Carbon emission intelligent optimization method and system based on monitoring management platform

Abstract

The invention relates to the technical field of carbon emission management, in particular to a carbon emission intelligent optimization method and system based on a monitoring management platform, and the method comprises the steps: training a collaborative energy consumption prediction model through multi-source data fusion, remarkably improving the prediction precision under a multi-equipment linkage scene, and further, combining with carbon emission factors and external environment parameters under different emission sources to obtain an energy consumption prediction model; and a dynamic correction mechanism is adopted to calibrate a carbon emission predicted value, so that an estimated result is closer to reality, and finally, based on a rehearsal regulation and control action library and a constructed fitness function, an optimal equipment regulation and control combination is automatically generated, and closed-loop automatic management of carbon emission optimization is realized. The technical problem that a traditional carbon emission optimization method depends on a fixed strategy and cannot dynamically respond to the equipment state and the external environment change can be solved, the accuracy of carbon emission prediction is improved, the automation degree of equipment regulation and control is improved, rapid response from carbon emission early warning to optimization execution is achieved, and the economic benefit is improved. And an effective technical means is provided for refined carbon management in multiple scenes of the project.

Description

Technical Field

[0001] This invention relates to the field of carbon emission management technology, specifically to a method and system for intelligent optimization of carbon emissions in industrial or building scenarios based on Internet of Things monitoring and machine learning models, and more particularly to a method and system for intelligent optimization of carbon emissions based on a monitoring and management platform. Background Technology

[0002] With the acceleration of industrialization and urbanization, energy consumption is constantly increasing, leading to a continuous rise in greenhouse gas emissions such as carbon dioxide, which has a serious impact on the global climate system. Reducing carbon emissions not only helps to mitigate climate change, but also reduces energy consumption costs, improves energy efficiency, and promotes sustainable development. Therefore, achieving intelligent optimization of carbon emissions is of great significance for promoting green and low-carbon transformation.

[0003] Existing technologies, such as CN202411039523.7, mainly achieve this by manually setting fixed energy-saving strategies, such as periodically shutting down equipment or adjusting equipment operating parameters. Although this method can reduce carbon emissions to some extent, it cannot dynamically adjust and optimize strategies based on real-time equipment operating status and external environmental factors, resulting in insufficiently accurate optimization effects. Furthermore, this method lacks accurate prediction of equipment energy consumption and carbon emissions, making it difficult to achieve refined carbon emission management. Summary of the Invention

[0004] This invention provides a method and system for intelligent carbon emission optimization based on a monitoring and management platform. Its main purpose is to improve the accuracy of carbon emission prediction and enhance the automation of equipment control during the carbon emission optimization process.

[0005] To achieve the above objectives, the present invention provides a method for intelligent optimization of carbon emissions based on a monitoring and management platform, comprising:

[0006] Receive carbon emission optimization instructions, determine the monitoring area based on the carbon emission optimization instructions, and obtain the set of equipment to be optimized in the monitoring area, wherein the set of equipment to be optimized includes multiple equipment to be optimized;

[0007] Based on a pre-built IoT gateway, a preset energy consumption polling command is sent to the set of devices to be optimized to obtain the target set of devices. The target set of devices includes multiple target devices, and the IoT gateway includes a protocol adaptation layer.

[0008] The target devices are extracted sequentially from the target device set, and energy consumption data is collected from the target devices to obtain the device energy consumption data.

[0009] Energy consumption is predicted based on equipment energy consumption data and a pre-built energy consumption prediction model to obtain the predicted equipment energy consumption.

[0010] The carbon emissions of the predicted equipment are calculated based on the preset power grid carbon emission factor and the predicted equipment energy consumption. The predicted equipment carbon emissions are then summarized to obtain the predicted equipment carbon emission set.

[0011] External factors are applied to the predicted carbon emissions set to obtain the cumulative carbon emissions.

[0012] Obtain a pre-simulated control action library, which includes multiple pre-simulated control data, including: pre-simulated control actions and the carbon emissions of the control actions;

[0013] A fitness function is constructed based on the pre-simulated control action library, cumulative carbon emissions, and preset baseline carbon emissions. Carbon emission optimization is then performed based on the fitness function to obtain the target optimized action set.

[0014] The target optimization action group is transmitted to the pre-built data management platform to complete the intelligent optimization of carbon emissions based on the monitoring and management platform.

[0015] Optionally, the step of collecting energy consumption data from the target device to obtain device energy consumption data includes:

[0016] Confirm the initial acquisition time and record it as the current acquisition time;

[0017] Data is collected from the target device based on the current acquisition time to obtain the current device data, which includes: current current, current voltage, current power, and current temperature;

[0018] Calculate the target acquisition time based on the current acquisition time and the preset acquisition interval, and calculate the acquisition duration between the initial acquisition time and the target acquisition time;

[0019] The target acquisition time is taken as the current acquisition time, and the step of acquiring data from the target device based on the current acquisition time is returned until the acquisition time is not less than the preset management cycle.

[0020] Summarize the current device data to obtain the current device dataset;

[0021] The current energy consumption is calculated based on the current device dataset, and the calculation method for the current energy consumption is as follows:

[0022] ,

[0023] in, Indicates current energy consumption. This indicates the number of data points for the current device in the current device dataset. Represents the first in the current device dataset The current power corresponding to the current device data. Indicates the data collection interval;

[0024] Based on the initial acquisition time, the previous operating state vector is identified. The previous operating state vector and the current energy consumption are added to the current device dataset to obtain device energy consumption data, which is used for energy consumption prediction.

[0025] Optionally, before performing energy consumption prediction based on equipment energy consumption data and a pre-built energy consumption prediction model to obtain the predicted equipment energy consumption, the method further includes:

[0026] Identify the target device's data repository;

[0027] Query historical energy consumption data of the target device based on the data repository;

[0028] The monitoring area is functionally divided into multiple functional zones, and the target area where the target device is located is identified among these multiple functional zones.

[0029] Identify the historical management cycle corresponding to the historical energy consumption data, and calculate the predicted management cycle based on the historical management cycle and the preset prediction interval;

[0030] Based on the target area, an operation status vector is constructed, and the operation status vector is supplemented to the historical energy consumption data to obtain multi-device fusion data;

[0031] Based on the predictive management cycle, query the actual device energy consumption in the data repository, and use the actual device energy consumption to label the multi-device fusion data to obtain labeled device data.

[0032] The pre-constructed original prediction model is trained using labeled equipment data to obtain an energy consumption prediction model, wherein the energy consumption prediction model is used to predict equipment energy consumption and calculate the predicted equipment carbon emissions.

[0033] Optionally, constructing the running state vector based on the target region includes:

[0034] Obtain the set of devices in the same area within the target area, wherein the set of devices in the same area includes multiple devices in the same area, and the devices in the same area are in the same functional area as the target device;

[0035] Based on the historical management cycle, the operating status of the equipment set in the same area is identified to obtain the operating status identifier set. The operating status identifier set includes multiple operating status identifiers, where the operating status identifier is a value of 0 or a value of 1. A value of 1 indicates that the equipment in the same area is in the operating state at the end of the historical management cycle, and a value of 0 indicates that the equipment in the same area is in the off state at the end of the historical management cycle.

[0036] Construct a running status vector based on the running status identifier set.

[0037] Optionally, the step of correcting the predicted carbon emissions set by external factors to obtain the cumulative carbon emissions includes:

[0038] Extract the functional areas sequentially from multiple functional areas;

[0039] Based on the management cycle, external factors are statistically analyzed for functional areas to obtain a set of external impact parameters, which include: personnel density, outdoor temperature, indoor temperature, and solar irradiance.

[0040] The set of external influence parameters is normalized to obtain the set of target influence parameters.

[0041] A carbon emission correction model is constructed, and the target impact parameter set is input into the carbon emission correction model to obtain the correction ratio;

[0042] Based on the functional area, the carbon emission set of the predicted equipment carbon emission set is identified, and the total regional emission is obtained by summing the regional carbon emission sets.

