Zero-carbon high-speed energy-saving carbon-reducing dynamic sensing intelligent monitoring device

Abstract

The invention discloses a zero-carbon high-speed energy-consumption carbon-reduction dynamic sensing intelligent monitoring device, and relates to the technical field of intelligent monitoring analysis, and the device comprises a dynamic sensing unit which is used for collecting energy use data and carbon emission data of a highway in real time based on a pre-arranged multi-source sensor, and transmitting the energy use data and the carbon emission data to a central processing unit; the energy use data and the carbon emission data are transmitted to the dynamic sensing unit; the data processing unit is used for receiving the energy use data and the carbon emission data, performing energy consumption analysis, carbon emission calculation and energy-saving optimization analysis on the energy use data and the carbon emission data, and generating a carbon reduction optimization scheme and an energy-saving and emission-reducing suggestion; and the display unit provides a display interface for the user, and displays the analysis result in real time by using charts and reports. According to the invention, the energy consumption and carbon emission capability of the expressway can be monitored in real time, an energy conservation and emission reduction optimization suggestion is automatically generated by using a built-in intelligent monitoring algorithm, and the management level of energy conservation and emission reduction of the expressway is remarkably improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent monitoring and analysis technology, and in particular to a dynamic perception intelligent monitoring device for zero-carbon high-speed energy use and carbon reduction. Background Art

[0002] As global climate change and environmental pollution become increasingly serious, energy conservation and emission reduction have become the focus of attention of all countries. As an important transportation infrastructure, the impact of highway energy consumption and carbon emissions on the environment cannot be ignored. Therefore, how to effectively monitor and manage highway energy consumption and carbon emissions has become an important research topic.

[0003] At present, there are some devices on the market for monitoring highway energy consumption and carbon emissions. The typical solution is usually composed of sensors, data acquisition devices, transmission systems and data display terminals. The various parts work together to realize data collection, transmission, processing and display: energy consumption and carbon emission data are collected by various sensors installed on the highway, and the collected data are transmitted to the central processing system using wired or wireless communication technology. The central processing system stores and analyzes the received data, generates corresponding monitoring reports, and displays the processed monitoring data through computers, mobile phones and other terminals. Users can view real-time data and historical records.

[0004] However, due to the limitations of sensor technology, existing technologies often lack monitoring accuracy and cannot accurately reflect the actual energy consumption and emissions of highways. First, there is often a delay in data processing in existing technologies, which cannot achieve true real-time monitoring, affecting the timeliness of management and decision-making; second, existing technologies mostly rely on manual analysis, lack intelligent data processing and analysis functions, and cannot provide in-depth energy conservation and emission reduction optimization suggestions; in addition, some devices are prone to failure when operating in complex highway environments, affecting the monitoring effect, and the user interface design is not friendly enough, and the data display is complex, which is not conducive to users' rapid understanding and application of monitoring results.

[0005] By analyzing the existing technical solutions, it can be seen that they have shortcomings in accuracy, real-time, intelligence, user-friendliness and equipment stability. A new monitoring and analysis technology is urgently needed to achieve high-precision, real-time, intelligent and user-friendly energy consumption and carbon emission monitoring.

[0006] Currently, no effective solution has been proposed for the problems in the related technologies. Summary of the invention

[0007] In response to the problems in the related technologies, the present invention proposes a zero-carbon highway energy consumption and carbon reduction dynamic perception intelligent monitoring device, which has the advantages of using high-precision sensors and advanced data processing algorithms to improve monitoring accuracy, ensure the accuracy of energy consumption and carbon emission data, and improve the intelligence level of management and decision-making, thereby solving the problems that existing energy consumption and carbon emission monitoring devices often have insufficient monitoring accuracy and data lag, are unable to reflect the actual energy consumption and emissions of highways in real time, lack intelligent analysis methods, and are unable to provide in-depth data analysis and optimization suggestions.

[0008] To this end, the specific technical solution adopted by the present invention is as follows:

[0009] A zero-carbon high-speed energy consumption and carbon reduction dynamic perception and intelligent monitoring device, the zero-carbon high-speed energy consumption and carbon reduction dynamic perception and intelligent monitoring device comprises a dynamic perception unit, a data processing unit and a display unit;

[0010] The dynamic sensing unit is used to collect the energy usage data and carbon emission data of the highway in real time based on the pre-arranged multi-source sensors, and transmit the energy usage data and carbon emission data to the dynamic sensing unit. The multi-source sensors include power sensors, fuel sensors, and temperature and humidity sensors.

[0011] A data processing unit is used to receive energy usage data and carbon emission data, and perform energy consumption analysis, carbon emission calculation and energy-saving optimization analysis on the energy usage data and carbon emission data, and generate carbon reduction optimization plans and energy-saving and emission reduction suggestions;

[0012] The display unit is used to provide a display interface for users and display the analysis results in real time using charts and reports.

[0013] Further, the dynamic sensing unit includes a sensor selection and calibration module, a power sensor module, a fuel sensor module, and a temperature and humidity sensor module;

[0014] Among them, the sensor selection and calibration module is used to select and calibrate the corresponding sensor according to different energy types;

[0015] Power sensor module, used to monitor the power consumption of highways in real time based on power sensors, measuring current and voltage;

[0016] A fuel sensor module is used to monitor fuel consumption using a fuel sensor, including energy usage of diesel and natural gas;

[0017] Temperature and humidity sensor module, used to monitor ambient temperature and humidity based on temperature and humidity sensors, and perform environmental correction on energy consumption and emission data;

[0018] According to different energy types, select the corresponding sensor and calibrate it including:

[0019] Select the power sensor and perform zero point calibration and load calibration;

[0020] Select the fuel sensor and perform flow and pressure calibration;

[0021] Select the temperature and humidity sensor to perform temperature and humidity calibration.

[0022] Furthermore, the data processing unit includes a data acquisition module, a storage unit module, a processor module and a communication module;

[0023] Among them, the data acquisition module is used to receive the monitoring data of the sensing unit and perform preliminary processing;

[0024] A storage unit module, used to establish and store energy consumption data sets based on preliminary processing results;

[0025] A processor module for in-depth analysis of energy consumption data sets using intelligent monitoring algorithms, including energy consumption analysis, carbon emission calculation, and energy-saving optimization analysis;

[0026] The communication module is used to transmit the results of the depth analysis to the display unit based on the communication protocol.

[0027] Further, the monitoring data of the sensing unit is received and initially processed including:

[0028] Using statistical analysis methods, detect the received monitoring data and eliminate abnormal data points;

[0029] Use interpolation algorithms to complete missing data;

[0030] Based on low-pass filter, high-frequency noise of monitoring data is removed, and Kalman filter algorithm is used for smoothing;

[0031] The normalization method is used to convert the monitoring data into the same dimension range.

[0032] Furthermore, the processor module includes an energy consumption analysis module, a carbon emission calculation module and an energy saving optimization module;

[0033] Among them, the energy consumption analysis module is used to use the energy conversion coefficient, unify the energy unit, calculate the total energy consumption, and predict the energy consumption trend;

[0034] The carbon emission calculation module is used to analyze the carbon emission of electricity based on the electricity consumption and the carbon emission factor of electricity, and calculate the comprehensive carbon emission in combination with the carbon emission of fuel;

[0035] The energy-saving optimization module is used to identify energy consumption patterns, analyze factors affecting energy consumption, and use linear programming algorithms to optimize energy use and generate carbon reduction optimization plans and energy-saving and emission reduction recommendations.

[0036] Furthermore, the energy consumption analysis module includes an energy unit conversion module, a total energy consumption calculation module and an energy consumption trend prediction module;

[0037] Among them, the energy unit conversion module is used to convert all energy consumption data into a unified energy unit using the energy conversion coefficient. The energy conversion coefficient includes the electric energy conversion coefficient, the diesel conversion coefficient and the natural gas conversion coefficient;

[0038] A total energy consumption calculation module, used for calculating the total energy consumption based on the converted energy consumption data;

[0039] Energy consumption trend forecasting module, used to forecast trends based on historical energy consumption data using time series models;

[0040] Based on historical energy consumption data, trend forecasting using time series models includes:

[0041] Use the difference algorithm to pre-process the historical energy consumption data;

[0042] Determine the time series model parameters based on the partial autocorrelation function and the autocorrelation function;

[0043] Use the maximum likelihood estimation method to estimate the model optimization parameters;

[0044] Based on the optimized time series model, future energy consumption data is predicted.

