Intelligent management method and system for carbon emission reduction of zero-carbon park

Abstract

The invention belongs to the technical field of carbon emission reduction, and discloses a carbon emission reduction intelligent management method and system for a zero-carbon park. Comprising the following steps: acquiring meteorological data, soil data and vegetation data in a park according to a preset period, preprocessing the data by adopting a Kalman filtering algorithm, and inputting the preprocessed data into an initial ecological system model; performing iterative optimization on the initial ecological system model by taking the carbon sequestration amount of each plant and the soil carbon sequestration amount of each region obtained in each preset period as reference amounts until a preset iteration period is reached so as to obtain a target biological system model; acquiring real-time meteorological data, real-time soil data and real-time vegetation data in the park, preprocessing the real-time meteorological data, the real-time soil data and the real-time vegetation data by adopting a Kalman filtering algorithm, and inputting the preprocessed data into the target ecological system model to dynamically predict the carbon sequestration of each plant and the carbon sequestration of each region in the park; and dynamically adjusting a carbon emission reduction strategy based on the predicted carbon sequestration amount of each plant and the predicted carbon sequestration amount of each region soil. According to the invention, rapid and effective realization of the zero-carbon park is promoted.

Description

Technical Field

[0001] The present invention relates to the technical field of carbon emission reduction, and in particular to a carbon emission reduction intelligent management method and system for a zero-carbon park. Background Art

[0002] A zero-carbon park refers to an industrial park where the total amount of carbon dioxide emissions generated are offset through various means within a preset time period, thereby achieving zero carbon dioxide emissions within the park.

[0003] In existing technologies, zero-carbon parks are mostly based on corresponding smart management platforms for carbon emission reduction, and are planned and designed around carbon emission reduction through the application of various advanced technologies. For example, clean energy facilities such as photovoltaic panels and wind turbines are deployed in the park to build a clean energy system to replace the traditional energy structure. Another example is to coordinate the comprehensive energy in the park and monitor the energy utilization in real time to optimize energy distribution. Another example is to consider green buildings and achieve the lowest energy consumption during construction and operation through green construction.

[0004] However, the above-mentioned smart carbon emission reduction management platform, which only considers carbon emission reduction from the perspective of energy, ignores the indispensable ecological carbon sink in the entire system, which makes it difficult to optimize the actual carbon emission reduction plan, and the technical implementation of the zero-carbon park is flawed, and ultimately can only achieve a near-zero-carbon park. Summary of the invention

[0005] The purpose of the present invention is to provide a smart management method and system for carbon emission reduction in a zero-carbon park, so as to improve the technical problem that the existing zero-carbon park implementation process only focuses on energy carbon emission reduction, which makes it difficult to achieve optimal carbon emission reduction planning.

[0006] To achieve the above object, the present invention proposes the following technical solutions:

[0007] In the first aspect, this technical solution provides a smart management method for carbon emission reduction in a zero-carbon park, including:

[0008] Acquire several batches of point cloud data corresponding to the vegetation in the park according to a preset period, pre-process each batch of point cloud data based on a single tree segmentation algorithm, and input a pre-constructed single tree biomass model, and then obtain the carbon sink of each plant in the vegetation in the park in each preset period through the biomass method based on the single tree biomass model;

[0009] The vegetation in the park is divided into periodic vegetation and evergreen vegetation. For the periodic vegetation, only the plant carbon sink when its biomass is the largest is considered;

[0010] Among them, based on a number of carbon dioxide sensors deployed along the vertical ground direction, the carbon dioxide concentration data in the vertical gradient direction within the preset vegetation area in the park is obtained, and then the data is used as a standard quantity to optimize the single tree biomass model;

[0011] According to the preset period, the soil carbon sequestration amount of each region in each preset period is obtained based on the soil carbon flux monitors deployed in each preset geographical area in the park;

[0012] Among them, in the process of obtaining the soil carbon sink in each region, firstly, the soil carbon flux monitors in the same preset geographical area are clustered based on the clustering algorithm; secondly, the mean of each soil carbon sink collected by each soil carbon flux detector in the same preset geographical area is used as the regional soil carbon sink in the corresponding preset geographical area, and the central coordinates of the preset geographical area are used as the collection coordinates corresponding to the regional soil carbon sink;

[0013] Among them, biomass carbon is pre-mixed in the soil of the park as an initial carbon sink;

[0014] Acquire meteorological data, soil data and vegetation data in the park according to a preset cycle, and use the Kalman filter algorithm to pre-process them and then input them into the initial ecosystem model, and use the carbon sink of each plant and the soil carbon sink of each region obtained in each preset cycle as a reference to iteratively optimize the initial ecosystem model until a preset iteration cycle is reached to obtain a target biological system model;

[0015] The meteorological data include: ambient temperature, air humidity, and solar radiation; the soil data include: soil texture, soil moisture, soil nutrient types, and the content of each soil nutrient type; the vegetation data include: leaf area index;

[0016] Acquire real-time meteorological data, real-time soil data and real-time vegetation data in the park, and use Kalman filter algorithm to pre-process them and then input them into the target ecosystem model to dynamically predict the carbon sequestration of each plant in the park and the carbon sequestration of each area of ​​soil;

[0017] Dynamically adjust the carbon emission reduction strategy based on the predicted carbon sequestration of each plant and the soil carbon sequestration of each region.

