A smart regulation system based on resource and environment data

Abstract

The present invention discloses an intelligent regulation system based on resource and environmental data, which relates to the field of energy management. The intelligent regulation system includes: obtaining energy consumption data at highway locations and generating energy regulation instructions according to the energy consumption data and data processing technology; monitoring carbon emission data during highway operation and dynamically adjusting the energy regulation instructions based on the carbon emission data and linkage control technology; monitoring environmental parameters at highway locations and combining the environmental parameters with fuzzy inference technology to adjust the usage status of operating equipment at highway locations; optimizing the operation strategy at highway locations according to real-time energy consumption data, carbon emission data and environmental parameters to achieve intelligent energy regulation. The present invention integrates functions in multiple aspects such as energy management, carbon emission monitoring and environmental monitoring for the highway system, and realizes real-time dynamic monitoring and intelligent regulation of energy, carbon emissions and environmental conditions.

Description

Technical Field

[0001] The present invention relates to the field of energy management, and more specifically, to an intelligent regulation system based on resource and environmental data. Background Art

[0002] With the rapid development of technology and continuous progress of society, environmental protection and energy conservation have become hot issues of concern to people. In this context, in order to improve energy utilization efficiency, reduce carbon emissions, and improve the environmental situation, the research and development of intelligent management systems for the road transportation field (especially the highway system) has become particularly important. These systems not only need to be able to monitor energy consumption and carbon emissions in real time, but also need to be able to intelligently regulate under different circumstances to achieve optimal energy efficiency and the lowest environmental impact.

[0003] The existing intelligent energy management system (EMS) has the ability to monitor and manage energy consumption in a building or area. It mainly collects energy usage data (such as electricity, water, and natural gas consumption) and environmental parameters (such as temperature and humidity) in real time through a sensor network distributed in the monitoring area, receives the data collected by the sensor network, conducts data analysis and processing, and based on the data processing results, optimizes and adjusts energy usage by controlling electrical appliances or system operations. It provides an interface for users to query data and receive notifications according to the analysis results, and at the same time allows users to set energy usage strategies.

[0004] However, although the above solution is helpful in energy management, its main drawbacks are: lack of refined management of the specific environment and conditions of highways, and lack of targeted solutions in carbon emission calculation and environmental monitoring, unable to comprehensively cover the environmental impact of highways, often lacking the ability to sensitively adjust to environmental changes, unable to respond in a timely manner to the impact of environmental changes on energy demand, resulting in inefficient energy utilization and energy waste.

[0005] At the same time, traditional environmental monitoring technologies rely on fixed monitoring stations, which cannot comprehensively cover, and the data update frequency is low, making environmental data lack timeliness and accuracy, difficult to provide effective support for energy management and environmental protection, and the control of carbon emissions is inaccurate, lacking an effective real-time carbon emission monitoring and management mechanism, with insufficient reliability and accuracy, and thus unable to effectively control and reduce carbon emissions, posing challenges to environmental protection and sustainable development.

[0006] For the problems in the related technologies, no effective solutions have been proposed yet. Summary of the Invention

[0007] In view of the problems in the related technologies, the present invention proposes an intelligent regulation system based on resource and environmental data to overcome the above-mentioned technical problems existing in the existing related technologies.

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

[0009] A smart regulation system based on resource and environmental data, the smart regulation system includes:

[0010] An energy management unit, configured to obtain energy consumption data at a highway and generate an energy regulation instruction according to the energy consumption data and data processing technology;

[0011] A carbon emission monitoring unit, configured to monitor carbon emission data during the operation of the highway and dynamically adjust the energy regulation instruction based on the carbon emission data and linkage control technology;

[0012] An environment perception unit, configured to monitor environmental parameters at the highway and combine the environmental parameters with fuzzy inference technology to adjust the usage status of operating equipment at the highway;

[0013] A central control unit, configured to optimize the operation strategy at the highway according to real-time energy consumption data, carbon emission data and environmental parameters, and achieve intelligent energy regulation.

[0014] Preferably, the energy management unit includes:

[0015] A sensor network deployment module, configured to deploy energy information sensors within the highway area and collect energy consumption data of the highway by using the energy information sensors;

[0016] An energy data processing module, configured to perform denoising and filtering processing on the energy consumption data, construct an energy consumption prediction model, and output an energy predicted consumption based on the energy consumption prediction model;

[0017] A decision instruction formulation module, configured to determine energy adjustment parameters according to the energy predicted consumption and energy usage requirements, and calculate an adjustment control instruction based on the energy adjustment parameters and a control algorithm;

[0018] An instruction execution control module, configured to receive the adjustment control instruction by using an actuator and regulate the operation status of the energy usage equipment according to the adjustment control instruction.

[0019] Preferably, the environment perception unit includes:

[0020] An environment data processing module, configured to collect environmental data at the highway through an environment sensor network and perform preprocessing operations on the environmental data by using denoising processing technology;

[0021] An environment data fusion module, configured to fuse environmental data by using Kalman filtering technology, determine environmental parameters based on the fusion result, and evaluate the environmental condition at the highway according to the environmental parameters;

[0022] A fuzzy rule determination block, which is used to generate a fuzzy set based on the error between the evaluation result of the environmental condition and the preset environmental condition value, and determine fuzzy rules based on the fuzzy set and the actual control requirements;

[0023] An operating device regulation module, which is used to perform fuzzy inference based on fuzzy rules and fuzzy sets to generate a fuzzy output, and convert the fuzzy output into an actual control quantity to adjust the usage status of the operating devices at the highway.

[0024] Preferably, the central control unit includes:

[0025] A data receiving module, which is used to receive the real-time energy usage data, carbon emission data and environmental data collected by the energy information sensor, energy consumption sensor and environmental sensor, and generate real-time operation data;

[0026] A comprehensive analysis module, which is used to perform a comprehensive analysis on the real-time operation data by using a data analysis algorithm, and identify abnormal operation conditions and regulation optimization space at the highway based on the comprehensive analysis result;

[0027] A strategy formulation module, which is used to formulate an energy dispatch and carbon emission control strategy based on the abnormal operation conditions and regulation optimization space to achieve the purpose of dynamically allocating energy;

[0028] A control instruction generation module, which is used to convert the energy dispatch and carbon emission control strategy into control instructions, and dynamically adjust the operation parameters of the energy management unit and the carbon emission monitoring unit based on the control instructions.