[0045] Furthermore, based on the electricity consumption and the electricity carbon emission factor, the expression for analyzing carbon emissions is:

[0046]

[0047] In the formula, C1 is the carbon emission of electricity, E 电 is the power consumption, f 电 is the carbon emission factor of electricity, γ env is the environmental impact factor, obtained by weighted average of three key indicators;

[0048] The expression of environmental impact factor obtained by weighted average of three key indicators is:

[0049]

[0050] Where CI is the climate adaptability index, PCE is the pollution control efficiency coefficient, ESR is the energy structure response factor, and w1, w2 and w3 are the weights corresponding to the climate adaptability index, pollution control efficiency coefficient and energy structure response factor, respectively.

[0051] Furthermore, the energy-saving optimization module includes an energy consumption pattern recognition module, an energy consumption factor analysis module, a linear programming model building module and an optimal energy-saving path search module:

[0052] Among them, the energy consumption pattern recognition module is used to identify different energy consumption patterns and behavior characteristics using clustering algorithms;

[0053] Energy consumption factor analysis module, which is used to analyze the main factors affecting energy consumption and determine high energy consumption points based on the decision tree algorithm;

[0054] The linear programming model building module is used to build a multi-objective linear programming model using a linear programming algorithm and output a carbon reduction optimization plan;

[0055] The optimal energy-saving path search module is used to find the optimal energy-saving path based on the carbon reduction optimization plan using genetic algorithms and generate energy-saving and emission reduction recommendations.

[0056] Furthermore, a multi-objective linear programming model is established using a linear programming algorithm, and the output of the carbon reduction optimization plan includes:

[0057] Establish an objective function with the goal of minimizing energy consumption costs and carbon emissions;

[0058] Determine constraints based on power supply capacity and equipment load;

[0059] Based on the objective function and constraints, a multi-objective linear programming model is established, and then the multi-objective linear programming model is solved to obtain the carbon reduction optimization plan.

[0060] Furthermore, based on the carbon reduction optimization plan, the genetic algorithm is used to find the optimal energy-saving path and generate energy-saving and emission reduction suggestions including:

[0061] Based on the carbon reduction optimization plan, an initial population is generated, and each individual in the initial population represents an energy-saving and emission reduction path;

[0062] Define the fitness function based on energy consumption cost and carbon emissions;

[0063] According to the fitness function, the crossover rate and mutation rate are dynamically adjusted to generate the next generation population;

[0064] Select the individual with the highest fitness as the optimal energy-saving and emission-reduction path, and output the selection result.

[0065] The beneficial effects of the present invention are:

[0066] (1) The present invention utilizes a dynamic sensing unit to achieve real-time monitoring of highway energy consumption and carbon emissions. By integrating multiple sensors, the present invention can fully cover the monitoring needs of electricity, fuel and environmental parameters, and provide comprehensive energy consumption and carbon emission data. At the same time, the high sensitivity and accuracy of the sensor effectively solve the problems of low data acquisition accuracy and poor real-time performance in the prior art.

[0067] (2) Through the data processing unit, the present invention adopts efficient data processing algorithms and intelligent analysis methods to ensure the real-time and accuracy of data processing. The high-performance computing capability of the processor module and the efficient storage technology of the storage unit enable the system to quickly respond to and process large amounts of data. The design of the communication module ensures reliable data transmission, solving the problems of low data processing efficiency and slow response speed in the prior art.

[0068] (3) Through the display unit, the present invention provides an intuitive and user-friendly interface, allowing users to easily view real-time data, query historical data, and export data. The energy-saving and emission-reduction optimization suggestions generated by the intelligent algorithm help users make scientific decisions, thereby improving the practicality and convenience of the system.

[0069] (4) Through the design and optimization of each unit, the present invention provides a set of efficient, reliable, and real-time dynamic perception and intelligent monitoring solutions for energy consumption and carbon emissions, which effectively overcomes the problems of low monitoring accuracy, low data processing efficiency, and inconvenient user operation in the prior art. It is capable of real-time monitoring of highway energy consumption and carbon emissions, and uses a built-in intelligent monitoring algorithm to automatically generate energy-saving and emission reduction optimization suggestions, realizing the integrated application of real-time data processing and intelligent analysis, and significantly improving the management level of highway energy conservation and emission reduction. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0071] Figure 1 It is a principle block diagram of a zero-carbon high-speed energy consumption and carbon reduction dynamic perception intelligent monitoring device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0072] To further illustrate each embodiment, the present invention provides drawings, which are part of the disclosure of the present invention and are mainly used to illustrate the embodiments and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these contents, ordinary technicians in the field should be able to understand other possible implementations and advantages of the present invention. The components in the figures are not drawn to scale, and similar component symbols are generally used to represent similar components.

[0073] According to an embodiment of the present invention, a zero-carbon high-speed energy consumption and carbon reduction dynamic perception intelligent monitoring device is provided.

[0074] The present invention is further described with reference to the accompanying drawings and specific embodiments. Figure 1 As shown, according to one embodiment of the present invention, a zero-carbon highway energy consumption and carbon reduction dynamic perception and intelligent monitoring device is provided, and the zero-carbon highway energy consumption and carbon reduction dynamic perception and intelligent monitoring device includes a dynamic perception unit 1, a data processing unit 2 and a display unit 3;

[0075] The dynamic sensing unit 1 is used to collect the energy usage data and carbon emission data of the highway in real time based on the pre-arranged multi-source sensors, and transmit the energy usage data and carbon emission data to the dynamic sensing unit. The multi-source sensors include power sensors, fuel sensors, and temperature and humidity sensors.

[0076] Specifically, the dynamic sensing unit 1 monitors power, fuel consumption and environmental parameters by using a variety of high-precision sensors pre-arranged on the highway section. Each sensor has its own unique calibration and data processing method to ensure the accuracy of the monitoring data.

[0077] Data processing unit 2, used to receive energy usage data and carbon emission data, and perform energy consumption analysis, carbon emission calculation and energy-saving optimization analysis on the energy usage data and carbon emission data, and generate carbon reduction optimization plans and energy-saving and emission reduction suggestions;

[0078] Specifically, the data processing unit 2 is the core of the device and is responsible for receiving, storing and processing data from the dynamic sensing unit 1 and generating meaningful information.

[0079] The display unit 3 is used to provide a display interface for the user and to display the analysis results in real time using charts and reports.

[0080] Specifically, the display unit 3 includes a display screen module and a user interface module, wherein the display screen module displays the processed data in real time through an external display screen, including energy consumption data, carbon emission data, energy-saving suggestions, etc.; the user interface module allows users to query, analyze and export data by providing a user-friendly interface.

[0081] Specifically, the display unit 3 displays data in the form of intuitive charts and reports, and supports historical data query and export, helping users to quickly understand and apply monitoring results.

[0082] Specifically, the present invention includes a dynamic sensing unit 1, including power sensors, fuel sensors, temperature and humidity sensors, etc., for real-time collection of energy consumption and carbon emission data on highways; a data processing unit 2, with a built-in intelligent monitoring algorithm, receiving and processing data from the sensing unit, and generating meaningful energy consumption and emission information; a display unit 3, through a friendly user interface, real-time display of processed data, facilitating monitoring and decision-making.

[0083] Specifically, with the help of the present invention, high-speed energy consumption is monitored. First, real-time data collection is realized. The dynamic perception unit 1 collects various energy usage data and carbon emission data on the highway in real time through high-precision sensors; secondly, intelligent data processing is realized. The data processing unit 2 uses a built-in intelligent algorithm to automatically analyze the collected data, generate optimization plans and energy-saving and emission reduction suggestions; finally, intuitive data display is realized. The display unit 3 intuitively displays data in the form of charts and reports to help users quickly understand and apply monitoring results.

[0084] Specifically, the device proposed in the present invention has both system integration and scalability functions, and has high reliability and stability; through high integration and good scalability, it can simultaneously monitor a variety of energy and emission data, and facilitate subsequent functional expansion and system upgrades; through optimized design and material selection, it can improve the reliability and stability of the device, ensuring stable operation in various environments.