[0018] Further, including:

[0019] The weight of each waste in each recycling bin is obtained based on a pre-deployed pressure sensor, and then the recycling bin with a waste weight greater than a preset weight is selected as the target recycling bin;

[0020] Obtain the coordinates of each target recycling bin, and use the initial position of the recycling vehicle as the starting point to plan the waste recycling path based on the path planning algorithm;

[0021] Waste collection in each target recycling bin is carried out in sequence according to the planned waste recycling route.

[0022] Further, including:

[0023] Obtain water volume and quality data in each drainage channel within the park according to the preset cycle;

[0024] The water volume data is measured by a pre-deployed flow meter; the water quality data is obtained by water quality sampling and testing, including: dissolved matter type and content, suspended matter weight and content, heavy metal weight and content, organic matter weight and content;

[0025] Inputting the water quantity data and the water quality data into a pre-trained first machine learning model to obtain a water resource level in the park;

[0026] Based on the water resource level, the operation of relevant equipment in the park is dynamically adjusted.

[0027] Furthermore, the carbon reduction strategy is dynamically adjusted based on the predicted carbon sequestration of each plant and the carbon sequestration of each regional soil; including:

[0028] Obtain the power generation and load in the park in real time;

[0029] Inputting the power generation, load and predicted ecological carbon sink into a pre-trained second machine learning model to obtain real-time carbon emissions;

[0030] The operation of each device in the park is dynamically adjusted based on the carbon emissions.

[0031] Further, including:

[0032] When the actual energy consumption is judged to be greater than the preset energy consumption threshold, a carbon emission alarm is obtained;

[0033] The carbon emission warning includes: actual energy consumption, and the type of equipment with the highest energy consumption;

[0034] Based on the carbon emission alarm, reduce the usage rate or usage time of the equipment with the highest energy consumption;

[0035] When it is determined that the fluctuation frequency of the operating parameters of each device is greater than the preset fluctuation frequency threshold, an abnormal device alarm is obtained;

[0036] The device abnormality alarm includes: the device number of the abnormal fluctuation device, the abnormal fluctuation frequency, the abnormal fluctuation period, and the abnormal parameters;

[0037] Maintain the abnormal fluctuation equipment based on the equipment abnormal alarm, and forward the equipment abnormal alarm to the background control end;

[0038] Among them, during the equipment procurement process, avoid purchasing equipment of corresponding models whose abnormal alarm frequency of equipment is greater than the preset alarm frequency threshold.

[0039] Secondly, this technical solution provides a carbon emission reduction intelligent management system for a zero-carbon park, including:

[0040] The first acquisition module is used to acquire a number of batches of point cloud data corresponding to the vegetation in the park according to a preset period, and pre-process each batch of point cloud data based on a single tree segmentation algorithm, and input a pre-constructed single tree biomass model, and then obtain the carbon sink of each plant in the vegetation in the park in each preset period through a biomass method based on the single tree biomass model;

[0041] The vegetation in the park is divided into periodic vegetation and evergreen vegetation. For the periodic vegetation, only the plant carbon sink when its biomass is the largest is considered;

[0042] Among them, based on a number of carbon dioxide sensors deployed along the vertical ground direction, the carbon dioxide concentration data in the vertical gradient direction within the preset vegetation area in the park is obtained, and then the data is used as a standard quantity to optimize the single tree biomass model;

[0043] The second acquisition module is used to obtain the soil carbon sink amount of each region within each preset period based on the soil carbon flux monitors deployed in each preset geographical area in the park according to the preset period;

[0044] Among them, in the process of obtaining the soil carbon sink in each region, firstly, the soil carbon flux monitors in the same preset geographical area are clustered based on the clustering algorithm; secondly, the mean of each soil carbon sink collected by each soil carbon flux detector in the same preset geographical area is used as the regional soil carbon sink in the corresponding preset geographical area, and the central coordinates of the preset geographical area are used as the collection coordinates corresponding to the regional soil carbon sink;

[0045] Among them, biomass carbon is pre-mixed in the soil of the park as an initial carbon sink;

[0046] The third acquisition module is used to obtain meteorological data, soil data and vegetation data in the park according to a preset period, and use the Kalman filter algorithm to pre-process them and then input them into the initial ecosystem model, and use the carbon sink of each plant and the soil carbon sink of each region obtained in each preset period as a reference to iteratively optimize the initial ecosystem model until the preset iteration period is reached to obtain a target biological system model;

[0047] The meteorological data include: ambient temperature, air humidity, and solar radiation; the soil data include: soil texture, soil moisture, soil nutrient types, and the content of each soil nutrient type; the vegetation data include: leaf area index;

[0048] A carbon sink prediction module is used to obtain real-time meteorological data, real-time soil data and real-time vegetation data in the park, and use the Kalman filter algorithm to pre-process them and then input them into the target ecosystem model to dynamically predict the carbon sink of each plant in the park and the carbon sink of each area of ​​soil;

[0049] The strategy adjustment module is used to dynamically adjust the carbon reduction strategy based on the predicted carbon sequestration of each plant and the soil carbon sequestration of each region.

[0050] Further, including:

[0051] A fourth acquisition module is used to acquire the weight of each waste in each recycling bin based on a pre-deployed pressure sensor, and then screen out a recycling bin with a waste weight greater than a preset weight as a target recycling bin;

[0052] The path planning module is used to obtain the coordinate position of each target recycling bin, and use the initial position of the recycling vehicle as the starting point to plan the waste recycling path according to the path planning algorithm;

[0053] The waste recycling module is used to recycle the waste in each target recycling bin in sequence according to the planned waste recycling path.