[0029] Preferably, performing a comprehensive analysis on the real-time operation data by using a data analysis algorithm, and identifying abnormal operation conditions and regulation optimization space at the highway based on the comprehensive analysis result includes:

[0030] Generating a linear relationship expression between the real-time operation data and the abnormal operation conditions at the highway by using a Bayesian framework structure and a preset parameter vector;

[0031] Introducing a sparse prior operation to the preset parameter vector, and optimizing the hyperparameter for controlling sparsity by maximizing the marginal approximation function during the sparse prior process;

[0032] Solving for the optimal hyperparameter based on an iterative optimization process, and obtaining an updated linear relationship expression of the sparse completed parameter vector based on the optimal hyperparameter;

[0033] Taking the real-time operation data as an input matrix and inputting it into the linear relationship expression to obtain the abnormal operation conditions at the highway, and analyzing the regulation optimization space of energy monitoring and carbon emission monitoring according to the abnormal operation conditions.

[0034] Preferably, based on abnormal operating conditions and the space for regulation and optimization, formulating energy dispatch and carbon emission control strategies to achieve the goal of dynamically allocating energy includes:

[0035] After obtaining the energy usage, carbon emission level, and environmental parameters based on abnormal operating conditions, define the state vector space, and define the action vector space of the available regulation actions according to the regulation and optimization space;

[0036] Based on the action vector and the state vector, define the reward function to judge the advantages and disadvantages of the energy dispatch and carbon emission control strategies, and use the deep neural network approximation technology to map the state vector space to the action vector space to generate the policy function;

[0037] Based on the reward function, define the objective function, and use the policy gradient method and the policy function to update the parameters of the deep neural network approximation technology to maximize the objective function;

[0038] According to the maximized objective function, find the optimal regulation actions that can be taken in the regulation and optimization space to generate the optimization strategies for energy dispatch and carbon emission control, so as to achieve the goal of dynamically allocating energy.

[0039] Preferably, the expression of the maximized objective function is:

[0040] ;

[0041] In the formula, represents the gradient of the objective function J(π) with respect to the parameter θ, logπ(a t ∣s t ;θ) represents the logarithmic probability of the policy function π for the action vector a t at the state vector s t , E represents the expectation, ρ π represents the interior of the state under the policy function π, s t represents the state vector, a t represents the action vector, π represents the policy function, θ represents the neural network parameter, R t′ represents the cumulative reward from the time step t to the future, γ represents the discount factor, t′ represents the time period from the time step t to the future, and T represents the maximum value of the time step.

[0042] Preferably, the control instruction generation module includes:

[0043] An optimization strategy parsing sub-module, which is used to parse the energy dispatch and carbon emission control optimization strategies into the execution tasks required by the energy management unit and the carbon emission monitoring unit;

[0044] The instruction generation selector module is used to calculate control signals after selecting a control mode according to the nature of the execution task, and perform digital-to-analog conversion and encapsulation operations on the control signals to generate control instructions;

[0045] The control instruction distribution sub-module is used to perform encryption processing on the control instructions and distribute them to the corresponding units;

[0046] The execution feedback adjustment module is used to monitor the execution status of the control instructions, start corrective instructions when abnormal execution status is found, dynamically adjust the control instructions, and analyze the energy and carbon emission status after adjustment according to the execution status analysis strategy.

[0047] Preferably, calculating control signals after selecting a control mode according to the nature of the execution task, and performing digital-to-analog conversion and encapsulation operations on the control signals to generate control instructions includes:

[0048] Select a corresponding control mode based on the nature of the execution task, set the parameters of the control mode, and calculate specific control signals according to the control mode and strategy requirements;

[0049] Convert the control signal into an analog signal through digital-to-analog conversion technology, and after performing amplification and filtering processing on the analog signal, convert the analog signal into a binary coding format;

[0050] Perform protocol encapsulation and packing processing on the binary signal according to the pre-set communication protocol to convert it into a parameterized control instruction, and append an error detection code at the end of the control instruction;

[0051] Configure an acknowledgement mechanism for the control instruction, use the acknowledgement mechanism to detect whether the feedback control instruction is received and executed by the energy management unit and the carbon emission monitoring unit during subsequent distribution, and adjust the control instruction distribution sub-module according to the feedback result.

[0052] Preferably, performing encryption processing on the control instructions and distributing them to the corresponding units includes:

[0053] Generate an additional check code based on the control instruction, encrypt the control instruction and the additional check code using an encryption algorithm to generate a key, and distribute the key to the energy management unit and the carbon emission monitoring unit through a secure channel;

[0054] Use a real-time communication protocol to send and transmit the control instruction, and deploy a firewall at the relay node in the transmission path to detect the status of the instruction transmission;

[0055] After the energy management unit and the carbon emission monitoring unit receive the corresponding encrypted control instructions, use the acknowledgement mechanism to feedback instruction reception confirmation information to the instruction generation selector module;

[0056] The energy management unit and the carbon emission monitoring unit decrypt the control instruction and the additional check code according to the secret key, recalculate the check code of the decrypted control instruction, compare the additional check code with the check code, and verify the consistency of the control instruction;

[0057] If the check codes are consistent, it means the control instruction can be executed. If the check codes are inconsistent, the control instruction is rejected and feedback to the central control unit to regenerate the control instruction.

[0058] The beneficial effects of the present invention are:

[0059] 1. The present invention is aimed at the highway system, which not only integrates the functions of energy management, carbon emission monitoring, environmental monitoring and other aspects, but also realizes the real-time dynamic monitoring and intelligent regulation of energy, carbon emissions and environmental conditions by using advanced deep learning algorithms and Internet of Things technologies, in order to achieve higher energy efficiency and environmental protection effects.

[0060] 2. The present invention realizes the real-time prediction and adjustment of energy demand by integrating dynamic environment perception and intelligent regulation technologies, improves energy use efficiency, reduces waste, and at the same time introduces advanced sensor networks and data processing technologies to realize the comprehensive and real-time monitoring of environmental conditions, ensure the accuracy and real-time nature of environmental data, and accurately monitor and control carbon emissions by establishing a real-time carbon emission monitoring system and supporting management strategies, providing a scientific basis for carbon emission reduction. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required to be used in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0062] Figure 1 is a schematic block diagram of a smart regulation system based on resource and environmental data according to an embodiment of the present invention;

[0063] Figure 2 is an architecture diagram of an energy management unit in a smart regulation system based on resource and environmental data according to an embodiment of the present invention;

[0064] Figure 3 is a processing flow chart of an energy management unit in a smart regulation system based on resource and environmental data according to an embodiment of the present invention;

[0065] Figure 4 is a control execution flow chart of an energy management unit in a smart regulation system based on resource and environmental data according to an embodiment of the present invention;

[0066] Figure 5 It is the architecture diagram of the carbon emission monitoring unit in a smart regulation system based on resource and environment data according to an embodiment of the present invention;

[0067] Figure 6 It is the analysis flow chart of the carbon emission monitoring unit in a smart regulation system based on resource and environment data according to an embodiment of the present invention;

[0068] Figure 7 It is the architecture diagram of the environment perception unit in a smart regulation system based on resource and environment data according to an embodiment of the present invention;

[0069] Figure 8 It is the processing flow chart of the environment perception unit in a smart regulation system based on resource and environment data according to an embodiment of the present invention;

[0070] Figure 9 It is the architecture diagram of the central control unit in a smart regulation system based on resource and environment data according to an embodiment of the present invention.