[0043] The total regional emissions are corrected using the correction ratio to obtain the corrected carbon emissions;

[0044] The corrected carbon emissions are summarized to obtain the corrected carbon emission set. The corrected carbon emission set is then summed to obtain the cumulative carbon emissions.

[0045] Optionally, the construction of the carbon emission correction model includes:

[0046] Collect the historical predicted emissions set of the functional area, wherein the historical predicted emissions set includes multiple historical predicted emissions, and each historical predicted emissions corresponds to a different management cycle;

[0047] Historical predicted emissions are extracted sequentially from the historical predicted emissions set;

[0048] Obtain the emission management cycle of historical predicted emissions, and statistically analyze the historical external parameter set of the functional area within the emission management cycle. The historical external parameter set includes: historical population density, historical outdoor temperature, historical outdoor temperature and historical solar irradiance.

[0049] A historical external parameter vector is constructed based on the historical external parameter set, and the actual carbon emissions are obtained according to the emission management cycle.

[0050] The carbon emission ratio is calculated based on actual carbon emissions and historical predicted emissions.

[0051] By summarizing the historical external parameter vectors and carbon emission ratios, we obtain the historical external parameter vector set and carbon emission ratio set.

[0052] The training extrinsic parameter vector set is obtained by clustering and filtering based on the historical extrinsic parameter vector set.

[0053] Identify the training proportion set based on the training extrinsic parameter vector set in the carbon emission proportion set;

[0054] The training ratio set is paired with the training extrinsic parameter vector set to obtain the carbon emission training dataset. The carbon emission training dataset includes multiple carbon emission training data, and each carbon emission training data contains a training ratio and its corresponding training extrinsic parameter vector.

[0055] A pre-built neural network is trained using a carbon emission training dataset to obtain a carbon emission correction model.

[0056] Optionally, the step of clustering and filtering based on the historical extrinsic parameter vector set to obtain the training extrinsic parameter vector set includes:

[0057] Clustering the historical extrinsic parameter vector set yields multiple clustered extrinsic parameter vector sets;

[0058] Extract cluster extrinsic parameter vector sets sequentially from multiple cluster extrinsic parameter vector sets;

[0059] The number of cluster vectors in the cluster extrinsic parameter vector set is counted. If the number of cluster vectors is greater than the preset extreme number, the cluster extrinsic parameter vector set is recorded as the effective parameter vector set.

[0060] The effective parameter vector set is summarized to obtain the training extrinsic parameter vector set.

[0061] Optionally, the step of constructing a fitness function based on the pre-simulated control action library, cumulative carbon emissions, and a preset baseline carbon emissions includes:

[0062] Set the control action vector, which consists of multiple execution parameters;

[0063] The number of control actions in the statistical control action vector is the same as the number of pre-simulated control data in the pre-simulated control action library;

[0064] A fitness function is constructed based on the pre-simulated control action library, the number of control actions, the control action vector, the cumulative carbon emissions, and the baseline carbon emissions.

[0065] Optionally, the fitness function is expressed as:

[0066] ,

[0067] in, Represents the fitness function. This represents the preset mapping function. Represents the control action vector, This indicates the preset carbon emission weight. This indicates cumulative carbon emissions. Indicates baseline carbon emissions. Indicates the number of regulatory actions. The first element in the control action vector represents the... One execution parameter, The first element in the control action vector represents the... Each execution parameter corresponds to a carbon emission amount of the control action in the pre-simulated control action library. This indicates the preset weight of the number of adjustments.

[0068] To achieve the above objectives, the present invention also provides a carbon emission intelligent optimization system based on a monitoring and management platform, comprising:

[0069] The target device determination module is used to receive carbon emission optimization instructions, determine the monitoring area based on the carbon emission optimization instructions, and obtain the set of devices to be optimized in the monitoring area. The set of devices to be optimized includes multiple devices to be optimized. Based on a pre-built IoT gateway, a preset energy consumption polling instruction is sent to the set of devices to be optimized to obtain the target device set. The target device set includes multiple target devices. The IoT gateway includes a protocol adaptation layer.

[0070] The equipment energy consumption prediction module is used to sequentially extract target devices from the target device set, collect energy consumption data of the target devices, obtain equipment energy consumption data, and perform energy consumption prediction based on the equipment energy consumption data and the pre-built energy consumption prediction model to obtain the predicted equipment energy consumption.

[0071] The carbon emission prediction module is used to calculate the carbon emission of the predicted equipment based on the preset power grid carbon emission factor and the energy consumption of the predicted equipment, summarize the carbon emission of the predicted equipment to obtain the carbon emission set of the predicted equipment, and perform external factor correction on the carbon emission set of the predicted equipment to obtain the cumulative carbon emission.

[0072] The control action transmission module is used to acquire the pre-simulated control action library, which includes multiple pre-simulated control data, including pre-simulated control actions and carbon emissions of control actions. Based on the pre-simulated control action library, cumulative carbon emissions, and preset baseline carbon emissions, a fitness function is constructed. Carbon emission optimization is performed based on the fitness function to obtain the target optimization action group, and the target optimization action group is transmitted to the pre-built data management platform.

[0073] To address the above problems, the present invention also provides an electronic device, the electronic device comprising:

[0074] Memory, storing at least one instruction;

[0075] The processor executes the instructions stored in the memory to implement the aforementioned intelligent carbon emission optimization method based on the monitoring and management platform.

[0076] To address the aforementioned issues, the present invention also provides a computer-readable storage medium storing at least one instruction, which is executed by a processor in an electronic device to implement the aforementioned intelligent carbon emission optimization method based on a monitoring and management platform.

[0077] To address the problems described in the background section, this invention first predicts energy consumption based on equipment energy consumption data and an energy consumption prediction model. This yields predicted equipment energy consumption. This step trains a dedicated energy consumption prediction model using historical multi-device fusion data, incorporating the high-dimensional variable of regional equipment start-up and shutdown combinations into the input. This transforms the model output from an isolated extrapolation of a single device into a group energy consumption prediction that anticipates the synergistic effects of equipment clusters, significantly reducing the bias of traditional sequence predictions in equipment linkage scenarios. Next, external factors are applied to the predicted equipment carbon emission set to obtain cumulative carbon emissions. This step introduces external parameters such as personnel density and solar irradiance to dynamically correct the predicted emissions at the regional level, transforming meteorological and human-caused disturbances from error terms into modelable variables. This allows the cumulative carbon emissions to closely approximate real-world operating scenarios, avoiding significant deviations that occur with traditional methods under conditions of high personnel mobility. Furthermore, this solution also incorporates pre-emptive control. The invention includes an action library, specifically a pre-simulated control action library comprising multiple pre-simulated control data sets. These pre-simulated control actions and their corresponding carbon emission values ​​pre-quantify the absolute carbon reduction of each operation, transforming control commands from fuzzy experience into quantifiable carbon emission values. This allows subsequent algorithms to directly combine and assemble these values ​​at the digital level, eliminating the need for online trial and error or on-site calibration, significantly shortening the optimization loop time. Finally, a fitness function is constructed based on the pre-simulated control action library, cumulative carbon emissions, and a preset baseline carbon emissions. Carbon emission optimization is then performed according to this fitness function to obtain the target optimization action set. This step simultaneously minimizes carbon emission excess and the number of control actions using the fitness function, compressing the multi-objective trade-off problem into a single numerical optimization. Combined with constraints, an executable action sequence is output in one go, achieving automatic transition from carbon emission alarms to specific equipment-level commands, eliminating the need for engineers to manually program strategies. Therefore, this invention improves the accuracy of carbon emission prediction and enhances the automation level of equipment control during carbon emission optimization. Attached Figure Description

[0078] Figure 1 A flowchart illustrating a carbon emission intelligent optimization method based on a monitoring and management platform provided in an embodiment of the present invention;

[0079] Figure 2 A functional block diagram of a carbon emission intelligent optimization system based on a monitoring and management platform provided in an embodiment of the present invention;

[0080] Figure 3 This is a schematic diagram of the structure of an electronic device for implementing the intelligent carbon emission optimization method based on a monitoring and management platform, according to an embodiment of the present invention.