[0054] Further, including:

[0055] The fifth acquisition module is used to obtain water volume data and water quality data in each drainage channel in the park according to a preset period;

[0056] The water volume data is measured by a pre-deployed flow meter; the water quality data is obtained by water quality sampling and testing, including: dissolved matter type and content, suspended matter weight and content, heavy metal weight and content, organic matter weight and content;

[0057] A sixth acquisition module, used for inputting the water quantity data and the water quality data into a pre-trained first machine learning model to obtain the water resource level in the park;

[0058] The equipment adjustment module is used to dynamically adjust the operation of various related equipment in the park based on the water resource level.

[0059] In a third aspect, the technical solution provides an electronic device, comprising at least one processor, wherein the processor is coupled to a memory, wherein a computer program is stored in the memory, and wherein the computer program is configured to execute the method described when executed by the processor.

[0060] In a fourth aspect, the present technical solution provides a computer-readable storage medium having a computer program stored thereon, and the computer program implements the described method when executed by a computer.

[0061] Beneficial effects:

[0062] It can be seen from the above technical solutions that the technical solution of the present invention provides a smart management method for carbon emission reduction in a zero-carbon park to improve the technical defect that the carbon emission reduction planning of the existing zero-carbon park is difficult to achieve optimization.

[0063] Specifically, this embodiment first constructs a single tree biomass model by collecting point cloud data, and introduces the biomass method to obtain plant carbon sinks. In this process, the vegetation is classified, and the single tree biomass model is optimized using the vertical gradient of carbon dioxide concentration, so as to improve the accuracy of the obtained plant carbon sink. Secondly, the regional soil carbon sink is obtained through a soil carbon flux monitor, and a clustering algorithm is introduced in the process to improve the accuracy of the acquisition of regional soil carbon sinks. Then, using them as reference quantities, the initial ecosystem model is iteratively optimized to obtain a target biological system model. At this point, various types of carbon sinks can be predicted based on the target biological system model through various types of IoT sensor parameters obtained in real time. Thereby quickly and reliably assisting the dynamic adjustment of carbon emission reduction strategies and promoting the construction of zero-carbon parks.

[0064] It should be appreciated that all combinations of the foregoing concepts, as well as additional concepts described in greater detail below, may be considered to be part of the inventive subject matter of the present disclosure, provided such concepts are not mutually inconsistent.

[0065] The foregoing and other aspects, embodiments and features of the present invention can be more fully understood from the following description in conjunction with the accompanying drawings. Other additional aspects of the present invention, such as the features and / or beneficial effects of the exemplary embodiments, will be apparent from the following description or learned from the practice of the specific embodiments according to the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] The drawings are not intended to be drawn to scale. In the drawings, each identical or nearly identical component shown in various figures may be represented by the same reference numeral. For clarity, not every component is labeled in every figure. Embodiments of various aspects of the present invention will now be described by way of example and with reference to the accompanying drawings, in which:

[0067] Figure 1 This is a flow chart of the carbon emission reduction intelligent management method for the zero-carbon park described in this embodiment;

[0068] Figure 2 Flow chart for optimizing the single tree biomass model for this embodiment;

[0069] Figure 3 This is a flow chart for obtaining regional soil carbon sinks in this embodiment;

[0070] Figure 4 A flowchart for dynamically adjusting equipment in this embodiment;

[0071] Figure 5 This is a flowchart of abnormal alarm for this embodiment;

[0072] Figure 6 This is a flow chart of waste recycling in this embodiment;

[0073] Figure 7 This is a flow chart of water resource recovery in this embodiment;

[0074] Figure 8 This is a structural block diagram of the carbon emission reduction intelligent management system for the zero-carbon park described in this embodiment;

[0075] Fig. 9 is a structural block diagram of the electronic device described in this embodiment. DETAILED DESCRIPTION

[0076] In order to make the purpose, technical solution and advantages of the embodiment of the present invention clearer, the technical solution of the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings of the embodiment of the present invention. Obviously, the described embodiment is a part of the embodiment of the present invention, not all of the embodiments. Based on the described embodiment of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Unless otherwise defined, the technical terms or scientific terms used herein should be the common meaning understood by people with general skills in the field to which the present invention belongs.

[0077] The words "first", "second" and similar words used in the specification and claims of this application do not indicate any order, quantity or importance, but are only used to distinguish different components. Similarly, unless the context clearly indicates otherwise, the singular form of "a", "an" or "the" and other similar words do not indicate a quantitative limitation, but rather indicate the presence of at least one. Words such as "include" or "comprise" and the like mean that the elements or objects appearing before "include" or "comprise" cover the features, wholes, steps, operations, elements and / or components listed after "include" or "comprise", and do not exclude the existence or addition of one or more other features, wholes, steps, operations, elements, components and / or their collections. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0078] A zero-carbon park refers to an industrial park where the total amount of carbon dioxide emissions generated are offset through various means within a preset time period, thereby achieving zero carbon dioxide emissions within the park.

[0079] In the prior art, most zero-carbon parks are based on corresponding smart carbon emission reduction management platforms, and are planned and designed around energy carbon emission reduction through the application of a variety of advanced technologies, but ignore the indispensable ecological carbon sink in the entire system, which makes it difficult to optimize the actual carbon emission reduction plan. The technical implementation of zero-carbon parks has flaws, and ultimately can only achieve near-zero-carbon parks. Based on this, this embodiment aims to provide a smart carbon emission reduction management method for zero-carbon parks to improve the above technical defects.