[0085] In one embodiment, the dynamic sensing unit 1 includes a sensor selection and calibration module, a power sensor module, a fuel sensor module, and a temperature and humidity sensor module;

[0086] Among them, the sensor selection and calibration module is used to select and calibrate the corresponding sensor according to different energy types;

[0087] Specifically, sensors are selected and calibrated for different energy types (e.g., electricity, fuel), including a) selecting an electric power sensor and performing zero point calibration and load calibration;

[0088] Specifically, high-precision current transformers (CTs) and voltage sensors are selected, both of which have high sensitivity and low measurement error, and can measure current and voltage and calculate power and energy consumption.

[0089] Specifically, the zero point calibration includes ① connecting the current transformer without load; ② recording the output value of the sensor, calibrating the zero point deviation, and adjusting the sensor output to make it close to zero value.

[0090] Specifically, load calibration includes ① selecting a standard load, using a standard load with a known resistance value; ② connecting the load, connecting the standard load to the current transformer; ③ measuring, measuring the current and voltage under the standard load, and recording the deviation between the actual value and the theoretical value; ④ adjusting, adjusting the output value of the sensor according to the measurement results to ensure its accuracy.

[0091] b) Select the fuel sensor and perform flow and pressure calibration;

[0092] Specifically, high-precision flow meters and pressure sensors are selected, both of which are suitable for different types of fuels, can measure fuel flow and pressure, and calculate fuel consumption.

[0093] Specifically, flow calibration includes ① preparation, using a standard liquid with a known flow rate; ② connection, passing the standard liquid through the flowmeter; ③ measurement, recording the flowmeter readings; ④ adjustment, adjusting the output of the flowmeter according to the known standard liquid flow rate to reduce measurement errors.

[0094] Specifically, pressure calibration includes ① preparation, using a standard pressure source; ② connection, connecting the standard pressure source to the pressure sensor; ③ measurement, recording the reading of the pressure sensor under standard pressure; ④ adjustment, adjusting the output value of the sensor to ensure its measurement accuracy.

[0095] c) Select temperature and humidity sensors and perform temperature and humidity calibration;

[0096] Specifically, a high-resolution temperature and humidity sensor is selected to quickly respond and measure the temperature and humidity of the environment.

[0097] Specifically, temperature calibration includes ① preparation, using a standard temperature source (a temperature calibrator is used in this embodiment); ② connection, placing the temperature sensor in the standard temperature source; ③ measurement, recording the reading of the sensor at the standard temperature; ④ adjustment, adjusting the sensor reading according to the known temperature of the standard temperature source.

[0098] Specifically, humidity calibration includes ① preparation, using a standard humidity source (a humidity calibrator is used in this embodiment); ② connection, placing the humidity sensor in the standard humidity source; ③ measurement, recording the sensor reading under standard humidity; ④ adjustment, adjusting the sensor reading according to the known humidity of the standard humidity source.

[0099] Power sensor module, used to monitor the power consumption of highways in real time based on power sensors, measuring current and voltage;

[0100] A fuel sensor module is used to monitor fuel consumption using a fuel sensor, including energy usage of diesel and natural gas;

[0101] The temperature and humidity sensor module is used to monitor the ambient temperature and humidity based on the temperature and humidity sensor, and perform environmental correction on energy consumption and emission data.

[0102] Specifically, the power sensor module is used to monitor the power consumption of the highway in real time and measure parameters such as current and voltage; the fuel sensor module is used to monitor fuel consumption, especially the use of traditional energy such as diesel or natural gas; the temperature and humidity sensor module is used to monitor ambient temperature and humidity and perform environmental correction on energy consumption and emission data.

[0103] Specifically, the dynamic perception unit 1 uses the above-mentioned various sensor modules and high-precision sensors to collect energy consumption and carbon emission data on the highway in real time, and transmits the data to the data processing unit.

[0104] Specifically, the present invention realizes real-time monitoring of energy consumption and carbon emissions of highways through a multi-sensor integrated dynamic perception unit 1 and a high-precision data acquisition method thereof.

[0105] Specifically, the high-precision data acquisition method includes acquiring data from multiple sensors (power sensor module, fuel sensor module, temperature and humidity sensor module), and synchronously processing and fusing these data to ensure the accuracy and reliability of real-time monitoring. The specific steps are as follows:

[0106] 1) Sensor selection and configuration;

[0107] a) Power sensor: used to monitor power consumption. Select high-precision current transformers (CT) and voltage sensors to ensure accurate measurement of power parameters; b) Fuel sensor: used to monitor fuel consumption. Select high-sensitivity flow meters and pressure sensors to accurately measure fuel flow and pressure; c) Temperature and humidity sensor: used to monitor ambient temperature and humidity. Select high-resolution temperature and humidity sensors with fast response and stable output characteristics.

[0108] 2) Data collection steps;

[0109] a) Sensor installation: Install sensors at key locations on the highway, including energy supply points, major traffic flow areas, etc., to ensure coverage of all monitoring areas; b) Data collection settings: Configure the sampling frequency of the sensor to ensure real-time performance. The sampling frequency should be set according to system requirements. In this embodiment, it is set to once per second; Set the range and accuracy parameters of the sensor to ensure data accuracy. For example, the power sensor should be set with an appropriate current and voltage range; c) Data acquisition: Power data acquisition, collect current and voltage data through power sensors, and calculate power and energy consumption; Fuel data acquisition, obtain fuel flow and pressure data through fuel flow meters and pressure sensors; Temperature and humidity data acquisition, obtain environmental temperature and humidity data through temperature and humidity sensors; d) Data synchronization and transmission: Synchronous processing, through the synchronous sampling mechanism, align the data of different sensors in time to ensure data consistency; Data transmission, transmit the collected data to the data processing center through wireless communication modules (such as Wi-Fi, LoRa, 5G, etc.); e) Data preprocessing: Data filtering, apply filtering algorithms to remove sensor noise and interference and improve data accuracy; Data calibration, calibrate sensor data and correct the sensor's system error; f) Data storage and processing: Data storage, store the processed data in a local database or cloud database for subsequent analysis; Data analysis, in the data processing unit 2, further analyze and process the data, including energy consumption calculation and carbon emission analysis.

[0110] In one embodiment, the data processing unit 2 includes a data acquisition module, a storage unit module, a processor module and a communication module;

[0111] Among them, the data acquisition module is used to receive the monitoring data of the sensing unit and perform preliminary processing;

[0112] A storage unit module, used to establish and store energy consumption data sets based on preliminary processing results;

[0113] A processor module for in-depth analysis of energy consumption data sets using intelligent monitoring algorithms, including energy consumption analysis, carbon emission calculation, and energy-saving optimization analysis;

[0114] The communication module is used to transmit the result of the depth analysis to the display unit based on the communication protocol.

[0115] Specifically, the communication module transmits the processed data to the display unit and supports remote data transmission and cloud storage.

[0116] Specifically, the present invention utilizes the data processing unit 2 to realize real-time data processing and feedback, wherein the real-time data processing includes ① a stream processing framework, using a stream processing framework such as Apache Kafka or Apache Flink, to process sensor data in real time to ensure low latency and high throughput of data processing; ② edge computing, performing data processing at a location close to the data source, reducing data transmission delays and improving real-time performance. The real-time feedback mechanism includes ① an alarm system, by setting energy consumption and carbon emission thresholds, when the thresholds are exceeded, the system automatically issues an alarm to notify the user; ② real-time report generation, regularly generating real-time energy consumption and carbon emission reports, displaying them to the user through the display unit 3, and supporting export and sharing functions.

[0117] Specifically, the data processing unit 2 uses efficient intelligent algorithms to ensure the real-time and accuracy of data processing and generate meaningful energy consumption and emission information.

[0118] In one embodiment, receiving monitoring data from a sensing unit and initially processing the data includes:

[0119] Using statistical analysis methods, detect the received monitoring data and eliminate abnormal data points;

[0120] Use interpolation algorithms to complete missing data;

[0121] Based on low-pass filter, high-frequency noise of monitoring data is removed, and Kalman filter algorithm is used for smoothing;

[0122] The normalization method is used to convert the monitoring data into the same dimension range.