[0081] Explanation of reference numerals in the attached figures:

[0082] 10. Electronic device; 11. Processor; 12. Memory; 13. Bus.

[0083] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0084] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0085] This application provides a method for intelligent carbon emission optimization based on a monitoring and management platform. The executing entity of this method includes, but is not limited to, at least one electronic device that can be configured to execute the method provided in this application, such as a server or a terminal. In other words, the method can be executed by software or hardware installed on a terminal device or server device, and the software may be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster.

[0086] Reference Figure 1 The diagram shown is a flowchart illustrating a carbon emission intelligent optimization method based on a monitoring and management platform according to an embodiment of the present invention. In this embodiment, the carbon emission intelligent optimization method based on a monitoring and management platform includes:

[0087] S1. Receive carbon emission optimization instructions, determine the monitoring area based on the carbon emission optimization instructions, and obtain the set of equipment to be optimized in the monitoring area, wherein the set of equipment to be optimized includes multiple equipment to be optimized.

[0088] It is clear that the carbon emission optimization instruction refers to a human-initiated instruction to optimize carbon emissions in a specific area. The monitoring area refers to the specific area included in the carbon emission optimization instruction. Carbon emission optimization refers to reducing carbon emissions by adjusting various electrical devices within the monitoring area. The set of devices to be optimized refers to the collection of various electrical devices within the monitoring area.

[0089] S2 sends a preset energy consumption polling command to the set of devices to be optimized based on a pre-built IoT gateway to obtain the target device set, wherein the target device set includes multiple target devices, and the IoT gateway includes a protocol adaptation layer.

[0090] Understandably, the IoT gateway refers to a communication hub device used to connect various electrical devices within the monitoring area with the upper-level management system. For example, it could be an industrial IoT gateway based on MQTT or CoAP protocols. This IoT gateway includes a protocol adaptation layer to support multiple communication protocols such as Zigbee and LoRa, enhancing compatibility with heterogeneous devices and obtaining a target device set. The energy consumption polling command refers to a periodically sent command to query the current energy consumption status of a device. Its content may include device identifier, query timestamp, data acquisition parameters, etc. This energy consumption polling command is sent periodically to achieve periodic carbon emission optimization of the monitoring area. The target device set refers to the set of devices to be optimized that receive the energy consumption polling command. Traditional gateways lack multi-protocol support; this invention automatically achieves compatibility with heterogeneous devices through the IoT gateway and polling command.

[0091] S3. Extract the target devices sequentially from the target device set, collect energy consumption data from the target devices, and obtain the device energy consumption data.

[0092] It is clear that the device energy consumption data refers to the data on the current operation and energy consumption of the target device. This data consists of the previous operating state vector, the current energy consumption, and the current device data. A detailed explanation of the previous operating state vector, the current energy consumption, and the current device data will be given later.

[0093] Specifically, the process of collecting energy consumption data from the target device to obtain device energy consumption data includes:

[0094] Confirm the initial acquisition time and record it as the current acquisition time;

[0095] Data is collected from the target device based on the current acquisition time to obtain the current device data, which includes: current current, current voltage, current power, and current temperature;

[0096] Calculate the target acquisition time based on the current acquisition time and the preset acquisition interval, and calculate the acquisition duration between the initial acquisition time and the target acquisition time;

[0097] The target acquisition time is taken as the current acquisition time, and the step of acquiring data from the target device based on the current acquisition time is returned until the acquisition time is not less than the preset management cycle.

[0098] Summarize the current device data to obtain the current device dataset;

[0099] The current energy consumption is calculated based on the current device dataset, and the calculation method for the current energy consumption is as follows:

[0100] ,

[0101] in, Indicates current energy consumption. This indicates the number of data points for the current device in the current device dataset. Represents the first in the current device dataset The current power corresponding to the current device data. Indicates the data collection interval;

[0102] Based on the initial acquisition time, the previous operating state vector is identified. The previous operating state vector and the current energy consumption are added to the current device dataset to obtain device energy consumption data, which is used for energy consumption prediction.

[0103] Understandably, the initial acquisition time refers to the moment when data acquisition of the target device begins, and the current acquisition time refers to the current moment when data acquisition of the target device begins. At the beginning of data acquisition of the target device, the initial acquisition time and the current acquisition time are equal. Subsequently, as data acquisition proceeds, the current acquisition time will continuously be greater than the initial acquisition time.

[0104] It should be explained that the current device data refers to the status data of the target device at the current acquisition time. The current device data includes the current current, current voltage, current power and current temperature of the target device at the current acquisition time. In addition, the current device data may also include: operating time, load rate, power factor, etc.

[0105] Furthermore, the acquisition interval refers to the time interval between two consecutive data acquisitions, which is set manually. The target acquisition time refers to the time of one acquisition interval after the current acquisition time. Furthermore, this solution also introduces an adaptive acquisition mechanism, which includes dynamically adjusting the interval according to the device load (e.g., increasing the frequency under high load) to reduce data blind spots. The acquisition duration refers to the time interval between the initial acquisition time and the target acquisition time. The management cycle refers to the duration required for one energy consumption data acquisition, which is also the duration for one carbon emission optimization of the set of devices to be optimized. The preceding operating state vector refers to the operating state vector of the area where the target device is located. This preceding operating state vector consists of multiple values ​​of 0 and multiple values ​​of 1, where a value of 0 indicates that a device to be optimized in the same area as the target device is in a turned-off state (i.e., power is not turned on), and a value of 1 indicates that a device to be optimized in the same area as the target device is in a turned-on state. The details of the operating state vector will be explained later.

[0106] It is clear that the energy consumption prediction model is trained by fusing historical multi-device data, outputs predicted device energy consumption, and then combines the power grid carbon emission factor to directly calculate carbon emissions, ensuring a linear correlation between the energy consumption prediction results and carbon emission calculations, thereby improving the rationality of carbon emission prediction.

[0107] S4. Based on the equipment energy consumption data and the pre-built energy consumption prediction model, energy consumption is predicted to obtain the predicted equipment energy consumption.

[0108] Understandably, the energy consumption prediction model refers to a pre-built neural network model that predicts the energy consumption of a target device. The input of this model is the device's energy consumption data, and the output is the energy consumption of the target device after a certain period of time (i.e., subsequent prediction intervals). In other words, the predicted device energy consumption is the output value of the energy consumption prediction model. Existing energy consumption prediction models are mostly single-device models. This invention enhances prediction accuracy by fusing data from multiple devices and operating state vectors.

[0109] Specifically, before predicting the energy consumption based on equipment energy consumption data and a pre-built energy consumption prediction model to obtain the predicted equipment energy consumption, the method further includes:

[0110] Identify the target device's data repository;

[0111] Query historical energy consumption data of the target device based on the data repository;

[0112] The monitoring area is functionally divided into multiple functional zones, and the target area where the target device is located is identified among these multiple functional zones.

[0113] Identify the historical management cycle corresponding to the historical energy consumption data, and calculate the predicted management cycle based on the historical management cycle and the preset prediction interval;

[0114] Based on the target area, an operation status vector is constructed, and the operation status vector is supplemented to the historical energy consumption data to obtain multi-device fusion data;

[0115] Based on the predictive management cycle, query the actual device energy consumption in the data repository, and use the actual device energy consumption to label the multi-device fusion data to obtain labeled device data.

[0116] The pre-constructed original prediction model is trained using labeled equipment data to obtain an energy consumption prediction model, wherein the energy consumption prediction model is used to predict equipment energy consumption and calculate the predicted equipment carbon emissions.