[0080] The carbon emission reduction intelligent management method for the zero-carbon park described in this embodiment is specifically introduced below in conjunction with the accompanying drawings.

[0081] In order to implement this method, from the perspective of the Internet of Things, the corresponding hardware platform is built based on the following framework. It includes: basic layer, data layer, service layer, application layer, and presentation layer. Among them, the basic layer, as the underlying data support, is responsible for data collection, protocol conversion and data isolation to realize data communication between systems. It can collect data from multiple systems such as photovoltaics, wind farms, energy storage, and various energy-consuming equipment. The data layer processes, analyzes, and stores the collected data. Use big data technology to reveal data patterns and trends and provide support for upper-level services and applications. The service layer supports the intelligent management of comprehensive energy and carbon monitoring in the park with technical capabilities (such as integrated tools, analysis tools, model tools, etc.), conducts data mining, multi-dimensional statistical analysis, and regularly updates the results to the database. The application layer is based on platform capabilities and intuitively presents the practical value of each model and function to the user on demand. The presentation layer presents the various applications of the platform in three dimensions in a diversified interface form, such as large screens, workstations, mobile terminals, etc.

[0082] At this time, based on the above platform architecture, combined with Figure 1 As shown, the method includes:

[0083] Step S102, obtaining several batches of point cloud data corresponding to the vegetation in the park according to a preset period, and preprocessing each batch of point cloud data based on a single tree segmentation algorithm, and inputting a pre-constructed single tree biomass model, and then obtaining the carbon sink of each plant in the vegetation in the park in each preset period through the biomass method based on the single tree biomass model.

[0084] In the specific implementation, the point cloud data is acquired based on the laser radars pre-deployed at different locations and heights in the park. Specifically, the point cloud data includes: tree height, crown width, leaf area index, etc. For the vegetation in the park, it is divided into periodic vegetation and evergreen vegetation. For the periodic vegetation, considering that the carbon sink of the vegetation after death will re-enter the carbon circle, it is only calculated once. Specifically, only the carbon sink of plants when its biomass is the largest is considered; and the carbon sink replanted after the periodic vegetation dies is no longer recalculated. And in the specific implementation, the baseline is set to zero. At this time, the plant carbon sink obtained in the periodic calculation process is the net carbon sink.

[0085] In specific implementation, combined with Figure 2 As shown, in order to improve the accuracy of plant carbon sinks obtained based on the single tree biomass model, the single tree biomass model is optimized by the following method:

[0086] Step S10202: Acquire carbon dioxide concentration data in a vertical gradient direction within a preset vegetation area in the park based on a plurality of carbon dioxide sensors deployed in a direction perpendicular to the ground.

[0087] Step S10204: Optimize the single tree biomass model using the carbon dioxide concentration data in the vertical gradient direction as a standard quantity.

[0088] Step S104: obtaining the soil carbon sink amount of each region within each preset period based on the soil carbon flux monitors deployed in each preset geographical area in the park according to the preset period.

[0089] Specific, combined Figure 3 As shown in the figure, the soil carbon sink in each region is obtained by the following method:

[0090] Step S10402: clustering the soil carbon flux monitors in the same preset geographical area based on a clustering algorithm.

[0091] Step S10404: taking the average of the soil carbon sinks collected by the soil carbon flux detectors in the same preset geographical area as the regional soil carbon sink in the corresponding preset geographical area, and taking the center coordinates of the preset geographical area as the collection coordinates corresponding to the regional soil carbon sink.

[0092] At this time, the introduction of the clustering algorithm based on steps S10402 to S10404 can effectively improve the reliability of the soil carbon sequestration amount in each region that is finally calculated.

[0093] In the specific implementation, biomass carbon is mixed in the soil as the initial carbon sink reserve. When biochar is added to the soil, it can absorb organic carbon in the soil and prevent it from being decomposed by microorganisms and released back into the atmosphere, thereby playing a role in carbon fixation. At the same time, biochar itself is a stable form of carbon, and its production process is equivalent to fixing the carbon in biomass. This part of the carbon sink is entered into the platform through quantitative calculation.

[0094] Step S106, obtaining meteorological data, soil data and vegetation data in the park according to a preset period, and using the Kalman filter algorithm to pre-process them and then input them into the initial ecosystem model, and using the carbon sink of each plant and the soil carbon sink of each region obtained in each preset period as a reference to iteratively optimize the initial ecosystem model until the preset iteration period is reached to obtain a target biological system model.

[0095] In specific implementation, the meteorological data includes: ambient temperature, air humidity, and solar radiation. The soil data includes: soil texture, soil moisture, soil nutrient types, and the content of each soil nutrient type. The vegetation data includes: leaf area index.

[0096] At this point, by continuously calibrating and verifying the acquired target biological system model, real-time estimation and prediction of the park's ecological carbon sink can be achieved. At the same time, the Kalman filter data assimilation method is used to combine the model simulation results with the actual observation data, optimize the model parameters, improve the accuracy and reliability of the target biological system model, and more accurately evaluate the carbon sink dynamics of the park's vegetation. Specifically, proceed as follows:

[0097] Step S108, obtaining real-time meteorological data, real-time soil data and real-time vegetation data in the park, and pre-processing them using the Kalman filter algorithm and then inputting them into the target ecosystem model to dynamically predict the carbon sink of each plant in the park and the carbon sink of each area of ​​soil.

[0098] Step S110: dynamically adjust the carbon emission reduction strategy based on the predicted carbon sequestration of each plant and the predicted carbon sequestration of each regional soil.