[0123] Specifically, the monitoring data of the sensing unit is preliminarily processed using a data preprocessing algorithm, including ① data cleaning, that is, using a statistical analysis method to detect the received monitoring data and remove abnormal data points to achieve abnormal value detection and removal. In this embodiment, the 3σ principle statistical analysis method is used to detect and remove abnormal data points. The expression is:

[0124]

[0125] Among them, x i is the data point of the collected monitoring data, μ is the mean of the monitoring data, and σ is the standard deviation of the monitoring data;

[0126] ② Data interpolation, that is, using an interpolation algorithm to complete missing data. In this embodiment, an interpolation algorithm (such as linear interpolation and spline interpolation) is used to complete missing data in the monitoring data;

[0127] ③ Data filtering, including low-pass filtering and Kalman filtering, that is, based on a low-pass filter, the high-frequency noise of the monitoring data is removed, and the Kalman filtering algorithm is used for smoothing. In this embodiment: a) Low-pass filtering, using a low-pass filter (Butterworth filter is used in this embodiment) to remove high-frequency noise and retain useful signals, the expression is:

[0128]

[0129] Among them, y[n] is the smoothed data, x[n] is the original data, and N is the window size of the filter;

[0130] b) Kalman filtering: Apply Kalman filtering algorithm to smooth the monitoring data and reduce the impact of noise;

[0131] ④ Data normalization, that is, using the normalization method to convert the monitoring data into the same dimension range. In this embodiment, the minimum-maximum normalization is adopted, and the expression is:

[0132]

[0133] Among them, x norm is the normalized monitoring data, x i is the data point of the original monitoring data, min(x) and max(x) are the minimum and maximum values ​​of the monitoring data, respectively.

[0134] In one embodiment, the processor module includes an energy consumption analysis module, a carbon emission calculation module, and an energy saving optimization module;

[0135] Among them, the energy consumption analysis module is used to use the energy conversion coefficient, unify the energy unit, calculate the total energy consumption, and predict the energy consumption trend;

[0136] The carbon emission calculation module is used to analyze the carbon emission of electricity based on the electricity consumption and the carbon emission factor of electricity, and calculate the comprehensive carbon emission in combination with the carbon emission of fuel;

[0137] Specifically, carbon emissions calculations include electricity carbon emissions and fuel carbon emissions. Fuel carbon emissions include diesel carbon emissions and natural gas carbon emissions.

[0138] Specifically, ① electricity carbon emissions. The electricity carbon emissions are calculated based on the electricity consumption and the electricity carbon emission factor. The present invention introduces the influencing factors of environmental factors into the carbon emission calculation formula, considers the changes in emission factors under different climatic conditions, and adjusts the emission factors according to different pollution control measures in the region.

[0139] Specifically, ② fuel carbon emissions include diesel carbon emissions and natural gas carbon emissions. Fuel carbon emissions are calculated based on fuel consumption and fuel carbon emission factors. The calculation formula is C燃 =E 燃 ×f 燃 , where C 燃 is the carbon emission of fuel, E 燃 is the fuel consumption, f 燃 is the fuel carbon emission factor. In this embodiment, the fuel includes diesel and natural gas.

[0140] Specifically, ③ use the data fusion algorithm to calculate the comprehensive carbon emissions:

[0141] In this embodiment, the weighted average method is used to perform weighted average on the carbon emission data from different sources to obtain the comprehensive carbon emissions. By introducing a nonlinear combination method, the weight is not just a simple linear proportion, but is adjusted according to the relationship between the data. This can be achieved by introducing a nonlinear function f(.) to adjust the influence of each data source, and the calculation expression of the initial comprehensive carbon emissions is obtained as follows:

[0142]

[0143] In the formula, the three main sources of carbon emission data include electricity carbon emission C1 (C1=C 电 ), diesel emissions C2 and natural gas emissions C3, then consider optimizing the above formula. We first assign corresponding initial weights v1, v2 and v3 to each data source based on historical data and current environmental conditions.

[0144] Specifically, the initial weights are set. In this embodiment, the magnitude of diesel emissions in the high-speed area is large and the accuracy is the highest, so it is given a higher initial weight v2=0.5; the electricity emission weight v1=0.3; and the natural gas emission weight v3=0.2.

[0145] Specifically, dynamic adjustment is then performed. In the above embodiment, as time goes by, it is found that the data update frequency of power emissions in a certain time period t is higher and the credibility is enhanced, so the value of v2(t) is increased accordingly, and other weights are adjusted to keep the total to 1.

[0146] Based on the above steps, the final comprehensive carbon emissions calculation expression is:

[0147]

[0148] In the formula, C 综合(t) is the comprehensive carbon emissions within a certain time period t, that is, the comprehensive carbon emissions taking into account multiple carbon emission sources (including electricity, diesel, natural gas) and environmental influencing factors (such as climate, pollution control efficiency, energy structure, etc.). It is an indicator that reflects the overall carbon emissions situation; C1(t) is the carbon emissions of electricity within the time period t; C2(t) is the carbon emissions of diesel within the time period t, calculated by the fuel carbon emission formula; C3(t) is the carbon emissions of natural gas within the time period t, calculated by the fuel carbon emission formula; v1(t), v2(t) and v3(t) are the electricity emission weight, diesel emission weight and natural gas emission weight after dynamic adjustment in the time period t.

[0149] The energy-saving optimization module is used to identify energy consumption patterns, analyze factors affecting energy consumption, and use linear programming algorithms to optimize energy use and generate carbon reduction optimization plans and energy-saving and emission reduction recommendations.

[0150] In one embodiment, the energy consumption analysis module includes an energy unit conversion module, a total energy consumption calculation module, and an energy consumption trend prediction module;

[0151] Among them, the energy unit conversion module is used to convert all energy consumption data into a unified energy unit using the energy conversion coefficient. The energy conversion coefficient includes the electric energy conversion coefficient, the diesel conversion coefficient and the natural gas conversion coefficient;

[0152] Specifically, we first unify the energy consumption data and convert the energy consumption data from different sources (such as electricity and fuel energy) into a unified energy unit to facilitate comprehensive calculation and analysis.

[0153] Specifically, the goal of energy consumption data unification is to convert energy consumption data from different sources (such as electricity and fuel energy) into a unified energy unit to facilitate comprehensive calculation and analysis. The detailed method steps are as follows:

[0154] 1) Based on the energy consumption data, determine the energy conversion coefficient: According to the energy consumption data from different energy types, determine the conversion coefficient of each energy type into a unified unit. In this embodiment, the electric energy is measured in kilowatt-hours (kWh), and the fuel energy is measured in liters (L) or kilograms (kg). The electric energy conversion coefficient is set to 1kWh = 3.6MJ (megajoules); the diesel conversion coefficient is 1L = 37.5MJ; the natural gas conversion coefficient is 1m³ = 37.0MJ;

[0155] 2) Data conversion: Use the above energy conversion coefficient to convert all energy consumption data into a unified energy unit (such as MJ). The expression is:

[0156]

[0157] In the formula, E unified is the unified energy value, E sourceis the original energy value and CF is the conversion factor.

[0158] 3) Comprehensive calculation, summarize the converted energy data and calculate the total energy consumption. The expression is:

[0159]

[0160] In the formula, E total is the total energy consumption, E i is the energy value of the i-th energy source, and n is the total number of energy types.

[0161] A total energy consumption calculation module, used for calculating the total energy consumption based on the converted energy consumption data;

[0162] Specifically, the real-time energy consumption calculation is then carried out: ① Establish a basic model: Based on sensor data (including current, voltage, fuel consumption, etc.), use the formula E=P×t to calculate energy consumption, where E is energy consumption, P is power, and t is time; ② Integrated energy consumption model: Consider multiple energy consumption sources (including electrical energy consumption, diesel energy consumption, and natural gas energy consumption) and comprehensively calculate the total energy consumption.

[0163] Energy consumption trend forecasting module, used to forecast trends based on historical energy consumption data using time series models;

[0164] Based on historical energy consumption data, trend forecasting using time series models includes:

[0165] Use the difference algorithm to pre-process the historical energy consumption data;

[0166] Determine the time series model parameters based on the partial autocorrelation function and the autocorrelation function;

[0167] Use the maximum likelihood estimation method to estimate the model optimization parameters;

[0168] Based on the optimized time series model, future energy consumption data is predicted.

[0169] Specifically, historical data trend analysis is performed, including: time series analysis, using the ARIMA (autoregressive integrated moving average) model to predict the trend of historical energy consumption data; sliding average, applying the sliding average algorithm to smooth the energy consumption data and observe the long-term trend. The expression is:

[0170]

[0171] In the formula, y t is the observed value at time t, μ is the mean term, ϕ i is the autoregressive coefficient, θ j is the moving average coefficient, ϵ t It is a random error.