[0117] It is clear that the data repository refers to a repository that records the operating data of the target device in previous periods. The historical energy consumption data refers to the energy consumption data of the target device collected during a certain historical management cycle. The multiple functional areas refer to multiple sub-areas that make up the monitoring area, which are divided manually, such as by floor, for example, dividing one floor into one functional area. The target area refers to the functional area where the target device is located. The historical management cycle refers to the management cycle when the historical energy consumption data was collected. The predictive management cycle refers to the cycle that the energy consumption prediction model needs to predict, and the prediction interval refers to the time interval that the energy consumption prediction model can predict. For example, if the data input to the energy consumption prediction model is the data collected within management cycle A (corresponding to the historical management cycle), and the energy consumption output by the energy consumption prediction model is the energy consumption within management cycle B (corresponding to the predictive management cycle), then the interval between management cycle A and management cycle B is the prediction interval. The multi-device fusion data refers to the historical energy consumption data after supplementing the operating state vector. The actual device energy consumption refers to the energy consumption value of the target device during the predictive management cycle recorded in the data repository. The labeled device data refers to the multi-device fusion data after labeling. The original prediction model refers to an untrained neural network model. Optionally, an MLP (Multilayer Perceptron) or LSTM (Long Short-Term Memory) network can be used as the original prediction model. It should be noted that in the above steps of training the pre-built original prediction model using labeled device data, a large amount of labeled device data needs to be obtained and used for training.

[0118] Specifically, the construction of the running state vector based on the target region includes:

[0119] Obtain the set of devices in the same area within the target area, wherein the set of devices in the same area includes multiple devices in the same area, and the devices in the same area are in the same functional area as the target device;

[0120] Based on the historical management cycle, the operating status of the equipment set in the same area is identified to obtain the operating status identifier set. The operating status identifier set includes multiple operating status identifiers, where the operating status identifier is a value of 0 or a value of 1. A value of 1 indicates that the equipment in the same area is in the operating state at the end of the historical management cycle, and a value of 0 indicates that the equipment in the same area is in the off state at the end of the historical management cycle.

[0121] Construct a running status vector based on the running status identifier set.

[0122] It should be explained that the "set of devices in the same region" refers to the set of all devices to be optimized in the target region. The construction of the running status vector based on the running status identifier set is, for example: if the running status identifier set is: (device in the same region C1:0, device in the same region C2:1, device in the same region C3:1), then the running status vector is: .

[0123] Furthermore, the purpose of introducing the aforementioned operating state vector is that, within the same functional area, different devices to be optimized are interconnected. For example, if one device to be optimized is turned off (such as an air conditioner), the load on another connected refrigeration device decreases, its power drops, and its energy consumption decreases. Conversely, if multiple devices operate simultaneously, the load on a single device may increase due to synergistic effects. Therefore, it is necessary to introduce an operating state vector to reflect the interrelationships of the operating states of devices within the area.

[0124] Understandably, the above-mentioned operational status identification requires incorporating equipment lifecycle data and seasonal parameters. Data augmentation techniques are used to synthesize simulated data for different seasons, such as adding aging degradation factors or seasonal fluctuation coefficients to historical data, in order to improve the model's adaptability to changes in equipment status.

[0125] S5. Calculate the carbon emissions of the predicted equipment based on the preset power grid carbon emission factor and the predicted equipment energy consumption, summarize the predicted equipment carbon emissions, and obtain the predicted equipment carbon emission set.

[0126] It is understood that the grid carbon emission factor refers to the carbon dioxide emissions (unit: kgCO2 / kWh) corresponding to a unit of electricity consumption. This grid carbon emission factor is obtained by using average carbon emission factor data published by the national or regional power grid. The predicted equipment carbon emission refers to the expected carbon dioxide emissions generated by the target equipment due to energy consumption in a future period. The predicted equipment carbon emission is calculated as follows: grid carbon emission factor multiplied by predicted equipment energy consumption = predicted equipment carbon emission.

[0127] S6. Apply external factor correction to the predicted carbon emission set of equipment to obtain the cumulative carbon emissions;

[0128] It should be explained that the cumulative carbon emissions refer to the cumulative carbon emissions within the monitoring area after correction. Since different external influencing factors affect carbon emissions, these external influencing factors refer to non-equipment-related factors that affect carbon emissions, such as indoor temperature, outdoor temperature, solar irradiance, and population density. For example, when population density increases, lighting and air conditioning loads increase, leading to increased energy consumption and carbon emissions; similarly, when outdoor temperature increases, refrigeration equipment loads increase, leading to increased energy consumption and carbon emissions. Therefore, it is necessary to combine external influencing factors to dynamically correct the carbon emissions of different functional areas within the monitoring area (i.e., the subsequent total regional emissions). Existing methods do not correct for external factors; this invention introduces parameters such as population density for dynamic correction to reduce errors.

[0129] In detail, the external factor correction of the predicted equipment carbon emission set to obtain the cumulative carbon emissions includes:

[0130] Extract the functional areas sequentially from multiple functional areas;

[0131] Based on the management cycle, external factors are statistically analyzed for functional areas to obtain a set of external impact parameters, which include: personnel density, outdoor temperature, indoor temperature, and solar irradiance.

[0132] The set of external influence parameters is normalized to obtain the set of target influence parameters.

[0133] A carbon emission correction model is constructed, and the target impact parameter set is input into the carbon emission correction model to obtain the correction ratio;

[0134] Based on the functional area, the carbon emission set of the predicted equipment carbon emission set is identified, and the total regional emission is obtained by summing the regional carbon emission sets.

[0135] The total regional emissions are corrected using the correction ratio to obtain the corrected carbon emissions;

[0136] The corrected carbon emissions are summarized to obtain the corrected carbon emission set. The corrected carbon emission set is then summed to obtain the cumulative carbon emissions.

[0137] It is clear that the external impact parameter set refers to a collection of multiple external impact parameters. These external impact parameters refer to external factors that affect the carbon emissions of a functional area, such as personnel density, outdoor temperature, indoor temperature, and solar irradiance. These external impact parameters are average values. For example, if a certain external impact parameter is personnel density, multiple statistical personnel densities are collected during the management period. Statistical personnel density is the number of people per unit area within the functional area. For example, the calculation method is: Statistical personnel density = Total number of people in the functional area at a certain time / Area of ​​the functional area. The average value of these multiple statistical personnel densities is the personnel density at this location. The target impact parameter set refers to the normalized set of external impact parameters. This normalization eliminates the influence of different dimensions between parameters. The normalization method can be: using a specific function (such as the sigmoid function) for normalization, or normalizing by manually setting a maximum value. The carbon emission correction model refers to a neural network model that can output a correction ratio based on the input current external impact factors. The explanation of the correction ratio will be given later in conjunction with detailed steps. The regional carbon emission set refers to the collection of carbon emissions from multiple predicted devices corresponding to multiple target devices within a functional area. The total regional emissions refer to the sum of all regional carbon emissions in the regional carbon emission set. The corrected carbon emissions refer to the corrected total regional emissions, calculated by multiplying the total regional emissions by a correction ratio.

[0138] Specifically, the construction of the carbon emission correction model includes:

[0139] Collect the historical predicted emissions set of the functional area, wherein the historical predicted emissions set includes multiple historical predicted emissions, and each historical predicted emissions corresponds to a different management cycle;

[0140] Historical predicted emissions are extracted sequentially from the historical predicted emissions set;

[0141] Obtain the emission management cycle of historical predicted emissions, and statistically analyze the historical external parameter set of the functional area within the emission management cycle. The historical external parameter set includes: historical population density, historical outdoor temperature, historical outdoor temperature and historical solar irradiance.

[0142] A historical external parameter vector is constructed based on the historical external parameter set, and the actual carbon emissions are obtained according to the emission management cycle.

[0143] The carbon emission ratio is calculated based on actual carbon emissions and historical predicted emissions.

[0144] By summarizing the historical external parameter vectors and carbon emission ratios, we obtain the historical external parameter vector set and carbon emission ratio set.

[0145] The training extrinsic parameter vector set is obtained by clustering and filtering based on the historical extrinsic parameter vector set.