[0071] In the figure:

[0072] 1. Energy management unit; 2. Carbon emission monitoring unit; 3. Environment perception unit; 4. Central control unit. Specific embodiments

[0073] To further illustrate each embodiment, the present invention provides accompanying drawings, which are part of the disclosure of the present invention. They 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, those of ordinary skill in the art should be able to understand other possible implementation manners and the advantages of the present invention.

[0074] According to an embodiment of the present invention, a smart regulation system based on resource and environment data is provided.

[0075] Now, the present invention will be further described in combination with the accompanying drawings and specific embodiments. As Figure 1 shown, the smart regulation system based on resource and environment data according to an embodiment of the present invention includes:

[0076] An energy management unit 1, configured to obtain energy consumption data at a highway and generate an energy regulation instruction according to the energy consumption data and data processing technology.

[0077] In this embodiment, the energy management unit 1 includes:

[0078] A sensor network deployment module, configured to deploy energy information sensors within the highway area and collect the energy consumption data of the highway by using the energy information sensors;

[0079] An energy data processing module, which is used to perform denoising and filtering on energy consumption data, construct an energy consumption prediction model, and output the predicted energy consumption based on the energy consumption prediction model;

[0080] A decision instruction formulation module, which is used to determine energy adjustment parameters according to the predicted energy consumption and energy usage requirements, and calculate an adjustment control instruction based on the energy adjustment parameters and a control algorithm;

[0081] An instruction execution control module, which is used to receive the adjustment control instruction by using an actuator, and regulate the operating state of the energy usage equipment according to the adjustment control instruction.

[0082] As Figure 2 shown, it should be noted that the main function of the energy management unit 1 is to monitor and manage the energy usage of the highway, and achieve real-time optimal regulation of energy.

[0083] Specific energy information sensors mainly include a current sensor (used to monitor power usage and record current changes in real time), a water flow meter (used to monitor water resource consumption and record water flow data in real time), etc. The current sensor and the water flow meter are deployed at key nodes of the highway, such as toll stations, power distribution stations, service areas, etc., to ensure that key areas of energy consumption can be fully covered, and the energy consumption data of the highway, including power usage and water resource consumption, can be collected in real time.

[0084] Perform preprocessing such as denoising and filtering on the collected energy consumption data to ensure the accuracy and effectiveness of the data. At the same time, the Kalman filtering algorithm is used for data fusion to improve the accuracy of the data.

[0085] At the same time, a linear regression model is used to analyze the influence of various factors on energy consumption, and a prediction model of energy consumption is established. Its mathematical formula is: E = β0 + β1X1 + β2X2 + … + β n X n ; where E is the energy consumption, X1, X2, …, X n are the factors affecting energy consumption, and β 0、 β 1、 …, β n are the regression coefficients.

[0086] Use a time series analysis model to predict future energy consumption. A commonly used model is the autoregressive integrated moving average (ARIMA) model. Its mathematical formula is: ; where Y t is the energy consumption value at time t, is the error term, and α, δ, γ are the model parameters.

[0087] Based on the data analysis results, the proportional-integral-derivative (PID) control algorithm is used to adjust energy usage to ensure real-time optimization of energy usage. The mathematical formula of the PID control algorithm is:

[0088] ;

[0089] where u(t) is the control variable, e(t) is the error (the difference between the actual energy usage and the expected usage), K p , K i and K d are the proportional, integral, and derivative gains respectively; is the derivative of the error with respect to time, representing the rate of change of the error over time, is the cumulative error from 0 to t, representing the sum of past errors.

[0090] Specifically, as shown in Figure 3 and Figure 4 , the processing flow of the energy management unit 1 is as follows:

[0091] Step 1: Data collection: Real-time collect the energy consumption data of the highway through the sensor network to ensure the real-time and comprehensiveness of the data.

[0092] Step 2: Data preprocessing: Perform preprocessing such as denoising and filtering on the collected data to improve the accuracy and reliability of the data. For example, use the Kalman filter algorithm to fuse multi-source data to obtain more accurate energy consumption data.

[0093] Step 3: Data analysis: Use the linear regression model and time series analysis model to analyze and predict the preprocessed data. The linear regression model is used to analyze the influence of various factors on energy consumption and establish a prediction model for energy consumption; the time series analysis model is used to predict future energy consumption.

[0094] Step 4: Decision-making: Based on the data analysis results, formulate an energy usage optimization strategy. For example, by analyzing historical data and predicting future energy demands, determine the optimal energy allocation plan and generate specific control instructions.

[0095] Step 5: Execution and control: Adjust the energy usage according to the formulated optimization strategy to ensure the efficient utilization and real-time optimization of energy. For example, use the PID control algorithm to adjust the energy allocation in real time according to the actual energy usage situation to reduce energy waste.

[0096] Specifically, the control actuator receives the analysis results and optimization strategies. Based on the received data and strategies, it uses the PID control algorithm to calculate specific control instructions, determines the energy usage parameters that need to be adjusted, and according to the calculation results, controls the execution unit to adjust the operating state of the energy usage equipment through the actuator to achieve real-time optimization control.

[0097] Detailed description of the PID control algorithm:

[0098] Proportional control (P): According to the magnitude of the current error, directly adjust the control quantity. The advantage of proportional control is rapid response, but when used alone, it may produce a steady-state error. Specifically: uP(t) = K p e(t), where e(t) is the error and K p is the proportion, and uP(t) is the proportional control quantity;

[0099] Integral control (I): Accumulate the error and eliminate the steady-state error by eliminating the accumulated error. The advantage of integral control is that it can eliminate the steady-state error, but the response is slow and may cause oscillations. Specifically:

[0100] ;

[0101] where e(t) is the error, K i is the proportional integral, uI(t) is the integral control quantity, is the error accumulation from 0 to t, representing the sum of past errors.