[0172] Specifically, the ARIMA (Autoregressive Integrated Moving Average) model is used to predict the trend of historical energy consumption data, including the use and optimization of the ARIMA model. The detailed method steps are as follows:

[0173] ① Data preprocessing to ensure data stability. In this embodiment, differential processing is performed on non-stationary data until the data is stable. The differential formula is expressed as:

[0174]

[0175] Where Y t is the data point at time t. In carbon emission calculation, Y t Indicates the carbon emissions, energy consumption data or other related indicators at a certain time point t; Y t-1 is the data point at time t-1, indicating the data at the previous time point of time t; ΔY t is the difference value at time t, indicating that Y t and Y t-1 The difference formula can capture the changing trend in the data.

[0176] ② Model identification: Use the partial autocorrelation function (PACF) and autocorrelation function (ACF) to determine the parameters of the ARIMA model; ACF and PACF graphs can help identify the values ​​of the autoregressive term (p), difference order (d), and moving average term (q).

[0177] ③ Model estimation and optimization: The maximum likelihood estimation (MLE) method is used to estimate the model parameters. In this embodiment, the optimal model parameters are selected by cross-validation and information criteria (including AIC and BIC), and the expression is:

[0178]

[0179] In the formula, L is the log-likelihood function and k is the number of model parameters. Finally, the optimized ARIMA model is used to predict future energy consumption data.

[0180] In one embodiment, based on the electricity consumption and the electricity carbon emission factor, the expression for analyzing the carbon emission is:

[0181]

[0182] In the formula, C1 is the carbon emission of electricity, E 电 is the power consumption, f 电 is the carbon emission factor of electricity, γ env is the environmental impact factor, obtained by weighted average of three key indicators;

[0183] The expression of environmental impact factor obtained by weighted average of three key indicators is:

[0184]

[0185] Where CI is the climate adaptability index, PCE is the pollution control efficiency coefficient, ESR is the energy structure response factor, and w1, w2 and w3 are the weights corresponding to the climate adaptability index, pollution control efficiency coefficient and energy structure response factor, respectively.

[0186] Specifically, environmental impact factor γ env It is obtained by weighted average of three key indicators: climate adaptability index (CI), pollution control effectiveness coefficient (PCE) and energy structure response factor (ESR). The following will elaborate on the method of obtaining each indicator and its dynamic adjustment mechanism.

[0187] Specifically, the climate adaptability index (CI) reflects the impact of regional climate characteristics on the power system, including the impact of climate parameters such as temperature, humidity, and precipitation on energy consumption and energy production. The acquisition methods include ① historical climate data analysis, collecting and analyzing the historical climate data of the region to determine the main climate parameters and their changing trends; ② climate prediction models, using climate prediction models (including time series analysis and machine learning models) to predict future climate changes and assess their potential impact on the power system; ③ real-time climate monitoring, by installing meteorological sensors to monitor high-speed regional climate parameters in real time to ensure that CI can promptly reflect the latest climate changes.

[0188] Specifically, a dynamic adjustment mechanism is set up for the Climate Adaptability Index (CI), including ① data update frequency, updating CI regularly (e.g. daily, monthly) according to the frequency of changes in climate data; ② adaptive algorithm, introducing an adaptive algorithm to automatically adjust CI according to the latest climate data to ensure that it reflects the current climate conditions.

[0189] Specifically, the Pollution Control Effectiveness Coefficient (PCE) measures the effectiveness of regional pollution control measures on carbon emissions and reflects the effects of policies and technologies in reducing pollutant emissions. The acquisition methods include: ① policy and regulatory analysis, collecting the current and latest pollution control policies and regulations in the region, and evaluating their coverage and implementation intensity; ② pollutant emission data, obtaining emission data of major pollutants (including carbon dioxide, nitrogen oxides, etc.) in the high-speed region, and summarizing the data reported by monitoring stations and enterprises; ③ technical effectiveness evaluation, analyzing the effectiveness of the pollution control technologies used (such as desulfurization and denitrification equipment) and evaluating their actual emission reduction effects.

[0190] Specifically, a dynamic adjustment mechanism is set up for the pollution control effectiveness coefficient (PCE), including ① response to policy changes. As new policies and regulations are introduced, PCE is adjusted in a timely manner to reflect their impact on carbon emissions; ② real-time monitoring feedback. Using real-time monitoring data, PCE is dynamically adjusted to ensure that it reflects the actual effectiveness of current pollution control measures.

[0191] Specifically, the energy structure response factor (ESR) reflects the sensitivity of the regional energy structure to environmental factors, taking into account the proportion of renewable energy and non-renewable energy in the energy structure and its responsiveness to environmental changes. The acquisition methods include: ① Energy structure data collection, obtaining the usage proportion of various energy sources (including natural gas, diesel, and electricity) in the region and their changing trends; ② Energy sensitivity analysis, analyzing the sensitivity of different energy types to environmental changes (including climate change and policy changes), and evaluating their adaptability under different environmental conditions; ③ Energy conversion and development planning, considering future energy development plans in the region, such as the introduction and expansion of renewable energy, and adjusting the ESR to reflect the dynamic changes in the energy structure.

[0192] Specifically, a dynamic adjustment mechanism is set up for the energy structure response factor (ESR), including ① real-time update of energy data, obtaining energy usage data in real time through the energy management system, and dynamically adjusting the ESR; ② scenario simulation and prediction, using scenario simulation tools to predict environmental responses under different energy structures and adjust the ESR to adapt to possible future changes.

[0193] Specifically, through the above steps, the comprehensive application of environmental impact factors is realized, including: ① weight determination: according to the importance of regional climate, pollution control policy and energy structure, the weights w1, w2, w3 of each indicator are reasonably allocated; combined with expert evaluation and data-driven methods, the weights are dynamically adjusted to ensure that the environmental impact factor γ env Accurately reflect the regional environmental impact; ② Dynamic adjustment mechanism: Through real-time monitoring and data analysis, dynamically adjust the weights and values ​​of CI, PCE, and ESR to ensure γ env Reflect environmental changes promptly; introduce machine learning and adaptive algorithms to continuously optimize based on historical and real-time dataγ env The calculation method of .

[0194] In one embodiment, the energy-saving optimization module includes an energy consumption pattern recognition module, an energy consumption factor analysis module, a linear programming model building module and an optimal energy-saving path search module:

[0195] Among them, the energy consumption pattern recognition module is used to identify different energy consumption patterns and behavior characteristics using clustering algorithms;

[0196] Specifically, a clustering algorithm (K-means clustering algorithm is used in this embodiment) is used to identify different energy consumption patterns and behavioral characteristics. In the present invention, the application of K-means algorithm does not only stay at the basic energy consumption pattern recognition level, but also combines the following innovations: ① Dynamically adjust the cluster center, by introducing the influence of time series analysis or external environmental factors (such as weather changes, policy adjustments), the cluster center is dynamically adjusted so that the clustering can better adapt to the changes in actual energy consumption behavior; ② Multi-dimensional feature fusion, on the basis of traditional energy consumption data, more dimensional features are added, such as real-time energy prices, user behavior patterns, equipment performance status, etc., so as to achieve more refined energy consumption pattern recognition.

[0197] Specifically, the implementation steps of using clustering algorithms to identify different energy consumption patterns and behavioral characteristics include: ① feature extraction, first extracting features of multiple dimensions from energy consumption data, such as time period energy consumption, peak energy consumption, load fluctuation, etc., and additional features such as external temperature, equipment utilization rate, etc. are also taken into consideration; ② initial clustering, using the traditional K-means algorithm to perform preliminary clustering of energy consumption data to obtain the initial energy consumption pattern; ③ dynamic adjustment, dynamically adjusting the initial clustering center according to the external environment or time series data, so that the clustering result is more adaptable; ④ pattern recognition, the final clustering result divides the energy consumption data into several modes, including "peak energy consumption mode", "energy-saving mode", and "abnormal energy consumption mode", thereby providing a basis for further energy consumption management and optimization.

[0198] Energy consumption factor analysis module, which is used to analyze the main factors affecting energy consumption and determine high energy consumption points based on the decision tree algorithm;

[0199] Specifically, the decision tree algorithm is applied to analyze the main factors affecting energy consumption and identify high energy consumption points.

