source.

[0036] Step 3: Based on the operating power and cooling / heating output of the air conditioning and heat pump equipment, determine the energy efficiency ratio and convert the cooling / heating energy consumption into equivalent electricity consumption. In other words, the carbon emissions from cooling and heating systems (air conditioning, heat pumps, etc.) are indirect carbon emissions and need to be converted into a unified carbon emission measurement benchmark through energy consumption equivalence conversion. The specific implementation process is as follows: Based on the real-time operating power (unit: kW) and cooling / heating output (unit: kWh) of the air conditioning and heat pump equipment collected by the aforementioned multi-source sensor network, the current operating energy efficiency ratio of the equipment is calculated using the formula: Energy Efficiency Ratio (COP) = Cooling / Heating Output / Dynamic Operating Power. This energy efficiency ratio directly reflects the energy utilization efficiency of the cooling and heating system. Using the energy efficiency ratio (COP) as the core conversion criterion, the energy consumed by the cooling and heating system (i.e., the energy consumption corresponding to the operating power) is converted into equivalent power consumption. The specific conversion logic is: equivalent power consumption = cooling and heating output / energy efficiency ratio (COP); where cooling and heating output refers to the cumulative output energy within a specific calculation cycle (e.g., 1 hour).

[0037] The equivalent power consumption obtained by conversion is superimposed with the aforementioned real-time acquired power carbon emission factor to form the indirect carbon emission factor corresponding to the heating and cooling system, thereby realizing the dynamic correlation between the carbon emissions of the heating and cooling system and the power carbon emission factor of the power grid. Meanwhile, the edge computing node monitors the changing trend of the energy efficiency ratio (COP) in real time. When it detects that the COP is lower than the preset threshold (which is set based on 80% of the rated energy efficiency ratio of the equipment), it determines that the energy efficiency of the equipment is deteriorating, automatically triggers a maintenance warning signal, and switches to standby unit operation according to the preset equipment redundancy strategy to ensure the continuity and low carbon emissions of the cooling and heating system.

[0038] Step S230: Based on the dynamic carbon emission factor and the real-time consumption data, determine the comprehensive real-time carbon emissions of the target building.

[0039] Specifically, the standardized energy and environment dataset generated after preprocessing is obtained, including real-time electricity consumption, real-time gas consumption, and equivalent electricity consumption after conversion of the heating and cooling system; the output results from the dynamic carbon emission factor determination step are obtained, including minute-level updated electricity carbon emission intensity and gas carbon emission coefficient calibrated by gas composition.

[0040] An integrated model combining direct calculation and indirect conversion is adopted to avoid computational delays and errors caused by complex intermediate derivations, ensuring the real-time accuracy of carbon emissions. The core calculation formula is as follows: Total real-time carbon emissions = ∑(electricity consumption value × electricity carbon emission intensity) + (real-time gas consumption value × calibrated gas carbon emission coefficient). In some embodiments, firstly, direct carbon emissions from electricity consumption encompass the carbon emissions corresponding to the real-time electricity consumption of conventional electrical equipment within the building (such as lighting, office equipment, and air conditioning units), calculated as follows: Direct carbon emissions from electricity = Real-time consumption of conventional electricity × Carbon emission factor of grid electricity during the same period; The real-time power consumption value is taken from standardized data collected by smart meters and smart sockets. The carbon emission factor of the power grid is a dynamic value updated every minute. When the network is interrupted, a temporary carbon intensity value generated by the moving average algorithm is used to replace it to ensure the continuity of calculation.

[0041] Furthermore, direct carbon emissions from gas consumption are calculated based on dynamically calibrated gas carbon emission coefficients and standardized gas consumption data, using the following method: Direct carbon emissions from natural gas = Real-time consumption of natural gas × Calibrated carbon emission coefficient of natural gas; The calibrated gas carbon emission coefficient is based on the industry standard gas carbon emission benchmark coefficient (2.2), and dynamically corrected by combining the methane concentration and calorific value fluctuation detected by the online component analyzer: when the gas calorific value is higher than the standard value, the coefficient is increased proportionally; when the methane concentration is lower than the standard value, the coefficient is corrected based on the methane combustion carbon emission characteristic formula to ensure that the gas carbon emission calculation is accurately matched with the actual gas source quality.