[0146] Identify the training proportion set based on the training extrinsic parameter vector set in the carbon emission proportion set;

[0147] The training ratio set is paired with the training extrinsic parameter vector set to obtain the carbon emission training dataset. The carbon emission training dataset includes multiple carbon emission training data, and each carbon emission training data contains a training ratio and its corresponding training extrinsic parameter vector.

[0148] A pre-built neural network is trained using a carbon emission training dataset to obtain a carbon emission correction model.

[0149] It is clear that the historical predicted emissions set refers to a collection of multiple historical predicted emissions, each corresponding to a management cycle. The historical predicted emissions refer to the sum of the total carbon emissions of a functional area obtained through prediction within a specific management cycle. This historical predicted emissions is obtained by acquiring the predicted carbon emissions set of the functional area within a specific management cycle (i.e., subsequent emission management cycles) using the method described above. Each predicted carbon emission in the set corresponds one-to-one with the equipment to be optimized within the functional area. Then, the sum of all predicted carbon emissions in the set is calculated to obtain the historical predicted emissions. In other words, this historical predicted emissions is the carbon emissions obtained through prediction without considering external influencing factors. The emission management cycle refers to the management cycle predicted by the historical predicted emissions. The historical external parameter set refers to the set of external influence parameters of the functional area collected within the emission management cycle, and all historical external parameter sets have been normalized. The historical extrinsic parameter vector refers to a vector constructed from a set of historical extrinsic parameters. The steps for constructing the historical extrinsic parameter vector based on the historical extrinsic parameter set are the same as those for constructing the operational status vector based on the operational status identifier set. The actual carbon emissions refer to the actual carbon emissions of the functional area obtained during the emission management cycle, which are obtained through actual data collection.

[0150] Furthermore, the carbon emission ratio refers to the result obtained by dividing the actual carbon emissions by the historical predicted emissions. The training extrinsic parameter vector set refers to the historical extrinsic parameter vector set after clustering and filtering. Since extreme external conditions may occur in the historical extrinsic parameter vector set, such as extreme heat weather or large gatherings of people due to major events, these extreme external conditions are not universal or representative. Therefore, it is necessary to perform clustering and filtering on the historical extrinsic parameter vector set to filter out these extreme external conditions.

[0151] It is clear that the training ratio set refers to a collection of multiple carbon emission ratios corresponding to the training extrinsic parameter vector set within the carbon emission ratio set. The carbon emission training dataset refers to a collection of multiple carbon emission training data, where each carbon emission training data represents a combination of a training ratio and its corresponding training extrinsic parameter vector. The process of matching the training ratio set with the training extrinsic parameter vector set involves: sequentially extracting training ratios from the training ratio set, identifying the corresponding training extrinsic parameter vector in the training extrinsic parameter vector set, merging the training ratio with its corresponding training extrinsic parameter vector to obtain the carbon emission training data, and summarizing the carbon emission training data to obtain the carbon emission training dataset. The neural network model used to train the carbon emission correction model can be selected from convolutional neural networks, long short-term memory networks, etc.

[0152] Specifically, the step of clustering and filtering based on the historical extrinsic parameter vector set to obtain the training extrinsic parameter vector set includes:

[0153] Clustering the historical extrinsic parameter vector set yields multiple clustered extrinsic parameter vector sets;

[0154] Extract cluster extrinsic parameter vector sets sequentially from multiple cluster extrinsic parameter vector sets;

[0155] The number of cluster vectors in the cluster extrinsic parameter vector set is counted. If the number of cluster vectors is greater than the preset extreme number, the cluster extrinsic parameter vector set is recorded as the effective parameter vector set.

[0156] The effective parameter vector set is summarized to obtain the training extrinsic parameter vector set.

[0157] It is clear that the multiple clustering extrinsic parameter vector sets refer to multiple category sets obtained after processing by the clustering algorithm. Each clustering extrinsic parameter vector set contains several historical extrinsic parameter vectors with similar Euclidean distances. In the above clustering process, vectors with similar Euclidean distances are grouped into the same cluster, thus ensuring that samples within each cluster have high similarity. Optionally, methods such as DBSCAN clustering and HDBSCAN clustering can be used to implement the above clustering process.

[0158] It should be explained that the number of clustering vectors refers to the number of extrinsic parameter vectors in the clustering extrinsic parameter vector set. The extreme number refers to a human-defined constant. When the number of clustering vectors is less than or equal to the extreme number, it indicates that the corresponding clustering extrinsic parameter vector set represents an extreme case and should not be considered a valid parameter vector set.

[0159] S7. Obtain the pre-simulation control action library, which includes multiple pre-simulation control data, including: pre-simulation control actions and the carbon emission of the control actions.

[0160] It is clear that the aforementioned pre-simulation control action library refers to a database constructed by humans to calibrate the effects of each pre-simulation control action. The pre-simulation control data refers to a combination of pre-simulation control actions, the carbon emissions of the control actions, and the wear values ​​of the control equipment. The pre-simulation control action refers to an executable energy-saving control operation, which consists of a specific action and a numerical value. For example: lowering the chilled water temperature by 1 degree Celsius (action: lowering the chilled water temperature, value: 1 degree Celsius); lowering the lighting brightness of a certain functional area by 50 nits (action: lowering the lighting brightness of a certain functional area, value: 50 nits). Different pre-simulation control actions will bring different effects, namely, reducing carbon emissions. The effects of different pre-simulation control actions are quantified numerically by relevant engineers through experiments. For example, a pre-simulation control action is to lower the lighting brightness of a certain functional area by 50 nits. Preliminary experiments show that when this action is executed, carbon emissions are reduced. Therefore, the pre-simulation control data is as follows: (reducing the lighting brightness of a certain functional area by 50 nits, the carbon emission of the control action is...) The pre-simulation control action library quantifies experience, replaces traditional trial and error, and improves the degree of automation.

[0161] S8. Construct a fitness function based on the pre-simulated control action library, cumulative carbon emissions, and preset baseline carbon emissions. Perform carbon emission optimization based on the fitness function to obtain the target optimized action group.

[0162] Understandably, the baseline carbon emissions refer to the maximum carbon emissions allowed within a management cycle, set manually. This baseline carbon emissions are obtained by setting it based on historical carbon emission data, policy requirements, or energy-saving targets. The fitness function integrates multi-objective optimization, solving the problem of traditional strategies relying on manual orchestration.

[0163] Furthermore, the fitness function refers to the formula for calculating the fitness value when the optimization algorithm is executed subsequently. The target optimization action group refers to the action combination obtained after carbon emission optimization. This target optimization action group contains multiple target actions, and each target action corresponds to an execution parameter. The target actions in the target optimization action group correspond one-to-one with the pre-execution control actions in the control action library. The execution parameter is a value of 0 or a positive integer. A value of 0 indicates that the target action is not executed, and a positive integer indicates the number of times the target action is executed. For example, if the target optimization action group is: (lower chilled water temperature by 1 degree Celsius: 0, lower the lighting brightness of a certain functional area by 50 nits: 5), then this target optimization action group means: not executing the action of lowering the chilled water temperature by 1 degree Celsius, that is, not controlling the chilled water temperature; lowering the lighting brightness of a certain functional area by 50 nits and lowering it 5 times, that is, lowering the lighting brightness of a certain functional area by 250 nits.

[0164] It should be explained that carbon emission optimization steps will only be performed when the cumulative carbon emissions exceed the baseline carbon emissions.

[0165] In detail, the construction of the fitness function based on the pre-simulated control action library, cumulative carbon emissions, and preset baseline carbon emissions includes:

[0166] Set the control action vector, which consists of multiple execution parameters;

[0167] The number of control actions in the statistical control action vector is the same as the number of pre-simulated control data in the pre-simulated control action library;

[0168] A fitness function is constructed based on the pre-simulated control action library, the number of control actions, the control action vector, the cumulative carbon emissions, and the baseline carbon emissions.