[0102] Derivative control (D): Control the rate of change of the error, which can improve the response speed and stability of the system. The advantage of derivative control is that it can predict the change trend of the error, but it is sensitive to noise. Specifically:

[0103] ;

[0104] where uD(t) is the derivative control quantity, K d is the integral, is the derivative of the error with respect to time, representing the rate of change of the error over time.

[0105] Furthermore, through the combined action of proportional, integral, and derivative controls, the PID control algorithm can achieve precise regulation of energy usage, ensuring the stability and response speed of the system.

[0106] The carbon emission monitoring unit 2 is used to monitor the carbon emission data during the operation of the highway and dynamically adjust the energy regulation instructions based on the carbon emission data and linkage control technology.

[0107] Such as Figure 5As shown in the figure, it should be noted that the main function of the carbon emission monitoring unit 2 is to monitor in real time the carbon emissions generated during highway operation due to power consumption, fuel use, air-conditioning operation, etc., provide detailed carbon emission data, and link with the energy management module to formulate emission reduction strategies.

[0108] The carbon emission data during highway operation is obtained through energy consumption sensors, specifically including power sensors (used to monitor the power usage of each node on the highway), fuel sensors (used to monitor the fuel usage of highway maintenance vehicles and power generation equipment), air-conditioning sensors (used to monitor the air-conditioning usage in highway service areas and control centers), etc. These sensors are installed at key equipment and facilities on the highway, such as street lights, monitoring equipment, service areas, and control centers.

[0109] The collected data includes power consumption data (the power usage of street light illumination, monitoring equipment, electric toll systems, etc.), fuel consumption data (the fuel usage of maintenance vehicles, standby generators, etc.), air-conditioning usage data (the air-conditioning operation in service areas, control centers, etc.).

[0110] Data preprocessing: Preprocess the data collected by the sensors, such as denoising and filtering, to ensure the accuracy and reliability of the data, and then obtain the carbon emission calculation model, which is as follows:

[0111] Carbon emissions from power consumption: YCO2 = Electricity × Emission Factor;

[0112] Among them, YCO2 is the carbon emissions from power consumption, Electricity is the power consumption, and Emission Factor is the emission factor of electricity.

[0113] Carbon emissions from fuel use: TCO2 = Fuel × Fuel Emission Factor;

[0114] Among them, TCO2 is the carbon emissions from fuel use, Fuel is the fuel usage, and Fuel Emission Factor is the emission factor of fuel.

[0115] Carbon emissions from air-conditioning use: RCO2 = AC Energy × Emission Factor;

[0116] Among them, RCO2 is the carbon emissions from air-conditioning use, AC Energy is the energy consumption of the air-conditioning, and EmissionFactor is the corresponding emission factor.

[0117] Meanwhile, use the linear regression model to analyze the impact of different factors on carbon emissions. The specific calculation formula is: L = ο0 + ο1M1 + ο2M2 +... + ο n M n ;

[0118] where L is the carbon emission, M1, M2,..., M n are the influencing factors, and ο0, ο1,..., ο n are the regression coefficients.

[0119] Use the ARIMA model to predict carbon emissions. Specifically: W t = a + bC t-1 + fd t-1 + d t ; In the formula, W t is the carbon emission at time t, d t is the error term, and a, b, f are the model parameters.

[0120] Specifically, based on the analysis results, cooperate with the energy management unit 1, and adopt a feedback control algorithm to dynamically adjust energy use to reduce carbon emissions. The feedback control algorithm is:

[0121] ;

[0122] In the formula, G(t) is the control strategy, L k is the expected carbon emission, L is the actual carbon emission, K p , K i and K d are the proportional, integral, and differential gains respectively.

[0123] Based on the data analysis results, adjust the energy use strategy, such as optimizing power dispatching, improving fuel use efficiency, and improving air conditioning use plans, and monitor and feedback adjust in real time to ensure that the carbon emissions are kept within the set target range.

[0124] Specifically, as shown in Figure 6 , the processing flow of the carbon emission monitoring unit 2 is as follows:

[0125] Step 1, data collection: Real-time collect data such as power, fuel, and air conditioning operation through energy consumption sensors.

[0126] Step 2, data cleaning: Clean the collected data through denoising, filtering, etc. to ensure the accuracy of the data.

[0127] Step 3, data analysis: Analyze and calculate the data using the carbon emission calculation models for power, fuel, and air conditioning use.

[0128] Step 4. Report Generation: Generate a detailed carbon emission report to provide support for decision-making. These reports include carbon emission data for each energy usage link, helping managers identify high-emission links and take corresponding optimization measures.

[0129] Step 5. Linkage Control: Based on the carbon emission data, adjust the energy management strategy to achieve dynamic regulation, and through collaborative work with the energy management module, ensure that the overall carbon emissions meet environmental protection requirements.

[0130] The environmental perception unit 3 is used to monitor the environmental parameters at the highway and combine the environmental parameters with fuzzy inference technology to adjust the usage status of the operating equipment at the highway.

[0131] In this embodiment, the environmental perception unit 3 includes:

[0132] The environmental data processing module is used to collect the environmental data at the highway through the environmental sensor network and perform preprocessing operations on the environmental data using denoising processing technology;

[0133] The environmental data fusion module is used to fuse the environmental data using Kalman filtering technology, determine the environmental parameters based on the fusion result, and evaluate the environmental conditions at the highway according to the environmental parameters;

[0134] The fuzzy rule determination block is used to generate a fuzzy set based on the error between the environmental condition evaluation result and the preset environmental condition value, and determine the fuzzy rules based on the fuzzy set and the actual control requirements;

[0135] The operating equipment regulation module is used to perform fuzzy inference based on the fuzzy rules and the fuzzy set to generate a fuzzy output, and convert the fuzzy output into an actual control quantity to adjust the usage status of the operating equipment at the highway.

[0136] Specifically, as Figure 7 shown, it should be explained that the environmental sensor network includes temperature and humidity sensors (detecting the temperature and humidity of the surrounding environment) and air quality sensors (detecting the concentrations of pollutants such as PM2.5, PM10, CO2, NO2, SO2 in the air), etc. The sensors are installed along the highway and its surrounding areas, including locations such as tunnels, bridges, toll stations, and service areas, to ensure the comprehensiveness and representativeness of the data. The environmental parameter data, including temperature, humidity, PM2.5 concentration, PM10 concentration, CO2 concentration, NO2 concentration, SO2 concentration, etc., are collected in real time using the sensor network.