[0042] Furthermore, carbon emissions from heating and cooling systems (air conditioning, heat pumps, etc.) are indirect carbon emissions and need to be calculated by converting them into equivalent electricity consumption using energy efficiency ratios. The calculation method is as follows: First, based on the operating power and real-time output of the cooling and heating systems in the standardized energy and environmental dataset, the formula is used: Energy Efficiency Ratio (COP) = Real-time Cooling / Heating Output / Operating Power Then, the energy consumption of the heating and cooling system is converted into equivalent electricity consumption, that is: Equivalent power consumption = Real-time output of cooling and heating / Energy efficiency ratio (COP); Finally, calculate the indirect carbon emissions: Indirect carbon emissions from the heating and cooling system = equivalent electricity consumption × carbon emission factor of the grid electricity during the same period.

[0043] The total real-time carbon emissions of the target building are obtained by adding together the direct carbon emissions from electricity consumption, the direct carbon emissions from gas consumption, and the indirect carbon emissions from heating and cooling systems. The calculation formula is as follows: Total real-time carbon emissions = direct carbon emissions from electricity + direct carbon emissions from gas + indirect carbon emissions from heating and cooling systems; The calculation results are updated synchronously on a minute-by-minute basis and stored in real time to local edge nodes and cloud servers, providing accurate carbon emission quantification basis for subsequent state space construction, multi-objective reward calculation and regulatory action decision-making.

[0044] The comprehensive real-time carbon emission calculation model constructed in this way has significant technical advantages: Firstly, relying on minute-level updated dynamic carbon emission factors and real-time consumption data, it achieves synchronous calculation of carbon emissions, effectively avoiding the lag caused by fixed-period calculations and fully meeting the real-time requirements of dynamic regulation; secondly, through real-time calibration of dynamic carbon emission factors and equivalent conversion logic of heating and cooling systems, it solves the problem that traditional fixed carbon emission factors cannot adapt to fluctuations in energy characteristics, ensuring the accuracy of carbon emission calculation under different gas source qualities and different grid energy structures; at the same time, it adopts linear superposition calculation logic, abandoning complex intermediate derivation processes, significantly reducing computational complexity while ensuring calculation accuracy, and can be executed quickly at the local edge gateway without occupying additional computing resources, ensuring that the overall system response speed is not affected; in addition, the model supports data input from various sensor devices accessed by industrial protocols such as Modbus and BACnet, and can be directly adapted to energy metering scenarios of different types of buildings without replacing existing equipment, significantly reducing transformation costs and adaptation thresholds.

[0045] Step S240: Based on comprehensive real-time carbon emissions, environmental status data and preset control targets, determine the control strategy for energy equipment.

[0046] Specifically, step 1 involves constructing a state space containing energy, environmental, and temporal parameters. Energy parameters directly reflect energy consumption and carbon emission status, providing a basis for quantifying carbon reduction targets. These parameters include: comprehensive real-time carbon emissions, real-time power of each energy subsystem, cumulative energy consumption of each energy subsystem, and current dynamic carbon emission factors. Environmental parameters provide direct reference for indoor comfort control and support the implementation of human-factor coupling mechanisms. These parameters include: indoor-outdoor temperature difference, regional population density, indoor carbon dioxide concentration, and indoor PM2.5 concentration. Temporal parameters are used to adapt to energy price fluctuations and building energy consumption patterns, including: electricity price time period labels and weekday / holiday identifiers. All parameters in the state space are updated at a frequency of 1 second, dynamically matching the minute-level calculation results of comprehensive real-time carbon emissions to ensure that state perception can reflect changes in building operating status in real time, providing accurate input for subsequent decision-making. Furthermore, combining thermal imaging technology with carbon dioxide concentration data to invert regional population density improves detection accuracy.