[0200] It should be noted that the decision tree algorithm is a commonly used supervised learning method that can classify and predict target variables by building a tree model. This method is used in energy consumption analysis to identify the main factors affecting energy consumption, thereby helping managers take corresponding measures.

[0201] Specifically, the present invention focuses on the following innovations in the application of decision tree algorithms: ① Construction of multi-level decision trees. For different energy consumption scenarios (including electricity consumption, diesel consumption, and natural gas consumption), multi-level decision tree models are constructed. Each model identifies the key energy consumption influencing factors in the scenario; ② Integration of external data. External data (such as electricity price fluctuations, policy adjustments, climate change, etc.) are combined with energy consumption data. The indirect impact on energy consumption is analyzed through the decision tree algorithm to identify potential high energy consumption points; ③ Adaptive decision trees. An adaptive decision tree model is designed to automatically adjust the splitting rules according to new data, thereby improving the model's ability to recognize new energy consumption patterns.

[0202] Specifically, based on the decision tree algorithm, the main factors affecting energy consumption are analyzed and high energy consumption points are determined. The implementation steps include: ① data preparation, collecting and cleaning historical energy consumption data, and extracting various influencing factors, including equipment usage frequency, ambient temperature, user behavior, external electricity price, etc.; ② building a decision tree model: based on the data, construct an initial decision tree, and the node splitting basis is information gain or Gini index. Each leaf node of the tree corresponds to an energy consumption feature; ③ analyzing energy consumption factors, through the structure of the tree, the factors that have the greatest impact on energy consumption are analyzed, such as equipment type, load intensity, time period, etc.; ④ identifying high energy consumption points, based on the prediction results of the decision tree, identifying specific high energy consumption time points or equipment, so as to guide the implementation of energy-saving measures; ⑤ model optimization, introducing new energy consumption data into the model, and using incremental learning to enable the decision tree to dynamically adapt to new energy consumption patterns and influencing factors.

[0203] Specifically, the present invention realizes dynamic adjustment of cluster centers and fusion of multi-dimensional features through the above steps, while the K-means algorithm in the prior art usually adopts fixed cluster centers. The present invention makes the algorithm more flexible and adaptable to actual conditions by dynamically adjusting the cluster centers and introducing multi-dimensional features (such as external environmental data); at the same time, the present invention improves the adaptability to complex energy consumption scenarios and the ability to recognize new patterns by constructing a multi-level decision tree model and introducing external data, while the prior art often only uses a static, single decision tree model.

[0204] The linear programming model building module is used to build a multi-objective linear programming model using a linear programming algorithm and output a carbon reduction optimization plan;

[0205] It should be noted that Linear Programming (LP) is a classic mathematical optimization method, which is mainly used to find the optimal solution of the objective function under given constraints. In energy management, linear programming is often used to optimize energy scheduling and allocation to reduce energy consumption costs and improve energy efficiency.

[0206] Specifically, the present invention is based on the traditional linear programming algorithm and has made the following innovations: ① Multi-objective linear programming, which not only optimizes the single energy usage cost, but also simultaneously optimizes multiple objective functions such as carbon emissions and equipment life, forming a multi-objective optimization model, making the optimization results more comprehensive and balanced; ② Dynamic constraint adjustment, combined with real-time data, through embedded algorithms to dynamically adjust the constraints in linear programming (such as power load, external electricity price, equipment performance, etc.), to improve the adaptability of the model in complex and dynamic environments; ③ Distributed optimization architecture, using cloud-edge collaborative technology to distribute the linear programming algorithm, so that each subsystem can independently calculate the optimal energy consumption plan while ensuring the coordination of the overall system.

[0207] Specifically, a linear programming algorithm is used to optimize energy use and generate a carbon reduction optimization plan. The implementation steps include: ① objective function definition, setting multiple optimization goals for energy use, including minimizing energy consumption cost min C(x), minimizing carbon emissions min E(x), etc.; ② constructing a linear programming model, constructing the constraints in the energy use scenario (such as power supply capacity, equipment load, etc.) as linear inequalities, and defining the objective function; ③ dynamically adjusting the constraints, combining real-time data and external environmental changes, and dynamically adjusting the constraints in the linear programming model so that the model can adapt to changes; ④ solving the optimal solution, using a distributed optimization architecture, and calculating the optimal solution through a linear programming solver (the Simplex algorithm is used in this embodiment) to generate a carbon reduction optimization plan.

[0208] The optimal energy-saving path search module is used to find the optimal energy-saving path based on the carbon reduction optimization plan using genetic algorithms and generate energy-saving and emission reduction recommendations.

[0209] It should be noted that the genetic algorithm (GA) is an optimization algorithm based on natural selection and genetic mechanisms, which is particularly suitable for complex nonlinear optimization problems. It simulates the biological evolution process to find the optimal solution to the problem and is widely used in energy management, path optimization and other fields.

[0210] Specifically, the present invention has made the following innovations in the application of genetic algorithms in combination with actual scenarios: ① Adaptive crossover and mutation operations, introducing an adaptive mechanism to dynamically adjust the crossover rate and mutation rate in the genetic algorithm according to changes in real-time energy consumption data, so that the algorithm can quickly adapt to different optimization environments; ② Integration of multiple constraints, comprehensively considering multiple constraints in the genetic algorithm, such as energy quotas, equipment failure rates, carbon emission limits, etc., to achieve multi-objective optimization in complex scenarios; ③ Parallel computing architecture, using parallel computing technology to accelerate the iterative process of the genetic algorithm, significantly improving the algorithm's solution speed, which is particularly suitable for large-scale energy consumption optimization problems.

[0211] Specifically, based on the carbon reduction optimization plan, a genetic algorithm is used to find the optimal energy-saving path and generate energy-saving and emission reduction recommendations. The implementation steps include ① encoding and initial population generation, encoding the energy-saving path optimization problem and generating an initial population. Each individual in the population represents an energy scheduling plan; ② fitness function design, defining the fitness function f(x), comprehensively considering multiple objectives such as energy consumption cost, carbon emissions, and equipment life, and evaluating the pros and cons of each individual; ③ adaptive crossover and mutation, dynamically adjusting the crossover rate and mutation rate according to the changes in the fitness function, generating the next generation of population, and gradually optimizing the energy-saving path; ④ parallel optimization, using multi-threaded or distributed computing platforms to perform iterative calculations of parallel genetic algorithms to accelerate the process of finding the optimal solution; ⑤ optimal path selection, after several generations of evolution, selecting the individual with the highest fitness as the final energy-saving path, and outputting the optimization results.

[0212] Specifically, the present invention realizes multi-objective linear programming and dynamic constraint adjustment through the above steps. Traditional linear programming usually targets a single objective. The present invention realizes more refined optimization of complex energy consumption scenarios through multi-objective optimization models and dynamic constraint adjustment. At the same time, the present invention integrates adaptive genetic algorithms with multiple constraints. On the basis of existing genetic algorithms, it introduces an adaptive mechanism and the integration of multiple constraints, making the algorithm more efficient and flexible when dealing with complex and changing energy consumption environments.

[0213] In one embodiment, a multi-objective linear programming model is established using a linear programming algorithm, and the output of a carbon reduction optimization plan includes:

[0214] Establish an objective function with the goal of minimizing energy consumption costs and carbon emissions;

[0215] Specifically, the present invention optimizes energy consumption cost E(x) and carbon emission C(x) simultaneously, and carbon emission C(x) is equal to the comprehensive carbon emission C 综合 (t), the following multi-objective linear programming model is constructed.

[0216] Specifically, the expression of the objective function is established as:

[0217]

[0218] Where x is the decision variable, including the energy consumption allocation of different equipment; E(x) is the energy cost, and C(x) is the carbon emission, which is equal to the comprehensive carbon emission C 综合 (t), reflects the relative importance of each objective in the overall optimization;

[0219] Determine constraints based on resource capacity and equipment load;

[0220] Specifically, the constraint condition expression is:

[0221]

[0222] In the formula, a ij represents the resource consumption coefficient of the i-th resource type corresponding to the j-th device; b i represents the resource upper limit of the i-th resource type; n represents the total number of resource types. In this embodiment, the resource types include electricity, diesel and natural gas, and n=3; x j represents the operating load of the jth device.

[0223] Based on the objective function and constraints, a multi-objective linear programming model is established, and then the multi-objective linear programming model is solved to obtain the carbon reduction optimization plan.