[0099] Specific, combined Figure 4 As shown, step S110 is specifically implemented through the following process:

[0100] Step S11002: Obtain the power generation and load in the park in real time.

[0101] In the specific implementation, various intelligent devices on the terminal are used to collect data on the production, consumption, storage, transmission, etc. of various energy sources in real time, such as photovoltaic power generation, carbon sink, heat output, hot water consumption, charging capacity, energy storage charging and discharging status, power quality parameters, steam flow, boiler operation parameters, etc. The collected multi-temporal, multi-dimensional, and multi-scale data are integrated, cleaned, and processed, including data format conversion, outlier processing, missing value filling, etc. Through data processing, the quality and availability of data are improved, providing a reliable foundation for subsequent data analysis.

[0102] Step S11004: input the power generation, load and predicted ecological carbon sink into a pre-trained second machine learning model to obtain real-time carbon emissions.

[0103] The machine learning algorithm corresponding to the second machine learning model may be transfer learning, small sample, zero sample, self-supervision, weak supervision, semi-supervision, unsupervised and active learning algorithms. At the same time, as a more preferred implementation, in the training process of the second machine learning model, the park area, population, facility construction, and energy consumption characteristics are also introduced to improve the accuracy of carbon emission prediction.

[0104] More specifically, the prediction of carbon emissions mainly includes two aspects: one is to make interval prediction through energy consumption (i.e. based on the energy consumption prediction value multiplied by the relevant carbon emission factor); the other is to monitor the direct carbon emissions in the park and make predictions through the analysis of historical data.

[0105] Step S11006: Dynamically adjust the operation of each device in the park based on the carbon emissions.

[0106] Specifically, based on the analysis of the park's energy demand and energy supply, through AI algorithms and equipment mechanism models, the park's energy storage efficiency and energy utilization efficiency are autonomously optimized to achieve deep carbon reduction. On the one hand, in the process of energy supply in the park, the reactive power compensation system and energy storage system based on big data further optimize the park's energy storage efficiency, reduce energy loss, and promote a significant improvement in the resilience and flexibility of the park's energy supply system. On the other hand, the energy efficiency of each energy system equipment (such as transformers, pipelines, etc.) is diagnosed, inefficient equipment and unreasonable operating modes are identified, and energy-saving transformation or operation strategy optimization suggestions are proposed. At the same time, the overall energy efficiency of each energy system (power distribution, steam, energy storage, etc.) is analyzed, including system operating efficiency, transmission and distribution system losses, energy consumption characteristics of terminal energy-consuming equipment, etc., to discover energy-saving opportunities at the system level.

[0107] Furthermore, the second machine learning model can also be loaded into the geographic scenario model of the park, so that the carbon emissions generated by each enterprise in the park can be displayed regionally. It can also show the direct carbon sources of high-carbon emission enterprises in the park and the high-carbon emission equipment or products within the enterprises, providing direction for subsequent carbon reduction and emission reduction work.

[0108] In order to deal with abnormal carbon emissions in the park, based on the energy consumption targets set in the park, through analysis and prediction of the collected data, big data analysis and machine learning technology are used to identify abnormal fluctuations in energy consumption, quickly locate faulty equipment or unreasonable energy use behaviors, and promptly troubleshoot or adjust energy use. If the energy consumption forecast reaches the set energy consumption target, an early warning is activated to prompt the park to reduce the use of energy-consuming equipment. Similarly, the carbon emission early warning is also based on the set target, and the direct carbon emission data and indirect carbon emission data are analyzed comprehensively. If the set target value is reached, an early warning is activated. At the same time, analysis suggestions are given to determine whether it is more beneficial to reduce carbon emissions from direct carbon emission sources or from indirect sources. Specifically, combined with Figure 5 As shown, the following steps are included:

[0109] Step S202: When it is determined that the actual energy consumption is greater than a preset energy consumption threshold, a carbon emission alarm is obtained.

[0110] Specifically, the carbon emission alarm includes: actual energy consumption, and the type of equipment with the highest energy consumption.

[0111] Step S204: reducing the usage rate or usage duration of the device with the highest energy consumption based on the carbon emission alarm.

[0112] Step S206: When it is determined that the fluctuation frequency of the operating parameters of each device is greater than a preset fluctuation frequency threshold, an equipment abnormality alarm is obtained.

[0113] In specific implementation, the device abnormality alarm includes: the device number of the abnormal fluctuation device, the abnormal fluctuation frequency, the abnormal fluctuation period, and the abnormal parameters. Specifically, the corresponding abnormal fluctuations include voltage fluctuations, abnormal current, temperature rise, high pressure, etc., which can reveal potential fault signs or abnormal operation conditions of the equipment in advance.

[0114] Step S208: Maintain the abnormal fluctuation device based on the device abnormal alarm, and forward the device abnormal alarm to the background control end.

[0115] During the equipment procurement process, avoid purchasing equipment of corresponding models whose abnormal alarm frequency is greater than the preset alarm frequency threshold.

[0116] This embodiment also includes corresponding resource recycling solutions to further assist in the realization of a zero-carbon park.

[0117] Specific, combined Figure 6 As shown, solid waste recycling is carried out in the following ways:

[0118] Step S302: obtaining the weight of each waste in each recycling bin based on the pre-deployed pressure sensor, and then screening out the recycling bin whose waste weight is greater than the preset weight as the target recycling bin.