[0047] Step 2: Based on a reinforcement learning framework, a control strategy is generated with the optimization objectives of comprehensive real-time carbon emissions, energy costs, and indoor comfort. This control strategy includes adjusting equipment start-stop priorities, continuously regulating the speed of variable frequency drives, and offsetting temperature setpoints. This process can be understood as follows: In the reinforcement learning framework, the agent is the energy equipment control system, the environment is the real-time operating state of the target building (i.e., the aforementioned state space), the action is the control operation of the energy equipment, and the reward value is the quantitative feedback of the multi-objective optimization effect. Through continuous iterative training, the agent gradually learns the optimal control strategy under different states. The agent collects state space data in real time, outputs control actions, and applies them to the building's energy system. After the system's operating state changes, a feedback reward value is calculated through a reward function. The agent adjusts its decision logic based on the reward value, forming a perception, decision-making, execution, and feedback process to ensure that the control strategy continuously adapts to changes in the building's operating state.

[0048] Furthermore, the optimization objective is achieved through a reward function, the expression of which is:

[0049] in, As a reward value, As a baseline carbon emission, This represents actual carbon emissions. As the first weighting coefficient, This is the second weighting coefficient. To set the temperature, For the actual temperature, Δ This represents the maximum permissible temperature deviation.

[0050] Furthermore, the benchmark carbon emissions are calculated as the average carbon emissions based on the target building's historical operating data for the same period over the past 30 days, serving as a benchmark for comparing carbon reduction effectiveness. The comprehensive real-time carbon emissions, namely the total carbon emissions calculated by the multi-energy integrated system in the aforementioned steps, directly reflect the effectiveness of carbon emission reduction and generate positive incentives when the emissions are lower than the benchmark value. Temperature deviation is the absolute value between the actual indoor temperature and the preset comfort temperature (26℃ in summer and 20℃ in winter). When it exceeds ±1.5℃, the bonus value is deducted proportionally to the deviation range to ensure the bottom line of comfort. Energy cost deviation is the difference between the actual energy cost in the current period and the best energy cost in the same period in history. When it is higher than the best value, a penalty is imposed to guide the strategy to reduce energy consumption during peak periods with high electricity prices. Subsequently, based on the decision output of the reinforcement learning framework, and combined with the building operation scenario and equipment safety constraints, three types of core control strategies (control actions) are generated: I. Equipment start-up and shutdown priority adjustment strategy.

[0051] Equipment start-up and shutdown priorities are sorted by carbon emission intensity, energy consumption necessity, and comfort impact, dynamically adapting to different operating scenarios: In high-carbon emission scenarios (comprehensive real-time carbon emissions > baseline carbon emissions × 110% or grid carbon emission factor ≥ baseline value 120%): prioritize shutting down redundant loads such as landscape lighting and non-essential office equipment, and switch to backup energy storage system power supply (if configured) to reduce high-carbon energy consumption; Low-carbon emission scenario (comprehensive real-time carbon emissions < baseline carbon emissions × 90% or grid carbon emission factor ≤ baseline value 80%): pre-start cold / heat storage equipment and standby units to store low-carbon energy and prepare for peak shaving during subsequent high-carbon emission periods; Emergency Scenario: When the indoor carbon dioxide concentration is >1200ppm, the fresh air system will be forcibly started, with priority over carbon emission reduction and cost control targets; when the equipment energy efficiency is below the threshold (air conditioner COP < 80% of rated value), the standby unit will be automatically switched and a maintenance warning will be triggered.

[0052] 2. Continuous speed adjustment of variable frequency equipment.

[0053] Variable frequency water pump: The speed adjustment range is 50%-100%. It dynamically adapts to the hot and cold water circulation flow and the indoor and outdoor temperature difference. Under the premise of meeting the energy supply demand, it prioritizes operation in the optimal energy efficiency range (70%-80% speed). Fresh air system fan: The speed is adjusted according to the indoor carbon dioxide concentration. It operates at low speed when the carbon dioxide concentration is 800-1000ppm and at medium speed when it is 1000-1200ppm, so as to ensure comfort while reducing fan energy consumption. Safety constraints: Pump speed change rate ≤ 5% / minute, to avoid sudden speed changes that could cause equipment overload damage.

[0054] 3. Temperature setpoint offset.