[0137] Perform preprocessing such as denoising and filtering on the collected data to ensure the accuracy and stability of the data. Commonly used methods include moving average filtering, median filtering, etc. At the same time, use the Kalman Filter to achieve multi-source data fusion, improving the reliability and accuracy of the data. The specific mathematical formula of the Kalman Filter is as follows:

[0138] ;

[0139] In the formula, is the state estimate value at the current time k, K k is the Kalman gain, Z k is the observation value at the current time k, and H is the observation matrix. is the state estimate value at the previous time k - 1.

[0140] Through the Kalman Filter, data from different sensors can be effectively fused to obtain a more accurate estimate of the environmental parameters. The specific Kalman Filter is a recursive estimation algorithm based on the state space model, which can perform optimal estimation on dynamic systems in a noisy environment. Its basic steps include:

[0141] (1) Prediction step:

[0142] ;

[0143] ;

[0144] (2) Update step:

[0145] ;

[0146] ;

[0147] ;

[0148] In the formula, is the predicted state estimate, is the predicted covariance matrix, K k is the Kalman gain, is the updated state estimate, P k∣k is the updated covariance matrix, F is the state transition matrix, B is the control input matrix, Q is the process noise covariance matrix, R is the observation noise covariance matrix, and I is the identity matrix.

[0149] Through the above steps, the Kalman Filter can continuously estimate and update the environmental parameters, providing reliable environmental data support.

[0150] At the same time, the fuzzy control algorithm is adopted to adjust the energy use and carbon emission control strategies according to the environmental data. The fuzzy control algorithm can handle complex and nonlinear systems. By defining fuzzy rules, precise control of the system can be achieved. Its mathematical formula is: p = s(v, Δv), where p is the control output, v is the error, Δv is the error change rate, and s is the fuzzy rule.

[0151] Through the fuzzy control algorithm, the operating parameters of the system can be dynamically adjusted according to environmental changes, optimizing energy use and carbon emission control.

[0152] It should be explained that fuzzy control is a control method based on fuzzy logic, which can handle complex and uncertain systems. Its basic steps include:

[0153] Fuzzification: Fuzzify the input variables (error v and error change rate Δv), that is, map them to fuzzy sets.

[0154] Fuzzy rules: According to the control requirements of the actual system, formulate a series of fuzzy rules. For example:

[0155] If v is positive large and Δv is positive large, then p should be positive large.

[0156] If v is negative large and Δv is negative large, then p should be negative large.

[0157] Inference: According to the fuzzy rules and fuzzy inputs, perform fuzzy inference to obtain a fuzzy output.

[0158] Defuzzification: Convert the fuzzy output into the actual control quantity p.

[0159] Through the fuzzy control algorithm, dynamic regulation of environmental parameters can be achieved, improving the intelligent level and control accuracy of the system.

[0160] Specifically, as Figure 8 shown, the processing flow of the environmental perception unit 3 is as follows:

[0161] Step 1, data collection: Real-time collect the environmental data around the highway through the environmental sensor network to ensure the real-time and comprehensiveness of the data.

[0162] Step 2, data fusion: Use the Kalman filtering algorithm to fuse multi-source data to obtain accurate environmental parameters. The Kalman filter can effectively eliminate noise and improve the reliability of the data.

[0163] Step 3, environmental analysis: Based on the fused environmental data, conduct comprehensive analysis to evaluate the environmental conditions. The analysis content includes the temperature change trend, humidity level, air quality status, etc.

[0164] Step 4. Strategy Optimization: Combine the results of environmental analysis to optimize energy use and carbon emission control strategies. By analyzing the impact of different environmental parameters on energy consumption and emissions, formulate the optimal control strategy.

[0165] Step 5. Feedback Control: According to the optimized strategy, adjust the system operation through the feedback control unit to achieve intelligent management. Specific control measures include adjusting lighting intensity, ventilation system operation mode, vehicle emission control, etc.

[0166] The central control unit 4 is used to optimize the operation strategy at the highway according to real-time energy consumption data, carbon emission data and environmental parameters, and realize intelligent energy control.

[0167] It should be noted that the central control unit 4 is the core of the entire system, responsible for receiving and processing data from the energy management unit 1, carbon emission monitoring unit 2 and environmental perception unit 3. The central control unit 4 uses advanced data processing technologies and intelligent algorithms to comprehensively analyze the data, formulate energy use, carbon emission control and environmental optimization strategies, and perform control operations through each unit to achieve the intelligent management of the system.

[0168] The central control unit 4 is connected to the energy management unit 1, carbon emission monitoring unit 2 and environmental perception unit 3 through a high-speed data communication network to ensure the real-time transmission and processing of data. The central control unit 4 also provides data query, strategy setting and system monitoring functions through the user interface module.

[0169] The data communication network uses high-speed Ethernet or wireless network to ensure the stable and reliable data transmission between each module and the central control unit 4. The user interface module is connected to the central control system through a display screen and an input device for users to operate and monitor.

[0170] As Figure 9 shown, in this embodiment, the central control unit 4 includes:

[0171] A data receiving module, used to receive real-time energy use data, carbon emission data and environmental data collected by the energy information sensor, energy consumption sensor and environmental sensor, and generate real-time operation data.

[0172] A comprehensive analysis module, used to perform a comprehensive analysis on the real-time operation data using data analysis algorithms, and identify abnormal operation conditions and control optimization space at the highway based on the comprehensive analysis results;

[0173] A strategy formulation module, used to formulate energy scheduling and carbon emission control strategies based on abnormal operation conditions and control optimization space to achieve the purpose of dynamically allocating energy;

[0174] The control instruction generation module is used to convert the energy scheduling and carbon emission control strategies into control instructions, and dynamically adjust the operating parameters of the energy management unit and the carbon emission monitoring unit based on the control instructions.

[0175] In this embodiment, when using a data analysis algorithm to perform comprehensive analysis on real-time operation data and identifying abnormal operation conditions and regulation optimization space at highway locations based on the comprehensive analysis results, a linear relationship expression between the real-time operation data and the abnormal operation conditions at highway locations can be generated using a Bayesian framework structure and a preset parameter vector; a sparse prior operation is introduced for the preset parameter vector, and the hyperparameters for controlling sparsity are optimized by maximizing the marginal approximation function during the sparse prior process; the optimal hyperparameters are solved based on the iterative optimization process, and the sparse completed parameter vector is obtained based on the optimal hyperparameters to update the linear relationship expression; the real-time operation data is used as the input matrix and input into the linear relationship expression to obtain the abnormal operation conditions at highway locations, and the regulation optimization space for energy monitoring and carbon emission monitoring is analyzed based on the abnormal operation conditions.