[0119] Step S304: Obtain the coordinate position of each target recycling bin, and use the initial position of the recycling vehicle as the starting point to perform waste recycling path planning according to the path planning algorithm.

[0120] In this embodiment, the path planning algorithm is specifically an RRT algorithm.

[0121] Step S306: Recycling the waste in each target recycling bin in sequence according to the planned waste recycling path.

[0122] Specific, combined Figure 7 As shown, water resources are recycled and utilized in the following ways:

[0123] Step S402: Acquire water volume data and water quality data in each drainage channel in the park according to a preset period.

[0124] In specific implementation, the water volume data is measured by a pre-deployed flow meter. The water quality data is obtained by water quality sampling and testing, including: dissolved matter type and content, suspended matter weight and content, heavy metal weight and content, organic matter weight and content.

[0125] Step S404: input the water quantity data and the water quality data into a pre-trained first machine learning model to obtain the water resource level in the park.

[0126] The water quality level described in this embodiment specifically refers to the quality level of water resources.

[0127] Step S406: Dynamically adjust the operation of relevant equipment in the park based on the water resource level.

[0128] Specifically, based on the water resource level results output by the model, more reasonable water resource management strategies can be formulated, such as adjusting the proportion of recycled water reuse and optimizing sewage treatment processes.

[0129] At the same time, in order to control water conservation in some water-intensive scenes and equipment, the actual reuse water rate of each enterprise is regularly obtained on a company-by-company basis. When the actual reuse water rate is lower than the preset reuse rate threshold, a water conservation alarm is sent to the client of the relevant enterprise to remind it to conserve water. This reduces carbon emissions in the subsequent water treatment process. The actual reuse water rate is the proportion of recycled water used by the corresponding enterprise in the total water consumption.

[0130] From the above, it can be seen that the method described in this embodiment adopts a layered architecture design to adapt to multi-level energy management needs. Through the coordinated scheduling of electricity, cold, heat, gas and steam and source, grid, load and storage, big data and intelligent technology are used to realize the functions of source-load two-way prediction, intelligent regulation, energy flow-carbon flow analysis, intelligent diagnosis and early warning. At the same time, on the basis of the energy-carbon solution, a resource recycling and utilization solution and an ecological carbon sink monitoring solution are designed to be added. Combining energy and carbon emission reduction from the perspective of resource recycling and ecological carbon sink, it helps to make carbon emission monitoring in zero-carbon parks more accurate.

[0131] The above program can be run in a processor, or it can also be stored in a memory (or referred to as a computer-readable storage medium), and the computer-readable medium includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. According to the definition in this embodiment, computer-readable media does not include temporary computer-readable media, such as modulated data signals and carriers.

[0132] These computer programs can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps of the functions specified in one or more blocks can be implemented by different modules corresponding to different steps.

[0133] Based on this, this embodiment also provides a carbon emission reduction intelligent management system for a zero-carbon park. Figure 8 As shown, the system includes the following functional modules:

[0134] The first acquisition module is used to acquire several batches of point cloud data corresponding to the vegetation in the park according to a preset period, and pre-process each batch of point cloud data based on a single tree segmentation algorithm, and input a pre-constructed single tree biomass model, and then obtain the carbon sink of each plant in the vegetation in the park in each preset period through the biomass method based on the single tree biomass model.

[0135] The vegetation in the park is divided into periodic vegetation and evergreen vegetation. For the periodic vegetation, only the plant carbon sink when its biomass is the largest is considered.

[0136] Among them, based on a number of carbon dioxide sensors deployed along the vertical ground direction, the carbon dioxide concentration data in the vertical gradient direction of the preset vegetation area in the park is obtained, and then it is used as a standard quantity to optimize the single tree biomass model.

[0137] The second acquisition module is used to obtain the soil carbon sink amount in each area within each preset period based on the soil carbon flux monitors deployed in each preset geographical area in the park according to the preset period.

[0138] Among them, in the process of obtaining the soil carbon sink in each region, firstly, the soil carbon flux monitors in the same preset geographical area are clustered based on the clustering algorithm; secondly, the mean of the soil carbon sinks collected by the soil carbon flux detectors in the same preset geographical area is used as the regional soil carbon sink in the corresponding preset geographical area, and the center coordinates of the preset geographical area are used as the collection coordinates corresponding to the regional soil carbon sink.

[0139] Among them, biomass carbon is pre-mixed in the soil within the park as an initial carbon sink.

[0140] The third acquisition module is used to obtain the meteorological data, soil data and vegetation data in the park according to a preset period, and use the Kalman filter algorithm to pre-process them and then input them into the initial ecosystem model, and use the carbon sink of each plant and the soil carbon sink of each region obtained in each preset period as a reference to iteratively optimize the initial ecosystem model until the preset iteration period is reached to obtain a target biological system model.

[0141] The meteorological data include: ambient temperature, air humidity, and solar radiation; the soil data include: soil texture, soil moisture, soil nutrient types, and the content of each soil nutrient type; the vegetation data include: leaf area index.

[0142] The carbon sink prediction module is used to obtain real-time meteorological data, real-time soil data and real-time vegetation data in the park, and use the Kalman filter algorithm to pre-process them and then input them into the target ecosystem model to dynamically predict the carbon sink of each plant in the park and the carbon sink of each area of ​​soil.

[0143] The strategy adjustment module is used to dynamically adjust the carbon reduction strategy based on the predicted carbon sequestration of each plant and the soil carbon sequestration of each region.

[0144] Since the system is built based on the method, what has been described above will not be repeated here.