[0055] High carbon emission and low density scenarios: Increase the air conditioning setting temperature by 1 degree Celsius in summer (to 27 degrees Celsius) and decrease the setting temperature by 1 degree Celsius in winter (to 19 degrees Celsius) to maximize carbon emission reduction within an acceptable comfort range; Low carbon emissions and high-density scenarios: In summer, lower the air conditioner setting temperature by 1 degree Celsius (to 25 degrees Celsius), and in winter, raise the setting temperature by 1 degree Celsius (to 21 degrees Celsius) to prioritize indoor comfort; Constraint control: The temperature setpoint deviation does not exceed ±1 degree Celsius to avoid excessive decrease in comfort, and the minimum start-stop interval of the compressor is ≥15 minutes to prevent frequent start-stop damage to the equipment.

[0056] This approach achieves precise perception through the construction of a full-dimensional state space, realizes dynamic collaboration of multiple objectives by relying on a reinforcement learning framework, and ensures the feasibility of regulation by combining scenario-based control actions. It effectively solves the technical defects of traditional strategies such as rigidity, delayed response, and conflict of multiple objectives, and provides core support for the refined and low-carbon operation of building energy systems.

[0057] Step S250: Based on the control strategy, regulate the operating status of the energy equipment.

[0058] Specifically, it adopts an edge-based real-time response and cloud-based iterative optimization model: Edge nodes receive optimal control parameters from the cloud and execute millisecond-level control actions based on real-time data from a standardized energy and environmental dataset. In the event of a network outage, they autonomously operate for 72 hours using locally cached strategies and data, ensuring uninterrupted control. Every morning at midnight, the cloud server trains a reinforcement learning model using the previous day's data, generates a library of optimal control strategies for the following day, and distributes it to the edge nodes for global optimization.

[0059] Subsequently, the operating status of energy equipment is regulated according to the three types of core control strategies generated.

[0060] Next, edge nodes collect real-time equipment operation data and environmental feedback data, calculate comprehensive real-time carbon emissions and comprehensive reward values, and dynamically fine-tune control parameters. Edge nodes upload feedback data to the cloud daily to support strategy optimization the following day; every quarter, extreme scenarios are injected through digital twin models to verify the robustness of the strategy and update the rule base.

[0061] To prevent others from bypassing the core technical solution of this application to achieve the same inventive purpose, this application also provides the following alternative solutions, each of which can achieve the goal of dynamic carbon sensing and intelligent control of building energy efficiency, as follows: 1. Alternative solutions for data collection.

[0062] Remote sensing carbon emission inversion replaces direct metering: Infrared spectrometers are used to monitor the gas composition of building exhaust outlets, and carbon emission inversion algorithms are used to estimate the real-time carbon emissions of the target building. There is no need to deploy direct metering instruments such as smart meters and gas flow meters, simplifying the hardware deployment process. Blockchain-based evidence storage replaces API interfaces: Building energy consumption data and environmental status data are uploaded to the blockchain network, and smart contracts are used to automatically synchronize the carbon emission factors of the regional power grid. This replaces the traditional enterprise-level API interface interface, enhances the tamper resistance and reliability of data transmission, and avoids data interruption caused by interface failure.

[0063] 2. Alternative solutions to regulatory strategies.

[0064] Establish a high-precision digital twin model of building thermodynamics to simulate changes in building energy consumption and carbon emissions under different carbon emission scenarios and weather conditions 24 hours in advance, generate a multi-scenario optimal control strategy library, and directly call the corresponding scenario strategy during real-time control without the need for online training of reinforcement learning models, thus reducing the computational pressure on edge nodes; Swarm intelligence optimization replaces centralized decision-making: Distributed controllers are deployed at the terminal devices such as air conditioners, water pumps, and fans. Each controller acts as an independent decision-making unit and achieves collaborative optimization of global control objectives through ant colony algorithms, replacing the centralized decision-making architecture of edge and cloud collaboration and improving the distributed response capability of control.

[0065] 3. Alternative solutions for carbon emission calculation.

[0066] Carbon flow tagging and tracking replaces grid average carbon intensity calculation: a blockchain traceability tag is attached to each kilowatt-hour of electricity delivered to the grid to accurately record the source of electricity (such as thermal power, wind power, and photovoltaic) and the corresponding carbon emission intensity. Based on the tag information, the accurate carbon emission of building electricity consumption is calculated, replacing the traditional grid average carbon intensity calculation method and improving the accuracy of carbon emission accounting. Equipment fingerprint database replaces direct metering: A database of carbon emission characteristics of energy-consuming equipment of different brands and models is established. Non-intrusive load monitoring (NILM) technology is used to identify the type and operating status of equipment operating in the building. Real-time carbon emissions are calculated by combining the carbon emission characteristic data in the equipment fingerprint database. There is no need to configure a separate metering instrument for each device, reducing deployment costs.