[0176] It should be noted that the comprehensive analysis module can use various data analysis algorithms (such as regression analysis, time series analysis, Kalman filtering, etc.) to perform comprehensive analysis on the data, identify abnormal situations and optimization space, and introduce Sparse Bayesian Learning (SBL) for data analysis and strategy formulation. This method is more flexible than traditional regression analysis and Kalman filtering, can effectively handle high-dimensional data and sparse data, and has stronger prediction ability and model interpretability.

[0177] SBL is a machine learning method based on the Bayesian framework. By introducing a sparse prior, the model can automatically select important features, thereby improving the generalization ability and interpretability of the model. In the energy-carbon-environment system, SBL can be used to extract key features from a large amount of environmental, energy, and carbon emission data, identify abnormal situations, and optimize strategies. The specific steps are as follows:

[0178] Step 1: Assume that there is a linear relationship between the input data X ∈ R n ×p and the output data y ∈ R n : y = Xη + χ; where η ∈ R n is the parameter vector of the model, and χ is a noise term subject to a normal distribution, χ ~ N(0, σ 2 I).

[0179] Step 2: Sparse prior: Introduce a sparse prior for the parameter vector η so that the model can automatically select the most important features:

[0180] ;

[0181] where α = {α1, α2, …, α p} is the hyperparameter for controlling sparsity, p is the number of hyperparameters; η j represents the number of the j-th regression coefficient, and follows a normal distribution with a mean of 0 and a variance of .

[0182] Step 3, Marginal likelihood function: Optimize the hyperparameter α by maximizing the marginal likelihood function:

[0183] ;

[0184] ;

[0185] where represents the marginal likelihood of the target variable y given the hyperparameter α and the noise variance σ 2 , represents the normal distribution with a mean of μ and a covariance matrix of Σ, representing the probability distribution of the variable y, X represents the input feature matrix, T represents the maximum value of the time step, σ 2 represents the noise variance, which is the intensity of the observation noise, I represents the identity matrix, representing the influence of the noise variance σ 2 in the observation.

[0186] Step 4, Parameter estimation: Solve for the optimal α and σ 2 through iterative optimization, so as to obtain the sparse parameter vector η.

[0187] In this embodiment, when formulating an energy dispatch and carbon emission control strategy based on the abnormal operation conditions and the regulation and optimization space to achieve the purpose of dynamically allocating energy, the state vector space can be defined based on the abnormal operation conditions after obtaining the energy usage, carbon emission level, and environmental parameters, and the action vector space can be defined according to the regulation and optimization space by defining the adjustable control actions that can be taken; the reward function is defined based on the action vector and the state vector to judge the advantages and disadvantages of the energy dispatch and carbon emission control strategy, and the state vector space is mapped to the action vector space by using the deep neural network approximation technology to generate the policy function; the objective function is defined based on the reward function, and the parameters of the deep neural network approximation technology are updated by using the policy gradient method and the policy function to maximize the objective function; the optimal adjustable control actions that can be taken are found according to the maximized objective function in the regulation and optimization space to generate the optimization strategy for energy dispatch and carbon emission control, so as to achieve the purpose of dynamically allocating energy.

[0188] It should be noted that during the strategy formulation process, based on the analysis results, energy usage and carbon emission control strategies are automatically formulated to optimize energy allocation and usage. Specifically, deep reinforcement learning (DRL) can be introduced. It continuously interacts with the environment to learn the optimal energy scheduling strategy and carbon emission control strategy. This algorithm is particularly suitable for dealing with decision-making problems in complex dynamic systems, such as highway energy management and carbon emission control. At the same time, deep reinforcement learning combines the advantages of deep learning and reinforcement learning. By approximating the state-action value function or policy function through a neural network, it can find the optimal strategy in a complex high-dimensional state space. In the energy-carbon-environment system, the DRL algorithm can dynamically optimize the allocation and usage of energy to minimize carbon emissions and maximize energy efficiency. The specific content and algorithm steps are as follows:

[0189] Step 1. State space (S): Based on the current energy usage, carbon emission level, environmental parameters, etc., define the state vector as: S t =[E t 、C t 、P t 、A t , where E t is the current energy consumption, C t is the carbon emission level, P t is the energy price, and A t is the environmental parameter (such as temperature, humidity, etc.).

[0190] Step 2. Action space (A): The set of actions that can be taken includes adjusting energy allocation, starting or stopping equipment, switching energy types, etc. Define the action vector as: a t =[△E t 、△C t 、M t , where △E t is the adjusted energy allocation amount, △C t is the adjusted carbon emission amount, and M t is the equipment operation mode.

[0191] Step 3. Reward function (R): Define the reward function R t , which is used to evaluate the quality of the current strategy. The reward function can be designed as a weighted sum of energy usage efficiency and carbon emission control: R t =-αE t -βC t , where α and β are weight coefficients, reflecting different degrees of attention to energy consumption and carbon emissions.

[0192] Step 4. Policy (π): The policy π(S t( ) is a mapping function from the state space to the action space, which is approximated by a deep neural network and is expressed as: a t = π(S t ; θ), where θ are the parameters of the neural network.

[0193] Step Five. Objective Function: The objective of the DRL algorithm is to find the optimal policy by maximizing the cumulative reward, and the expected value of the cumulative reward is expressed as:

[0194] ;

[0195] Step Five. Gradient Update: Use the policy gradient method to update the parameters θ of the neural network to maximize the objective function J(π):

[0196] ;

[0197] In the formula, represents the gradient of the objective function J(π) with respect to the parameter θ, logπ(a t ∣ s t ; θ) represents the logarithmic probability of the policy function π with respect to the action vector a t under the state vector s t , E represents the expectation, ρ π represents the interior of the state under the policy function π, s t represents the state vector, a t represents the action vector, π represents the policy function, θ represents the neural network parameters, R t′ represents the cumulative reward from time step t to the future, γ represents the discount factor, t′ represents the time period from time step t to the future, and T represents the maximum value of the time step.

[0198] In this embodiment, the DRL algorithm can dynamically formulate optimal energy usage and carbon emission control strategies by continuously exploring and exploiting the state space and the action space. For example, when the energy price rises or the carbon emission approaches the upper limit, the system can minimize the cost and carbon emission by adjusting the energy distribution or changing the device operation mode. In addition, the DRL algorithm can adapt to environmental changes and quickly adjust the strategy when the environment changes suddenly (such as extreme weather or energy crisis) to achieve dynamic optimization of energy and carbon emissions.