[0145] For example, the system further comprises:

[0146] The fourth acquisition module is used to acquire the weight of each waste in each recycling bin based on the pre-deployed pressure sensor, and then screen out the recycling bin whose waste weight is greater than the preset weight as the target recycling bin.

[0147] The path planning module is used to obtain the coordinate position of each target recycling bin, and use the initial position of the recycling vehicle as the starting point to plan the waste recycling path based on the path planning algorithm.

[0148] The waste recycling module is used to recycle the waste in each target recycling bin in sequence according to the planned waste recycling path.

[0149] For another example, the system further includes:

[0150] The fifth acquisition module is used to obtain the water volume data and water quality data in each drainage channel in the park according to a preset period.

[0151] Among them, the water volume data is measured by a pre-deployed flow meter; the water quality data is obtained by water quality sampling and testing, including: type and content of dissolved matter, weight and content of suspended matter, weight and content of heavy metals, weight and content of organic matter.

[0152] The sixth acquisition module is used to input the water quantity data and the water quality data into a pre-trained first machine learning model to obtain the water resource level in the park.

[0153] The equipment adjustment module is used to dynamically adjust the operation of various related equipment in the park based on the water resource level.

[0154] Combination Fig. 9 As shown, this embodiment further provides an electronic device, including at least one processor, wherein the processor is coupled to a memory, wherein a computer program is stored in the memory, and wherein the computer program is configured to execute the method when executed by the processor.

[0155] At the same time, this embodiment also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a computer, the method described above is implemented.

[0156] Since the system, the electronic device and the computer-readable storage medium are all built based on the method, or are used to implement the method, in actual application, the construction of a zero-carbon park can be achieved efficiently and reliably.

[0157] Although the present invention has been disclosed as above with preferred embodiments, it is not intended to limit the present invention. A person with ordinary knowledge in the technical field to which the present invention belongs may make various changes and modifications without departing from the spirit and scope of the present invention. Therefore, the protection scope of the present invention shall be determined by the definition of the claims.

Claims

1. A carbon emission reduction intelligent management method for a zero-carbon park, characterized in that: include: Acquire several batches of point cloud data corresponding to the vegetation in the park according to a preset period, pre-process each batch of point cloud data based on a single tree segmentation algorithm, and input a pre-constructed single tree biomass model, and then obtain the carbon sink of each plant in the vegetation in the park in each preset period through the biomass method based on the single tree biomass model; The vegetation in the park is divided into periodic vegetation and evergreen vegetation. For the periodic vegetation, only the plant carbon sink when its biomass is the largest is considered; Among them, based on a number of carbon dioxide sensors deployed along the vertical ground direction, the carbon dioxide concentration data in the vertical gradient direction within the preset vegetation area in the park is obtained, and then the data is used as a standard quantity to optimize the single tree biomass model; According to the preset period, the soil carbon sequestration amount of each region in each preset period is obtained based on the soil carbon flux monitors deployed in each preset geographical area in the park; Among them, in the process of obtaining the soil carbon sink in each region, firstly, the soil carbon flux monitors in the same preset geographical area are clustered based on the clustering algorithm; secondly, the mean of each soil carbon sink collected by each soil carbon flux detector in the same preset geographical area is used as the regional soil carbon sink in the corresponding preset geographical area, and the central coordinates of the preset geographical area are used as the collection coordinates corresponding to the regional soil carbon sink; Among them, biomass carbon is pre-mixed in the soil of the park as an initial carbon sink; Acquire meteorological data, soil data and vegetation data in the park according to a preset cycle, and use the Kalman filter algorithm to pre-process them and then input them into the initial ecosystem model, and use the carbon sink of each plant and the soil carbon sink of each region obtained in each preset cycle as a reference to iteratively optimize the initial ecosystem model until a preset iteration cycle is reached to obtain a target biological system model; The meteorological data include: ambient temperature, air humidity, and solar radiation; the soil data include: soil texture, soil moisture, soil nutrient types, and the content of each soil nutrient type; the vegetation data include: leaf area index; Acquire real-time meteorological data, real-time soil data and real-time vegetation data in the park, and use Kalman filter algorithm to pre-process them and then input them into the target ecosystem model to dynamically predict the carbon sequestration of each plant in the park and the carbon sequestration of each area of ​​soil; Dynamically adjust the carbon emission reduction strategy based on the predicted carbon sequestration of each plant and the soil carbon sequestration of each region.

2. The carbon emission reduction intelligent management method for a zero-carbon park according to claim 1 is characterized in that: include: The weight of each waste in each recycling bin is obtained based on a pre-deployed pressure sensor, and then the recycling bin with a waste weight greater than a preset weight is selected as the target recycling bin; Obtain the coordinates of each target recycling bin, and use the initial position of the recycling vehicle as the starting point to plan the waste recycling path based on the path planning algorithm; Waste collection in each target recycling bin is carried out in sequence according to the planned waste recycling route.

3. The carbon emission reduction intelligent management method for a zero-carbon park according to claim 1 is characterized in that: include: Obtain water volume and quality data in each drainage channel within the park according to the preset cycle; The water volume data is measured by a pre-deployed flow meter; the water quality data is obtained by water quality sampling and testing, including: dissolved matter type and content, suspended matter weight and content, heavy metal weight and content, organic matter weight and content; Inputting the water quantity data and the water quality data into a pre-trained first machine learning model to obtain a water resource level in the park; Based on the water resource level, the operation of relevant equipment in the park is dynamically adjusted.