[0067] This application provides a building energy efficiency intelligent control method based on dynamic carbon sensing. The method includes: acquiring real-time consumption data of multiple energy sources and environmental status data within a target building; determining a dynamic carbon emission factor based on the real-time consumption data and the environmental status data; determining the comprehensive real-time carbon emissions of the target building based on the dynamic carbon emission factor and the real-time consumption data; determining a control strategy for energy equipment based on the comprehensive real-time carbon emissions, environmental status data, and a preset control target; and regulating the operating status of the energy equipment based on the control strategy. This method achieves multi-energy synergistic optimization in buildings through dynamic carbon sensing and multi-step closed-loop control, significantly reducing operational carbon emissions.

[0068] Corresponding to the above method, embodiments of this application also provide a building energy efficiency intelligent control device based on dynamic carbon sensing, such as... Figure 3 As shown, the device includes: Acquisition unit 310 is used to acquire real-time consumption data of various energy sources and environmental status data within the target building; The determining unit 320 is used to determine the dynamic carbon emission factor based on the real-time consumption data and the environmental status data; Furthermore, based on the dynamic carbon emission factor and the real-time consumption data, the comprehensive real-time carbon emissions of the target building are determined; Furthermore, based on the comprehensive real-time carbon emissions, environmental status data, and preset control targets, a control strategy for energy equipment is determined; The control unit 330 is used to control the operating status of the energy equipment based on the control strategy.

[0069] The functions of each unit in the intelligent building energy efficiency control device based on dynamic carbon sensing provided in the above embodiments of this application can be realized through the above methods and steps. Therefore, the specific working process and beneficial effects of each unit in the intelligent building energy efficiency control device based on dynamic carbon sensing provided in the embodiments of this application will not be repeated here.

[0070] This application also provides an electronic device, such as... Figure 4 As shown, it includes a processor 410, a communication interface 420, a memory 430, and a communication bus 440, wherein the processor 410, the communication interface 420, and the memory 430 communicate with each other through the communication bus 440.

[0071] Memory 430 is used to store computer programs; When the processor 410 executes the program stored in the memory 430, it performs the following steps: Acquire real-time energy consumption data and environmental status data within the target building; Based on the real-time consumption data and the environmental status data, a dynamic carbon emission factor is determined; Based on the dynamic carbon emission factor and the real-time consumption data, the comprehensive real-time carbon emissions of the target building are determined. Based on the comprehensive real-time carbon emissions, environmental status data, and preset control targets, the control strategy for energy equipment is determined. Based on the control strategy, the operating status of the energy equipment is regulated.

[0072] The communication bus mentioned above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not mean that there is only one bus or one type of bus.

[0073] The communication interface is used for communication between the aforementioned electronic devices and other devices.

[0074] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0075] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0076] The implementation methods and beneficial effects of the various components of the electronic device in the above embodiments for solving the problem can be found in [reference needed]. Figure 2 The steps in the illustrated embodiments are used to implement the electronic device. Therefore, the specific working process and beneficial effects of the electronic device provided in this application will not be repeated here.

[0077] In another embodiment provided in this application, a computer-readable storage medium is also provided, which stores instructions that, when executed on a computer, cause the computer to perform any of the above embodiments of a building energy efficiency intelligent control method based on dynamic carbon sensing.

[0078] In another embodiment provided in this application, a computer program product containing instructions is also provided, which, when run on a computer, causes the computer to execute any of the above embodiments of a building energy efficiency intelligent control method based on dynamic carbon sensing.