[0199] In this embodiment, the control instruction generation module includes:

[0200] An optimization strategy parsing sub-module, configured to parse the energy scheduling and carbon emission control optimization strategies into execution tasks required by the energy management unit and the carbon emission monitoring unit;

[0201] The instruction generation selector module is used to calculate control signals after selecting a control mode according to the nature of the execution task, and perform digital-to-analog conversion and encapsulation operations on the control signals to generate control instructions;

[0202] The control instruction distribution sub-module is used to perform encryption processing on the control instructions and distribute them to the corresponding units;

[0203] The execution feedback adjustment module is used to monitor the execution status of the control instructions, start corrective instructions when abnormal execution status is found, dynamically adjust the control instructions, and analyze the energy and carbon emission status after adjustment according to the execution status analysis strategy.

[0204] It should be noted that through the control instruction generation module, the formulated strategy is transformed into specific control instructions, and the operating parameters of the energy management unit 1 and the carbon emission monitoring unit 2 are adjusted to achieve the dynamic regulation and intelligent management of the system.

[0205] In this embodiment, when calculating control signals after selecting a control mode according to the nature of the execution task, and performing digital-to-analog conversion and encapsulation operations on the control signals to generate control instructions, the corresponding control mode can be selected based on the nature of the execution task, and the parameters of the control mode can be set, and specific control signals can be calculated according to the control mode and the strategy requirements; the control signals are converted into analog signals through digital-to-analog conversion technology, and after performing amplification and filtering processing on the analog signals, the analog signals are converted into binary coding format; the binary signals are subjected to protocol encapsulation and packaging processing according to the pre-set communication protocol to be converted into parameterized control instructions, and an error detection code is appended at the end of the control instructions; a confirmation mechanism is configured for the control instructions, and the confirmation mechanism is used to detect whether the feedback control instructions are received and executed by the energy management unit 1 and the carbon emission monitoring unit 2 during the subsequent distribution process, and the control instruction distribution sub-module is adjusted according to the feedback result.

[0206] Specifically, the overall energy use and carbon emission control strategy is decomposed into specific instructions that each module can execute. According to the results generated by the strategy (such as adjusting the energy distribution amount, adjusting the device working mode, etc.), the macro strategy is converted into specific tasks that each module needs to execute, and the complex strategy is further decomposed into sub-tasks that can be executed by a single control instruction. For example, the strategy may require reducing carbon emissions, which can be decomposed into adjusting the input power of the energy management unit 1, controlling the threshold setting of the carbon emission monitoring unit 2, etc.

[0207] Select a suitable control model for each specific control task to ensure the accurate execution of instructions. Based on the nature of the task (such as linear control, non-linear control, optimal control, etc.), select a suitable control model. For example, for temperature control, a PID control model can be used; for energy distribution, optimal control based on a prediction model may be required. Set the parameters of the selected control model to conform to the current system operating state and policy requirements. For example, adjust the proportional, integral, and derivative coefficients of the PID controller.

[0208] Generate specific control instructions from the decomposed tasks and the corresponding control models. Specifically, calculate specific control signals according to the control model and policy requirements. These control signals may include voltage, current, switch status, threshold adjustment, etc.

[0209] Convert the control signals into an instruction format that each module can understand. For example, convert the signal for adjusting voltage into the form of an analog signal, or convert the switch operation instruction into a binary format.

[0210] During the calculation of the control signals, based on the carbon emission data, as well as the external energy usage demand and emission target, and the previously set feedback control model (such as a PID controller), calculate specific control signals. These signals are generated based on the gap between the current carbon emission situation and the target value. Specifically, they may include: voltage adjustment (the control signal for regulating power consumption may involve adjusting the voltage to optimize energy usage efficiency), current control (calculate the required current adjustment signal according to different device load conditions), switch status adjustment (turn on or off certain devices (such as standby generators) to meet different energy demands), threshold adjustment (set new operation thresholds for various sensors and actuators to ensure they operate within the optimal range), etc.

[0211] For control signals that need to adjust voltage or current, specifically, first convert the digital signal into an analog signal through a DAC (Digital-to-Analog Converter). For example, convert the calculated voltage adjustment signal into the corresponding voltage value, which is suitable for driving the analog input of power equipment. In some cases, it may be necessary to amplify or filter the analog signal to ensure that the signal quality meets the required standard. The amplifier and filter can be used to enhance the amplitude of the signal or remove noise.

[0212] For switch operations or other discrete control signals, convert them into a binary coding format. This format is widely used in digital control systems and can ensure the accuracy and reliability of the instructions. At the same time, according to the specific communication protocol (such as Modbus, CAN, RS-485, etc.), encapsulate the binary signal to make it conform to the communication standard. This can ensure that the signal is correctly decoded and executed when transmitted over the network.

[0213] For the threshold setting signal, convert it into a parameterized instruction format. For example, set the operating threshold of a temperature sensor to a certain numerical range, generate an instruction containing this range parameter, and send it to the corresponding sensor or controller. In some intelligent devices, the instruction format may need to be adjusted according to the device's adaptability. For example, some devices can automatically adjust the input format to adapt to different operating conditions, and then adjust the instruction format according to the device's feedback.

[0214] Pack the converted signal according to the communication protocol. The packed content may include: signal type identifier, data field, checksum, start and end flags, etc. If the communication protocol involves multi-level encapsulation (such as the data link layer and network layer in the TCP / IP protocol), it will be encapsulated layer by layer to ensure the integrity and correctness of the instruction during transmission. At the same time, append an error detection code (such as CRC code) at the end of the instruction to detect possible errors during transmission, and configure an acknowledgment mechanism. When the instruction is received and executed by the target unit, the acknowledgment mechanism will send an acknowledgment signal back to the central control unit 4. If the acknowledgment signal is not received or an error occurs, the instruction will be resent to ensure the reliability of the operation.

[0215] In this embodiment, when encrypting the control instruction and sending it to the corresponding unit, an additional checksum can be generated based on the control instruction, and the control instruction and the additional checksum are encrypted using an encryption algorithm to generate a key, and the key is distributed to the energy management unit 1 and the carbon emission monitoring unit 2 through a secure channel; use a real-time communication protocol to send and transmit the control instruction, and deploy a firewall at the relay node in the transmission path to detect the status of the instruction transmission; after the energy management unit 1 and the carbon emission monitoring unit 2 receive the corresponding encrypted control instruction, use the acknowledgment mechanism to feedback the instruction reception acknowledgment information to the instruction generation selection sub-module; the energy management unit 1 and the carbon emission monitoring unit 2 decrypt the control instruction and the additional checksum according to the key, and recalculate the checksum of the decrypted control instruction, compare the additional checksum with the checksum to verify the consistency of the control instruction; if the checksums are consistent, it means the control instruction is executable, if the checksums are inconsistent, the control instruction will be rejected and feedback to the central control unit to regenerate the control instruction.