4. The carbon emission reduction intelligent management method for a zero-carbon park according to claim 1 is characterized in that: The carbon reduction strategy is dynamically adjusted based on the predicted carbon sequestration of each plant and the soil carbon sequestration of each region; including: Obtain the power generation and load in the park in real time; Inputting the power generation, load and predicted ecological carbon sink into a pre-trained second machine learning model to obtain real-time carbon emissions; The operation of each device in the park is dynamically adjusted based on the carbon emissions.

5. The carbon emission reduction intelligent management method for a zero-carbon park according to claim 1 is characterized in that: include: When the actual energy consumption is judged to be greater than the preset energy consumption threshold, a carbon emission alarm is obtained; The carbon emission warning includes: actual energy consumption, and the type of equipment with the highest energy consumption; Based on the carbon emission alarm, reduce the usage rate or usage time of the equipment with the highest energy consumption; When it is determined that the fluctuation frequency of the operating parameters of each device is greater than the preset fluctuation frequency threshold, an abnormal device alarm is obtained; The device abnormality alarm includes: the device number of the abnormal fluctuation device, the abnormal fluctuation frequency, the abnormal fluctuation period, and the abnormal parameters; Maintain the abnormal fluctuation equipment based on the equipment abnormal alarm, and forward the equipment abnormal alarm to the background control end; Among them, during the equipment procurement process, avoid purchasing equipment of corresponding models whose abnormal alarm frequency of equipment is greater than the preset alarm frequency threshold.

6. A carbon emission reduction intelligent management system for a zero-carbon park, characterized in that: include: The first acquisition module is used to acquire a number of batches of point cloud data corresponding to the vegetation in the park according to a preset period, and pre-process each batch of point cloud data based on a single tree segmentation algorithm, and input a pre-constructed single tree biomass model, and then obtain the carbon sink of each plant in the vegetation in the park in each preset period through a biomass method based on the single tree biomass model; The vegetation in the park is divided into periodic vegetation and evergreen vegetation. For the periodic vegetation, only the plant carbon sink when its biomass is the largest is considered; Among them, based on a number of carbon dioxide sensors deployed along the vertical ground direction, the carbon dioxide concentration data in the vertical gradient direction within the preset vegetation area in the park is obtained, and then the data is used as a standard quantity to optimize the single tree biomass model; The second acquisition module is used to obtain the soil carbon sink amount of each region within each preset period based on the soil carbon flux monitors deployed in each preset geographical area in the park according to the preset period; Among them, in the process of obtaining the soil carbon sink in each region, firstly, the soil carbon flux monitors in the same preset geographical area are clustered based on the clustering algorithm; secondly, the mean of each soil carbon sink collected by each soil carbon flux detector in the same preset geographical area is used as the regional soil carbon sink in the corresponding preset geographical area, and the central coordinates of the preset geographical area are used as the collection coordinates corresponding to the regional soil carbon sink; Among them, biomass carbon is pre-mixed in the soil of the park as an initial carbon sink; The third acquisition module is used to obtain meteorological data, soil data and vegetation data in the park according to a preset period, and use the Kalman filter algorithm to pre-process them and then input them into the initial ecosystem model, and use the carbon sink of each plant and the soil carbon sink of each region obtained in each preset period as a reference to iteratively optimize the initial ecosystem model until the preset iteration period is reached to obtain a target biological system model; The meteorological data include: ambient temperature, air humidity, and solar radiation; the soil data include: soil texture, soil moisture, soil nutrient types, and the content of each soil nutrient type; the vegetation data include: leaf area index; A carbon sink prediction module is used to obtain real-time meteorological data, real-time soil data and real-time vegetation data in the park, and use the Kalman filter algorithm to pre-process them and then input them into the target ecosystem model to dynamically predict the carbon sink of each plant in the park and the carbon sink of each area of ​​soil; The strategy adjustment module is used to dynamically adjust the carbon reduction strategy based on the predicted carbon sequestration of each plant and the soil carbon sequestration of each region.

7. The carbon emission reduction intelligent management system for a zero-carbon park according to claim 6 is characterized in that: include: A fourth acquisition module is used to acquire the weight of each waste in each recycling bin based on a pre-deployed pressure sensor, and then screen out a recycling bin with a waste weight greater than a preset weight as a target recycling bin; The path planning module is used to obtain the coordinate position of each target recycling bin, and use the initial position of the recycling vehicle as the starting point to plan the waste recycling path according to the path planning algorithm; The waste recycling module is used to recycle the waste in each target recycling bin in sequence according to the planned waste recycling path.

8. The carbon emission reduction intelligent management system for a zero-carbon park according to claim 6 is characterized in that: include: The fifth acquisition module is used to obtain water volume data and water quality data in each drainage channel in the park according to a preset period; The water volume data is measured by a pre-deployed flow meter; the water quality data is obtained by water quality sampling and testing, including: dissolved matter type and content, suspended matter weight and content, heavy metal weight and content, organic matter weight and content; A sixth acquisition module, used for inputting the water quantity data and the water quality data into a pre-trained first machine learning model to obtain the water resource level in the park; The equipment adjustment module is used to dynamically adjust the operation of various related equipment in the park based on the water resource level.

9. An electronic device, characterized in that: The method comprises at least one processor, wherein the processor is coupled to a memory, wherein a computer program is stored in the memory, and wherein the computer program is configured to execute the method according to any one of claims 1 to 5 when executed by the processor.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a computer, the method according to any one of claims 1 to 5 is implemented.

Images