[0079] Those skilled in the art will understand that the embodiments in this application can be provided as methods, systems, or computer program products. Therefore, the embodiments in this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the embodiments in this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0080] This application describes embodiments of methods, apparatus (systems), and computer program products according to embodiments of this application with reference to flowchart illustrations and / or block diagrams. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0081] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0082] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0083] Unless otherwise defined, the technical or scientific terms used in this application shall have the ordinary meaning understood by one of ordinary skill in the art to which this invention pertains. The terms "first," "second," and similar terms used in this application do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed following the word and their equivalents, without excluding other elements or objects. Terms such as "connected," "coupled," or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are used only to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0084] Although preferred embodiments have been described in this application, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the embodiments in this application are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments in this application.

[0085] Obviously, those skilled in the art can make various modifications and variations to the embodiments of this application without departing from the spirit and scope of the embodiments of this application. Therefore, if these modifications and variations to the embodiments of this application fall within the scope of the embodiments of this application and their equivalents, then these modifications and variations are also intended to be included in the embodiments of this application.

Claims

1. A method for intelligent control of building energy efficiency based on dynamic carbon sensing, characterized in that, The method includes: Acquire real-time energy consumption data and environmental status data within the target building; Based on the real-time consumption data and the environmental status data, a dynamic carbon emission factor is determined; Based on the dynamic carbon emission factor and the real-time consumption data, the comprehensive real-time carbon emissions of the target building are determined. Based on the comprehensive real-time carbon emissions, environmental status data, and preset control targets, the control strategy for energy equipment is determined. Based on the control strategy, the operating status of the energy equipment is regulated.

2. The method as described in claim 1, characterized in that, After acquiring real-time consumption data of various energy sources and environmental status data within the target building, the method further includes: Edge preprocessing is performed on the consumption data and environmental data to generate an energy and environment dataset.

3. The method as described in claim 1, characterized in that, Based on the aforementioned real-time consumption data and environmental status data, a dynamic carbon emission factor is determined, including: The regional power grid's carbon emission intensity can be obtained in real time through the configured interface; Based on the fluctuations in methane concentration and calorific value detected by the gas composition analyzer, the carbon emission coefficient of the gas is calibrated. Based on the operating power and cooling / heating output of air conditioning and heat pump equipment, the energy efficiency ratio is determined, and the cooling and heating energy consumption is converted into equivalent electricity consumption.

4. The method as described in claim 3, characterized in that, The method further includes: When real-time grid carbon intensity is unavailable, a temporary carbon intensity value is generated based on historical data and weather forecasts using a moving average algorithm.

5. The method as described in claim 1, characterized in that, Based on the comprehensive real-time carbon emissions, environmental status data, and preset control targets, a control strategy for energy equipment is determined, including: Construct a state space that includes energy, environment, and time parameters; Based on a reinforcement learning framework, a control strategy is generated with the comprehensive real-time carbon emissions, energy consumption costs, and indoor comfort as optimization objectives. The control strategy includes adjusting the start / stop priority of the equipment, continuously adjusting the speed of the variable frequency equipment, and offsetting the temperature setpoint.

6. The method as described in claim 5, characterized in that, The optimization objective is achieved through a reward function, the expression of which is: in, As a reward value, As a baseline carbon emission, This represents actual carbon emissions. As the first weighting coefficient, This is the second weighting coefficient. To set the temperature, For the actual temperature, Δ This represents the maximum permissible temperature deviation.

7. The method as described in claim 6, characterized in that, The weighting coefficient is determined based on the population density within the target building; When the personnel density is lower than the configured quantity threshold, λ takes a first value; when the personnel density is higher than the quantity threshold, λ takes a second value; wherein the second value is greater than the first value.

8. A building energy efficiency intelligent control device based on dynamic carbon sensing, characterized in that, The device includes: The acquisition unit is used to acquire real-time consumption data of various energy sources and environmental status data within the target building; The determining unit is used to determine the dynamic carbon emission factor based on the real-time consumption data and the environmental status data; Furthermore, based on the dynamic carbon emission factor and the real-time consumption data, the comprehensive real-time carbon emissions of the target building are determined; Furthermore, based on the comprehensive real-time carbon emissions, environmental status data, and preset control targets, a control strategy for energy equipment is determined; The control unit is used to control the operating status of the energy equipment based on the control strategy.

9. An electronic device, characterized in that, The electronic device includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, when executing a program stored in memory, implements the steps of the method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the method described in any one of claims 1-7.

Images