[0169] It is clear that the aforementioned control action vector refers to a vector composed of multiple execution parameters, where each execution parameter corresponds to a pre-simulated control action. For example, in a control action vector of (0, 5), the vector position of 0 corresponds to the pre-simulated control action: lowering the chilled water temperature by 1 degree Celsius, and 5 corresponds to the control action: reducing the lighting brightness of a certain functional area by 50 nits. That is, the execution parameters in the control action vector correspond one-to-one with the pre-simulated control actions in the pre-simulated control action library. The subsequent optimization process involves adjusting each execution parameter in the control action vector through an optimization algorithm to minimize the value of the fitness function, thereby achieving intelligent recommendation of control actions while meeting carbon emission constraints.

[0170] In detail, the fitness function is expressed as:

[0171] ,

[0172] in, Represents the fitness function. This represents the preset mapping function. Represents the control action vector, This indicates the preset carbon emission weight. This indicates cumulative carbon emissions. Indicates baseline carbon emissions. Indicates the number of regulatory actions. The first element in the control action vector represents the... One execution parameter, The first element in the control action vector represents the... Each execution parameter corresponds to a carbon emission amount of the control action in the pre-simulated control action library. This indicates the preset weight of the number of adjustments.

[0173] It is clear that the mapping function refers to a function that scales a value to a specific range of values; optionally, the mapping function is selected as the sigmoid function. The carbon emission weight and the adjustment frequency weight refer to the artificially set weights for carbon emission and the adjustment frequency, respectively. The first... The carbon emission of the corresponding control action in the pre-simulated control action library for each execution parameter refers to: the first... The carbon emission amount of the corresponding control action in the pre-simulated control action library for each execution parameter location.

[0174] The above needs to be explained. This represents the reduction in carbon emissions achieved by executing the control actions and parameters in the control action vector. This represents the difference between the cumulative carbon emissions after reduction and the baseline carbon emissions. This item must meet the following requirements: ,in, This represents the minimum carbon emission level set by the individual, and the smaller the value, the greater the reduction in carbon emissions. The term represents the total number of adjustments required in the adjustment action vector. The larger the term, the more adjustments are required, i.e., the more complex the operation. The fitness function described above is constructed by using the two optimization objectives of the number of operations and the amount of carbon emissions reduced.

[0175] It is important to note that when executing a specific algorithm, relevant engineers need to set constraints. These constraints include numerical constraints on the carbon emissions of each pre-simulated control action in the pre-simulated control action library. For example, if the current time is nighttime and the lighting brightness of a certain area should not be too low, the relevant engineers can retrieve the constraint that reduces the lighting brightness of a certain functional area by 50 nits under nighttime conditions: the lighting brightness of that area should not be lower than 500 nits. These constraints are set by the relevant R&D personnel, and the engineers only need to retrieve them based on the current situation. Meanwhile, This constraint ensures that the reduction in carbon emissions guarantees that the cumulative carbon emissions will not exceed the baseline carbon emissions, while also ensuring the normal operation of the monitoring area. In addition, the number of control measures can also be introduced. Numerical constraints and other constraints are applied.

[0176] Furthermore, this scheme provides a specific fitness function, optimization objective (the smaller the fitness function, the better), and optimization carrier (regulation action vector). Therefore, the above-mentioned carbon emission optimization can be performed through optimization algorithms such as genetic algorithms and simulated annealing. Since the optimization algorithms here are existing technologies, they will not be described in detail here.

[0177] S9. Transmit the target optimization action group to the pre-built data management platform to complete the intelligent optimization of carbon emissions based on the monitoring and management platform.

[0178] It should be explained that once the target optimization action group is obtained, it needs to be transmitted to the data management platform. The data management platform refers to the software used to receive, store, display, and issue control instructions, thus providing reference for relevant operators or managers. The aforementioned data management platform includes a visual dashboard, which can be used to display carbon emission reductions, control effects, and equipment status in real time, providing user feedback and decision support.

[0179] To address the problems described in the background section, this invention first predicts energy consumption based on equipment energy consumption data and an energy consumption prediction model. This yields predicted equipment energy consumption. This step trains a dedicated energy consumption prediction model using historical multi-device fusion data, incorporating the high-dimensional variable of regional equipment start-up and shutdown combinations into the input. This transforms the model output from an isolated extrapolation of a single device into a group energy consumption prediction that anticipates the synergistic effects of equipment clusters, significantly reducing the bias of traditional sequence predictions in equipment linkage scenarios. Next, external factors are applied to the predicted equipment carbon emission set to obtain cumulative carbon emissions. This step introduces external parameters such as personnel density and solar irradiance to dynamically correct the predicted emissions at the regional level, transforming meteorological and human-caused disturbances from error terms into modelable variables. This allows the cumulative carbon emissions to closely approximate real-world operating scenarios, avoiding significant deviations that occur with traditional methods under conditions of high personnel mobility. Furthermore, this solution also incorporates pre-emptive control. The invention includes an action library, specifically a pre-simulated control action library comprising multiple pre-simulated control data sets. These pre-simulated control actions and their corresponding carbon emission values ​​pre-quantify the absolute carbon reduction of each operation, transforming control commands from fuzzy experience into quantifiable carbon emission values. This allows subsequent algorithms to directly combine and assemble these values ​​at the digital level, eliminating the need for online trial and error or on-site calibration, significantly shortening the optimization loop time. Finally, a fitness function is constructed based on the pre-simulated control action library, cumulative carbon emissions, and a preset baseline carbon emissions. Carbon emission optimization is then performed according to this fitness function to obtain the target optimization action set. This step simultaneously minimizes carbon emission excess and the number of control actions using the fitness function, compressing the multi-objective trade-off problem into a single numerical optimization. Combined with constraints, an executable action sequence is output in one go, achieving automatic transition from carbon emission alarms to specific equipment-level commands, eliminating the need for engineers to manually program strategies. Therefore, this invention improves the accuracy of carbon emission prediction and enhances the automation level of equipment control during carbon emission optimization.

[0180] like Figure 2 The diagram shown is a functional block diagram of a carbon emission intelligent optimization system based on a monitoring and management platform provided in an embodiment of the present invention.

[0181] The carbon emission intelligent optimization system 100 based on a monitoring and management platform described in this invention can be installed in an electronic device. Depending on the functions implemented, the carbon emission intelligent optimization system 100 based on the monitoring and management platform may include a target device determination module 101, a device energy consumption prediction module 102, a carbon emission prediction module 103, and a control action transmission module 104. The module described in this invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and are stored in the memory of the electronic device.

[0182] The target device determination module 101 is used to receive carbon emission optimization instructions, determine the monitoring area based on the carbon emission optimization instructions, and obtain the set of devices to be optimized in the monitoring area. The set of devices to be optimized includes multiple devices to be optimized. Based on a pre-built IoT gateway, a preset energy consumption polling instruction is sent to the set of devices to be optimized to obtain the target device set. The target device set includes multiple target devices. The IoT gateway includes a protocol adaptation layer.

[0183] The device energy consumption prediction module 102 is used to sequentially extract target devices from the target device set, collect energy consumption data of the target devices to obtain device energy consumption data, and perform energy consumption prediction based on the device energy consumption data and the pre-built energy consumption prediction model to obtain the predicted device energy consumption.

[0184] The carbon emission prediction module 103 is used to calculate the carbon emission of the prediction equipment based on the preset power grid carbon emission factor and the energy consumption of the prediction equipment, summarize the carbon emission of the prediction equipment to obtain the carbon emission set of the prediction equipment, and perform external factor correction on the carbon emission set of the prediction equipment to obtain the cumulative carbon emission.

[0185] The control action transmission module 104 is used to acquire a pre-simulated control action library, wherein the pre-simulated control action library includes multiple pre-simulated control data, and the pre-simulated control data includes: pre-simulated control actions and control action carbon emissions. Based on the pre-simulated control action library, the cumulative carbon emissions and the preset benchmark carbon emissions, a fitness function is constructed. Carbon emission optimization is performed according to the fitness function to obtain a target optimization action group. The target optimization action group is then transmitted to a pre-constructed data management platform.