[0224] In one embodiment, based on the carbon reduction optimization scheme, a genetic algorithm is used to find the optimal energy-saving path, and energy-saving and emission-reduction suggestions are generated, including:

[0225] Based on the carbon reduction optimization plan, an initial population is generated, and each individual in the initial population represents an energy-saving and emission reduction path;

[0226] Specifically, we first generate an initial population, randomly generating an initial population, where each individual x k Represents a possible energy-saving path solution.

[0227] Define the fitness function based on energy consumption cost and carbon emissions;

[0228] Specifically, define the fitness function f(x k ), combined with the energy cost C(x k ), carbon emissions E(x k ) and other multiple targets, the expression is:

[0229]

[0230] In the formula, α is the weight coefficient of energy consumption cost, which indicates the relative importance of energy consumption cost in the fitness function; β is the weight coefficient of carbon emission, which indicates the relative importance of carbon emission in the fitness function.

[0231] According to the fitness function, the crossover rate and mutation rate are dynamically adjusted to generate the next generation population;

[0232] Specifically, crossover and mutation are performed. In each generation, better individuals are selected according to the fitness value to perform crossover and mutation operations to generate the next generation population.

[0233] Specifically, the crossover operation includes the adaptive crossover probability p c , the two individuals x p and x q Crossover generates a new individual x′, the expression is:

[0234]

[0235] Specifically, the mutation operation includes adaptive mutation probability p m , for individual x k Perform random mutation to generate a new solution x'', the expression is:

[0236]

[0237] Where Δx is the variation value.

[0238] Select the individual with the highest fitness as the optimal energy-saving and emission-reduction path, and output the selection result.

[0239] Specifically, we select the optimal solution, and after several generations of evolution, we select the individual x with the highest fitness. best As the optimal energy-saving path.

[0240] Specifically, the present invention utilizes expert systems and machine learning predictions to construct a rule-based expert system, uses machine learning algorithms (such as random forests and support vector machines) to predict energy consumption data, and provides energy-saving and emission-reduction recommendations in combination with the optimal energy-saving and emission-reduction path.

[0241] It should be noted that the expert system is a rule-based system that provides personalized energy-saving suggestions based on predefined rules and conditions and actual conditions.

[0242] Specifically, the implementation steps of building a rule-based expert system include ① knowledge base construction, building a knowledge base containing energy-saving rules and experience. These rules can be based on industry standards, historical data analysis, expert experience, etc. In this embodiment, the knowledge base contains the following rules: a) If the energy consumption exceeds a certain threshold, it is recommended to reduce the operating frequency of the equipment; b) If the energy efficiency of a certain device is detected to be reduced, it is recommended to perform maintenance or replacement; ② Inference engine, through the inference engine, based on the real-time monitoring data and the rules in the knowledge base, infer energy-saving suggestions suitable for the current situation. In this embodiment, the inference engine can give suggestions for reducing energy consumption based on the current energy consumption pattern recognition results and the corresponding rules in the knowledge base.

[0243] Specifically, the present invention dynamically adjusts the rules and introduces a self-learning mechanism, so that the expert system can dynamically adjust the weights or conditions of the rules according to historical data and actual application situations, thereby improving the accuracy and practicality of the recommendations; at the same time, the present invention combines multi-source data and introduces external environmental data (such as weather, traffic flow, policy changes, etc.) into the expert system, further enhancing the personalization and foresight of the recommendations. In the above embodiment, in hot weather, the expert system can recommend increasing the operation of cooling equipment to prevent equipment overheating, and adjust energy consumption strategies to reduce peak power consumption.

[0244] Specifically, the steps for using machine learning algorithms (such as random forests and support vector machines) to predict energy consumption data and provide energy conservation and emission reduction suggestions in combination with the optimal energy conservation and emission reduction path include: ① data preprocessing, first, clean and normalize the real-time collected energy consumption data, remove abnormal data, and standardize the data format; then, divide the processed data into training sets and test sets; ② model training, use machine learning algorithms (such as random forests and support vector machines, etc.) to model historical energy consumption data. The specific steps are as follows: a) feature selection, extract features that have a greater impact on energy consumption prediction from the data set, such as time, equipment type, frequency of use, external environmental parameters, etc.; b) training model, use the above features to train the machine learning model so that it can predict energy consumption trends in future time periods; c) real-time prediction and optimization, after the model training is completed, input the real-time data into the model for energy consumption prediction. According to the prediction results, forward-looking energy-saving suggestions are proposed in combination with optimization algorithms (such as linear programming and genetic algorithms).

[0245] Specifically, the present invention designs a mechanism by updating the model in real time, so that the machine learning model can be updated online according to the newly collected data, so as to ensure the accuracy and robustness of the model after a long time of operation; at the same time, the present invention combines the prediction results of multiple machine learning models through multi-model fusion, and adopts weighted average, voting mechanism and other methods to improve the accuracy of the prediction. In the above embodiment, the random forest model and the long short-term memory network (LSTM) can be combined to integrate their prediction results to obtain more reliable energy-saving suggestions; in addition, the present invention designs an adaptive time window in energy consumption prediction through an adaptive prediction window, and dynamically adjusts the prediction time span according to the current environment and energy consumption fluctuations, so as to improve the accuracy and practicality of the prediction.

[0246] Specifically, the present invention has made innovations and improvements in the following aspects, including ① dynamic adjustment and self-learning. The expert system not only relies on fixed rules, but also introduces a self-learning mechanism, which can continuously optimize and adjust the rules according to actual application conditions, thereby improving the intelligence level of the system; ② fusion of external data. In both the expert system and machine learning prediction, external environmental data (such as weather, policies, etc.) are introduced to make energy-saving suggestions more personalized and forward-looking, which is relatively rare in the prior art; ③ multi-model fusion and real-time update. Through multi-model fusion and real-time update mechanisms, the accuracy and adaptability of machine learning predictions are further improved, so that the system can maintain efficient operation in a dynamically changing environment; ④ adaptive time window. When predicting energy consumption, the concept of adaptive time window is innovatively introduced to make the prediction results more in line with actual conditions.

[0247] In order to facilitate understanding of the above technical solution of the present invention, a specific description is given below taking a highway as an example:

[0248] Based on the technical solution of the present invention, the highway monitoring system is pre-arranged with power sensors, fuel sensors and temperature and humidity sensors, and the implementation steps are as follows: First, install the sensors, including ① installing power sensors at the power supply point of the highway, and the installation position is close to the power line and the distribution box; ② installing fuel sensors at the fuel supply station, ensuring that the flow meter is installed in the fuel pipeline and the pressure sensor is installed in the fuel storage container; ③ installing temperature and humidity sensors at the environmental monitoring point of the highway and placing them in an open environment. Secondly, configuration and calibration are performed, including ① setting the sampling frequency of the power sensor to 1Hz (sampling once per second), configuring the range to 0-1000A (current) and 0-500V (voltage); ② setting the sampling frequency of the fuel sensor to 0.5Hz (sampling once every 2 seconds), configuring the flow meter range to 0-1000L / h, and the pressure sensor range to 0-10MPa; ③ setting the sampling frequency of the temperature and humidity sensor to 1Hz, and the range to -40°C to 85°C (temperature) and 0-100%RH (humidity). Finally, data collection and transmission are carried out, including ① the sensor collects data in real time, and after data synchronization, it is transmitted to the central data processing center through the Wi-Fi unit; ② after data transmission, the central processing system filters and calibrates the data; the processed data is stored in the cloud database. The data processing unit 2 analyzes the data, calculates power consumption, fuel consumption and environmental impact, and generates a real-time monitoring report, which is transmitted to the display unit 3. The display unit 3 displays the data in the form of intuitive charts and reports to help users quickly understand and apply the monitoring results.