[0186] In detail, the modules in the carbon emission intelligent optimization system 100 based on the monitoring and management platform described in this embodiment of the invention adopt the same characteristics as described above when in use. Figure 1 The method uses the same technical means as the intelligent carbon emission optimization method based on the monitoring and management platform described in the article, and can produce the same technical effect, so it will not be repeated here.

[0187] like Figure 3The diagram shown is a schematic representation of an electronic device for implementing a carbon emission intelligent optimization method based on a monitoring and management platform, according to an embodiment of the present invention.

[0188] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and capable of running on the processor 10, such as a carbon emission intelligent optimization method program based on a monitoring and management platform.

[0189] The memory 11 includes at least one type of readable storage medium, such as flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as a portable hard drive. In other embodiments, the memory 11 can be an external storage device of the electronic device 1, such as a plug-in portable hard drive, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the electronic device 1. Furthermore, the memory 11 includes both internal storage units and external storage devices of the electronic device 1. The memory 11 can be used not only to store application software and various types of data installed on the electronic device 1, such as the code of a carbon emission intelligent optimization method program based on a monitoring and management platform, but also to temporarily store data that has been output or will be output.

[0190] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device, connecting various components of the entire electronic device through various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., a carbon emission intelligent optimization method program based on a monitoring and management platform) and calls data stored in the memory 11 to perform various functions of the electronic device 1 and process data.

[0191] The bus 12 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 can be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to realize the connection and communication between the memory 11 and at least one processor 10, etc.

[0192] Figure 3 Only electronic devices with components are shown; it will be understood by those skilled in the art that... Figure 3 The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0193] For example, although not shown, the electronic device 1 may also include a power supply (such as a battery) to power the various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management system, thereby enabling functions such as charging management, discharging management, and power consumption management through the power management system. The power supply may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0194] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, a Bluetooth interface, etc.), which is typically used to establish communication connections between the electronic device 1 and other electronic devices.

[0195] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), and optionally, a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device 1 and to display a visual user interface.

[0196] The carbon emission intelligent optimization method program based on the monitoring and management platform stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When run in the processor 10, it can achieve the following:

[0197] Receive carbon emission optimization instructions, determine the monitoring area based on the carbon emission optimization instructions, and obtain the set of equipment to be optimized in the monitoring area, wherein the set of equipment to be optimized includes multiple equipment to be optimized;

[0198] Based on a pre-built IoT gateway, a preset energy consumption polling command is sent to the set of devices to be optimized to obtain the target set of devices. The target set of devices includes multiple target devices, and the IoT gateway includes a protocol adaptation layer.

[0199] The target devices are extracted sequentially from the target device set, and energy consumption data is collected from the target devices to obtain the device energy consumption data.

[0200] Energy consumption is predicted based on equipment energy consumption data and a pre-built energy consumption prediction model to obtain the predicted equipment energy consumption.

[0201] The carbon emissions of the predicted equipment are calculated based on the preset power grid carbon emission factor and the predicted equipment energy consumption. The predicted equipment carbon emissions are then summarized to obtain the predicted equipment carbon emission set.

[0202] External factors are applied to the predicted carbon emissions set to obtain the cumulative carbon emissions.

[0203] Obtain a pre-simulated control action library, which includes multiple pre-simulated control data, including: pre-simulated control actions and the carbon emissions of the control actions;

[0204] A fitness function is constructed based on the pre-simulated control action library, cumulative carbon emissions, and preset baseline carbon emissions. Carbon emission optimization is then performed based on the fitness function to obtain the target optimized action set.

[0205] The target optimization action group is transmitted to the pre-built data management platform to complete the intelligent optimization of carbon emissions based on the monitoring and management platform.

[0206] Specifically, the processor 10's implementation method for the above instructions can be found in [reference needed]. Figures 1 to 3 The descriptions of the relevant steps in the corresponding embodiments are not repeated here.

[0207] Furthermore, if the modules / units integrated in the electronic device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or system capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0208] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor of an electronic device, can perform the following:

[0209] Receive carbon emission optimization instructions, determine the monitoring area based on the carbon emission optimization instructions, and obtain the set of equipment to be optimized in the monitoring area, wherein the set of equipment to be optimized includes multiple equipment to be optimized;

[0210] Based on a pre-built IoT gateway, a preset energy consumption polling command is sent to the set of devices to be optimized to obtain the target set of devices. The target set of devices includes multiple target devices, and the IoT gateway includes a protocol adaptation layer.

[0211] The target devices are extracted sequentially from the target device set, and energy consumption data is collected from the target devices to obtain the device energy consumption data.

[0212] Energy consumption is predicted based on equipment energy consumption data and a pre-built energy consumption prediction model to obtain the predicted equipment energy consumption.

[0213] The carbon emissions of the predicted equipment are calculated based on the preset power grid carbon emission factor and the predicted equipment energy consumption. The predicted equipment carbon emissions are then summarized to obtain the predicted equipment carbon emission set.

[0214] External factors are applied to the predicted carbon emissions set to obtain the cumulative carbon emissions.

[0215] Obtain a pre-simulated control action library, which includes multiple pre-simulated control data, including: pre-simulated control actions and the carbon emissions of the control actions;

[0216] A fitness function is constructed based on the pre-simulated control action library, cumulative carbon emissions, and preset baseline carbon emissions. Carbon emission optimization is then performed based on the fitness function to obtain the target optimized action set.

[0217] The target optimization action group is transmitted to the pre-built data management platform to complete the intelligent optimization of carbon emissions based on the monitoring and management platform.

[0218] In the embodiments provided by this invention, it should be understood that the disclosed devices, systems, and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative, and actual implementations may have other classification methods.

[0219] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0220] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0221] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0222] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for intelligent optimization of carbon emissions based on a monitoring and management platform, characterized in that, The method includes: Receive carbon emission optimization instructions, determine the monitoring area based on the carbon emission optimization instructions, and obtain the set of equipment to be optimized in the monitoring area, wherein the set of equipment to be optimized includes multiple equipment to be optimized; Based on a pre-built IoT gateway, a preset energy consumption polling command is sent to the set of devices to be optimized to obtain the target set of devices. The target set of devices includes multiple target devices, and the IoT gateway includes a protocol adaptation layer. The target devices are extracted sequentially from the target device set, and energy consumption data is collected from the target devices to obtain the device energy consumption data. Energy consumption is predicted based on equipment energy consumption data and a pre-built energy consumption prediction model to obtain the predicted equipment energy consumption. The carbon emissions of the predicted equipment are calculated based on the preset power grid carbon emission factor and the predicted equipment energy consumption. The predicted equipment carbon emissions are then summarized to obtain the predicted equipment carbon emission set. External factors are applied to the predicted carbon emissions set to obtain the cumulative carbon emissions. Obtain a pre-simulated control action library, which includes multiple pre-simulated control data, including: pre-simulated control actions and the carbon emissions of the control actions; A fitness function is constructed based on the pre-simulated control action library, cumulative carbon emissions, and preset baseline carbon emissions. Carbon emission optimization is then performed based on the fitness function to obtain the target optimized action set. The target optimization action group is transmitted to the pre-built data management platform to complete the intelligent optimization of carbon emissions based on the monitoring and management platform.

2. The intelligent carbon emission optimization method based on a monitoring and management platform as described in claim 1, characterized in that, The process of collecting energy consumption data from the target device to obtain device energy consumption data includes: Confirm the initial acquisition time and record it as the current acquisition time; Data is collected from the target device based on the current acquisition time to obtain the current device data, which includes: current current, current voltage, current power, and current temperature; Calculate the target acquisition time based on the current acquisition time and the preset acquisition interval, and calculate the acquisition duration between the initial acquisition time and the target acquisition time; The target acquisition time is taken as the current acquisition time, and the step of acquiring data from the target device based on the current acquisition time is returned until the acquisition time is not less than the preset management cycle. Summarize the current device data to obtain the current device dataset; The current energy consumption is calculated based on the current device dataset, and the calculation method for the current energy consumption is as follows: ， in, Indicates current energy consumption. This indicates the number of data points for the current device in the current device dataset. Represents the first in the current device dataset The current power corresponding to the current device data. Indicates the data collection interval; Based on the initial acquisition time, the previous operating state vector is identified. The previous operating state vector and the current energy consumption are added to the current device dataset to obtain device energy consumption data, which is used for energy consumption prediction.

3. The intelligent carbon emission optimization method based on a monitoring and management platform as described in claim 2, characterized in that, Before predicting the predicted energy consumption of the equipment based on equipment energy consumption data and a pre-built energy consumption prediction model, the method further includes: Identify the target device's data repository; Query historical energy consumption data of the target device based on the data repository; The monitoring area is functionally divided into multiple functional zones, and the target area where the target device is located is identified among these multiple functional zones. Identify the historical management cycle corresponding to the historical energy consumption data, and calculate the predicted management cycle based on the historical management cycle and the preset prediction interval; Based on the target area, an operation status vector is constructed, and the operation status vector is supplemented to the historical energy consumption data to obtain multi-device fusion data; Based on the predictive management cycle, query the actual device energy consumption in the data repository, and use the actual device energy consumption to label the multi-device fusion data to obtain labeled device data. The pre-constructed original prediction model is trained using labeled equipment data to obtain an energy consumption prediction model, wherein the energy consumption prediction model is used to predict equipment energy consumption and calculate the predicted equipment carbon emissions.

4. The intelligent carbon emission optimization method based on a monitoring and management platform as described in claim 3, characterized in that, The construction of the running state vector based on the target region includes: Obtain the set of devices in the same area within the target area, wherein the set of devices in the same area includes multiple devices in the same area, and the devices in the same area are in the same functional area as the target device; Based on the historical management cycle, the operating status of the equipment set in the same area is identified to obtain the operating status identifier set. The operating status identifier set includes multiple operating status identifiers, where the operating status identifier is a value of 0 or a value of 1. A value of 1 indicates that the equipment in the same area is in the operating state at the end of the historical management cycle, and a value of 0 indicates that the equipment in the same area is in the off state at the end of the historical management cycle. Construct a running status vector based on the running status identifier set.

5. The intelligent carbon emission optimization method based on a monitoring and management platform as described in claim 4, characterized in that, The process of applying external factor correction to the predicted carbon emission set to obtain the cumulative carbon emissions includes: Extract the functional areas sequentially from multiple functional areas; Based on the management cycle, external factors are statistically analyzed for functional areas to obtain a set of external impact parameters, which include: personnel density, outdoor temperature, indoor temperature, and solar irradiance. The set of external influence parameters is normalized to obtain the set of target influence parameters. A carbon emission correction model is constructed, and the target impact parameter set is input into the carbon emission correction model to obtain the correction ratio; Based on the functional area, the carbon emission set of the predicted equipment carbon emission set is identified, and the total regional emission is obtained by summing the regional carbon emission sets. The total regional emissions are corrected using the correction ratio to obtain the corrected carbon emissions; The corrected carbon emissions are summarized to obtain the corrected carbon emission set. The corrected carbon emission set is then summed to obtain the cumulative carbon emissions.

6. The intelligent carbon emission optimization method based on a monitoring and management platform as described in claim 5, characterized in that, The construction of the carbon emission correction model includes: Collect the historical predicted emissions set of the functional area, wherein the historical predicted emissions set includes multiple historical predicted emissions, and each historical predicted emissions corresponds to a different management cycle; Historical predicted emissions are extracted sequentially from the historical predicted emissions set; Obtain the emission management cycle of historical predicted emissions, and statistically analyze the historical external parameter set of the functional area within the emission management cycle. The historical external parameter set includes: historical population density, historical outdoor temperature, historical outdoor temperature and historical solar irradiance. A historical external parameter vector is constructed based on the historical external parameter set, and the actual carbon emissions are obtained according to the emission management cycle. The carbon emission ratio is calculated based on actual carbon emissions and historical predicted emissions. By summarizing the historical external parameter vectors and carbon emission ratios, we obtain the historical external parameter vector set and carbon emission ratio set. The training extrinsic parameter vector set is obtained by clustering and filtering based on the historical extrinsic parameter vector set. Identify the training proportion set based on the training extrinsic parameter vector set in the carbon emission proportion set; The training ratio set is paired with the training extrinsic parameter vector set to obtain the carbon emission training dataset. The carbon emission training dataset includes multiple carbon emission training data, and each carbon emission training data contains a training ratio and its corresponding training extrinsic parameter vector. A pre-built neural network is trained using a carbon emission training dataset to obtain a carbon emission correction model.

7. The intelligent carbon emission optimization method based on a monitoring and management platform as described in claim 6, characterized in that, The step of clustering and filtering based on historical extrinsic parameter vector sets to obtain a training extrinsic parameter vector set includes: Clustering the historical extrinsic parameter vector set yields multiple clustered extrinsic parameter vector sets; Extract cluster extrinsic parameter vector sets sequentially from multiple cluster extrinsic parameter vector sets; The number of cluster vectors in the cluster extrinsic parameter vector set is counted. If the number of cluster vectors is greater than the preset extreme number, the cluster extrinsic parameter vector set is recorded as the effective parameter vector set. The effective parameter vector set is summarized to obtain the training extrinsic parameter vector set.

8. The intelligent carbon emission optimization method based on a monitoring and management platform as described in claim 7, characterized in that, The process of constructing a fitness function based on the pre-simulated control action library, cumulative carbon emissions, and a preset baseline carbon emissions includes: Set the control action vector, which consists of multiple execution parameters; The number of control actions in the statistical control action vector is the same as the number of pre-simulated control data in the pre-simulated control action library; A fitness function is constructed based on the pre-simulated control action library, the number of control actions, the control action vector, the cumulative carbon emissions, and the baseline carbon emissions.

9. The intelligent carbon emission optimization method based on a monitoring and management platform as described in claim 8, characterized in that, The fitness function is expressed as follows: ， in, Represents the fitness function. This represents the preset mapping function. Represents the control action vector, This indicates the preset carbon emission weight. This indicates cumulative carbon emissions. Indicates baseline carbon emissions. Indicates the number of regulatory actions. The first element in the control action vector represents the... One execution parameter, The first element in the control action vector represents the... Each execution parameter corresponds to the carbon emission amount of the control action in the pre-simulated control action library. This indicates the preset weight of the number of adjustments.

10. A carbon emission intelligent optimization system based on a monitoring and management platform, characterized in that, The system includes: The target device determination module is used to receive carbon emission optimization instructions, determine the monitoring area based on the carbon emission optimization instructions, and obtain the set of devices to be optimized in the monitoring area. The set of devices to be optimized includes multiple devices to be optimized. Based on a pre-built IoT gateway, a preset energy consumption polling instruction is sent to the set of devices to be optimized to obtain the target device set. The target device set includes multiple target devices. The IoT gateway includes a protocol adaptation layer. The equipment energy consumption prediction module is used to sequentially extract target devices from the target device set, collect energy consumption data of the target devices, obtain equipment energy consumption data, and perform energy consumption prediction based on the equipment energy consumption data and the pre-built energy consumption prediction model to obtain the predicted equipment energy consumption. The carbon emission prediction module is used to calculate the carbon emission of the predicted equipment based on the preset power grid carbon emission factor and the energy consumption of the predicted equipment, summarize the carbon emission of the predicted equipment to obtain the carbon emission set of the predicted equipment, and perform external factor correction on the carbon emission set of the predicted equipment to obtain the cumulative carbon emission. The control action transmission module is used to acquire the pre-simulated control action library, which includes multiple pre-simulated control data, including pre-simulated control actions and carbon emissions of control actions. Based on the pre-simulated control action library, cumulative carbon emissions, and preset baseline carbon emissions, a fitness function is constructed. Carbon emission optimization is performed based on the fitness function to obtain the target optimization action group, and the target optimization action group is transmitted to the pre-built data management platform.

Images