[0249] In summary, with the help of the above technical solution of the present invention, by adopting the dynamic sensing unit 1, real-time monitoring of highway energy consumption and carbon emissions is realized. The high sensitivity and accuracy of these sensors effectively solve the problems of low data acquisition accuracy and poor real-time performance in the prior art. By integrating multiple sensors, it can fully cover the monitoring needs of electricity, fuel and environmental parameters, and provide comprehensive energy consumption and carbon emission data; the data processing unit 2 adopts efficient data processing algorithms and intelligent analysis methods to ensure the real-time and accuracy of data processing. The high-performance computing capability of the processor module and the efficient storage technology of the storage unit enable the system to quickly respond to and process large amounts of data. The design of the communication module ensures The reliable transmission of data solves the problems of low data processing efficiency and slow response speed in the prior art; the display unit 3 provides an intuitive and user-friendly interface, allowing users to easily view real-time data, query historical data, and export data. The energy-saving and emission reduction optimization suggestions generated by the intelligent algorithm help users make scientific decisions, thereby improving the practicality and convenience of the system; based on the design and optimization of the above units, the present invention provides a set of efficient, reliable, and real-time dynamic perception and intelligent monitoring solutions for energy consumption and carbon emissions, which effectively overcomes the problems of low monitoring accuracy, low data processing efficiency, and inconvenient user operation in the prior art, and significantly improves the management level of energy conservation and emission reduction on highways.

[0250] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A zero-carbon high-speed energy consumption and carbon reduction dynamic perception intelligent monitoring device, characterized in that: The zero-carbon high-speed energy consumption and carbon reduction dynamic perception and intelligent monitoring device comprises a dynamic perception unit, a data processing unit and a display unit; The dynamic sensing unit is used to collect energy usage data and carbon emission data of the highway in real time based on pre-arranged multi-source sensors, and transmit the energy usage data and carbon emission data to the dynamic sensing unit, wherein the multi-source sensors include power sensors, fuel sensors, and temperature and humidity sensors; The data processing unit is used to receive energy usage data and carbon emission data, and perform energy consumption analysis, carbon emission calculation and energy-saving optimization analysis on the energy usage data and carbon emission data, and generate carbon reduction optimization solutions and energy-saving and emission reduction suggestions; The display unit is used to provide a display interface for users, and to display the analysis results in real time using charts and reports.

2. According to claim 1, a zero-carbon high-speed energy consumption and carbon reduction dynamic perception intelligent monitoring device is characterized in that: The dynamic sensing unit includes a sensor selection and calibration module, a power sensor module, a fuel sensor module and a temperature and humidity sensor module; Wherein, the sensor selection and calibration module is used to select and calibrate corresponding sensors according to different energy types; The power sensor module is used to monitor the power consumption of the highway in real time based on the power sensor and measure the current and voltage; The fuel sensor module is used to monitor fuel consumption, including energy usage of diesel and natural gas, using a fuel sensor; The temperature and humidity sensor module is used to monitor the ambient temperature and humidity based on the temperature and humidity sensor, and perform environmental correction on the energy consumption and emission data; The selecting and calibrating corresponding sensors according to different energy types includes: Select the power sensor and perform zero point calibration and load calibration; Select the fuel sensor and perform flow and pressure calibration; Select the temperature and humidity sensor to perform temperature and humidity calibration.

3. According to claim 1, a zero-carbon high-speed energy consumption and carbon reduction dynamic perception intelligent monitoring device is characterized in that: The data processing unit includes a data acquisition module, a storage unit module, a processor module and a communication module; Wherein, the data acquisition module is used to receive the monitoring data of the sensing unit and perform preliminary processing; The storage unit module is used to establish and store energy consumption data sets based on the preliminary processing results; The processor module is used to deeply analyze the energy consumption data set using an intelligent monitoring algorithm, wherein the intelligent monitoring algorithm includes energy consumption analysis, carbon emission calculation and energy saving optimization analysis; The communication module is used to transmit the result of the depth analysis to the display unit based on the communication protocol.

4. According to claim 3, a zero-carbon high-speed energy consumption and carbon reduction dynamic perception intelligent monitoring device is characterized in that: The receiving and preliminary processing of the monitoring data of the sensing unit includes: Using statistical analysis methods, detect the received monitoring data and eliminate abnormal data points; Use interpolation algorithms to complete missing data; Based on low-pass filter, high-frequency noise of monitoring data is removed, and Kalman filter algorithm is used for smoothing; The normalization method is used to convert the monitoring data into the same dimension range.

5. According to claim 3, a zero-carbon high-speed energy consumption and carbon reduction dynamic perception intelligent monitoring device is characterized in that: The processor module includes an energy consumption analysis module, a carbon emission calculation module and an energy saving optimization module; The energy consumption analysis module is used to utilize the energy conversion coefficient, unify the energy units, calculate the total energy consumption, and predict the energy consumption trend; The carbon emission calculation module is used to analyze the electricity carbon emission according to the electricity consumption and the electricity carbon emission factor, and calculate the comprehensive carbon emission in combination with the fuel carbon emission; The energy-saving optimization module is used to identify energy consumption patterns, analyze factors affecting energy consumption, and optimize energy use using a linear programming algorithm to generate carbon reduction optimization plans and energy-saving and emission reduction recommendations.

6. According to claim 5, a zero-carbon high-speed energy consumption and carbon reduction dynamic perception intelligent monitoring device is characterized in that: The energy consumption analysis module includes an energy unit conversion module, a total energy consumption calculation module and an energy consumption trend prediction module; The energy unit conversion module is used to convert all energy consumption data into a unified energy unit using an energy conversion coefficient, wherein the energy conversion coefficient includes an electric energy conversion coefficient, a diesel conversion coefficient, and a natural gas conversion coefficient; The total energy consumption calculation module is used to calculate the total energy consumption based on the converted energy consumption data; The energy consumption trend prediction module is used to perform trend prediction based on historical energy consumption data using a time series model; The trend forecasting based on the historical energy consumption data using the time series model includes: Use the difference algorithm to pre-process the historical energy consumption data; Determine the time series model parameters based on the partial autocorrelation function and the autocorrelation function; Use the maximum likelihood estimation method to estimate the model optimization parameters; Based on the optimized time series model, future energy consumption data is predicted.

7. According to claim 5, a zero-carbon high-speed energy consumption and carbon reduction dynamic perception intelligent monitoring device is characterized in that: According to the electricity consumption and the electricity carbon emission factor, the expression for analyzing carbon emissions is: ； In the formula, C1 is the carbon emission of electricity, E 电 is the power consumption, f 电 is the carbon emission factor of electricity, γ env is the environmental impact factor, obtained by weighted average of three key indicators; The expression of the environmental impact factor obtained by weighted average of the three key indicators is: ； Where CI is the climate adaptability index, PCE is the pollution control efficiency coefficient, ESR is the energy structure response factor, and w1, w2 and w3 are the weights corresponding to the climate adaptability index, pollution control efficiency coefficient and energy structure response factor, respectively.

8. According to claim 5, a zero-carbon high-speed energy consumption and carbon reduction dynamic perception intelligent monitoring device is characterized in that: The energy-saving optimization module includes an energy consumption pattern recognition module, an energy consumption factor analysis module, a linear programming model building module and an optimal energy-saving path search module: The energy consumption pattern recognition module is used to recognize different energy consumption patterns and behavior characteristics by using a clustering algorithm; The energy consumption factor analysis module is used to analyze the main factors affecting energy consumption and determine high energy consumption points based on a decision tree algorithm; The linear programming model building module is used to use a linear programming algorithm to build a multi-objective linear programming model and output a carbon reduction optimization plan; The optimal energy-saving path search module is used to find the optimal energy-saving path based on the carbon reduction optimization plan using a genetic algorithm to generate energy-saving and emission reduction suggestions.

9. A zero-carbon high-speed energy consumption and carbon reduction dynamic perception intelligent monitoring device according to claim 8, characterized in that: The linear programming algorithm is used to establish a multi-objective linear programming model, and the output of the carbon reduction optimization plan includes: Establish an objective function with the goal of minimizing energy consumption costs and carbon emissions; Determine constraints based on power supply capacity and equipment load; Based on the objective function and constraints, a multi-objective linear programming model is established, and then the multi-objective linear programming model is solved to obtain the carbon reduction optimization plan.

10. The zero-carbon high-speed energy consumption and carbon reduction dynamic perception intelligent monitoring device according to claim 8 is characterized in that: The carbon reduction optimization scheme is based on the use of genetic algorithms to find the optimal energy-saving path and generate energy-saving and emission reduction suggestions, including: Based on the carbon reduction optimization plan, an initial population is generated, wherein each individual in the initial population represents an energy-saving and emission-reduction path; Define the fitness function based on energy consumption cost and carbon emissions; According to the fitness function, the crossover rate and mutation rate are dynamically adjusted to generate the next generation population; Select the individual with the highest fitness as the optimal energy-saving and emission-reduction path, and output the selection result.

Images