[0216] It should be noted that the generated control instructions are transmitted to the corresponding execution units, and their execution status is monitored. Specifically, a pair of keys (public key and private key) are first generated and distributed to the relevant control modules through a secure channel. The public key is used for encryption, and the private key is used for decryption. After the control signal is converted into an instruction format, the selected encryption algorithm is used to encrypt the instruction. Even if the encrypted instruction is intercepted during transmission, it cannot be interpreted. At the same time, the keys need to be updated regularly to prevent key leakage and ensure that each module can obtain the updated keys in a timely manner.

[0217] TCP / IP or UDP and other communication protocols suitable for real-time requirements are adopted to ensure the accurate transmission of instructions, monitor the status of data transmission in real time, detect whether there is abnormal traffic or potential attacks, and take appropriate countermeasures when problems are found. At the same time, firewalls are deployed at the relay nodes on the transmission path to further protect the security of data transmission.

[0218] Specifically, before encrypting the instruction, a checksum is generated and appended to the encrypted data. This checksum will be used for integrity verification after transmission. After receiving the encrypted instruction, the target execution unit uses the private key to decrypt it to obtain the original control instruction and the checksum, and then recalculates the checksum of the decrypted instruction and compares it with the checksum attached during transmission. If the checksums are consistent, it means the instruction has not been tampered with and can be executed; otherwise, it is refused to be executed and feedback is sent to the central control unit 4. If the consistency verification fails, the execution unit should immediately send a warning message to the central control unit 4 and request the retransmission of the instruction, and the control strategy can be dynamically adjusted according to the feedback situation.

[0219] At the same time, a real-time dynamic key update mechanism can also be implemented to ensure that the keys are not outdated and effectively prevent malicious attacks. A sound instruction retransmission strategy is established. When the network transmission is interrupted or the instruction execution fails, it will be automatically retransmitted to ensure successful execution.

[0220] During the process of instruction transmission, the control instructions are transmitted to the corresponding execution units through a high-speed data communication network (such as Ethernet, wireless network). This process needs to ensure the integrity and timeliness of the data.

[0221] After the execution unit executes the instruction, the feedback data is returned to the central control unit 4 for monitoring the execution status and adjusting the strategy. For example, if the energy management unit 1 does not adjust the power as expected, a new instruction will be recalculated and issued immediately. It is necessary to ensure that the instruction is correctly executed and necessary adjustments are made according to the feedback information.

[0222] Meanwhile, the status of the execution unit is monitored in real time to ensure that instructions are executed correctly. If an anomaly is detected or the instruction fails to achieve the expected effect, the system will automatically issue a corrective instruction. Based on the execution results and feedback information, the strategy is dynamically adjusted. For example, if the carbon emission monitoring unit 2 feedback shows that the carbon emissions are still exceeding the standard, the energy allocation may be further reduced or the operating frequency of the equipment may be increased.

[0223] Analyze the feedback data of the execution unit to confirm whether the various strategic objectives are achieved. For example, analyze whether the energy usage data and carbon emission data meet the expectations. If the execution effect is not ideal, the optimization algorithm will be triggered for secondary regulation, and the control instruction will be regenerated and issued to ensure the ultimate realization of the strategic objectives.

[0224] Through the organic combination and intelligent regulation of the above units, the intelligent regulation system based on resource and environmental data in this embodiment can significantly improve the energy utilization efficiency of highways, reduce carbon emissions, enhance environmental protection performance, and achieve sustainable development.

[0225] Therefore, this embodiment shows the connection relationship between the energy management unit 1, the carbon emission monitoring unit 2, the environmental perception unit 3 and the central control unit 4. Through the close integration of multiple functional units, comprehensive monitoring and intelligent regulation of highway energy usage, carbon emissions and environmental impacts are achieved. Each unit operates independently to complete specific tasks, and data is aggregated, processed and decisions are made through the central control unit 4 to ensure the efficient, stable and intelligent operation of the system.

[0226] In summary, by means of the above technical solutions of the present invention, the present invention integrates three units of energy management, carbon emission monitoring and environmental perception to form an intelligent regulation system based on resource and environmental data, realizing real-time monitoring and intelligent management of highway energy use, carbon emissions and environmental conditions. Combining the innovation points of each unit and the coordinated operation of the central control unit, it shows significant advantages in solving the defects of the existing technology. Through real-time monitoring and data analysis of the energy management unit 1, linear regression models and time series analysis are used for energy use prediction and optimization regulation, significantly improving energy utilization efficiency and reducing waste. Through the PID control algorithm, the system can adaptively adjust according to real-time data, ensuring the dynamic optimization ability of energy management. The carbon emission monitoring unit 2 uses advanced carbon emission sensors and data analysis models to monitor the carbon emissions of highways in real time and accurately, calculates the carbon emissions using the emission factor model, and is linked with the energy management unit 1 to achieve dynamic regulation of carbon emissions through the feedback control algorithm, effectively reducing carbon emissions and contributing to environmental protection and sustainable development. Finally, the environmental perception unit 3 collects data such as temperature, humidity, and air quality in real time through a variety of environmental sensors, uses the Kalman filtering algorithm for multi-source data fusion to ensure the accuracy and reliability of environmental data, combines the fuzzy control algorithm, comprehensively analyzes environmental parameters, optimizes energy use and carbon emission control strategies, and improves the intelligent level of the system.

[0227] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A smart regulation system based on resource and environment data, characterized in that Including: An energy management unit, configured to obtain energy consumption data at a highway and generate an energy regulation instruction according to the energy consumption data and data processing technology; A carbon emission monitoring unit; An environment perception unit, configured to monitor environmental parameters at a highway and combine the environmental parameters with fuzzy inference technology to adjust the usage status of operating equipment at the highway; A central control unit, configured to optimize the operation strategy at a highway according to real-time energy consumption data, carbon emission data and environmental parameters to achieve intelligent energy regulation; including: Obtaining a linear relationship expression between real-time operation data and abnormal operation conditions at a highway based on a Bayesian framework and a sparse prior; inputting the real-time operation data as an input matrix into the linear relationship expression to obtain the abnormal operation conditions at the highway, and analyzing the regulation and optimization space of energy monitoring and carbon emission monitoring according to the abnormal operation conditions; Obtaining a parameter information-defined state vector space based on the abnormal operation conditions, and performing a mapping process on the state vector space by combining the regulation and optimization space and an approximation technology to generate a policy function; defining an objective function based on a reward function, and updating the parameters of the deep neural network approximation technology by using a policy gradient method and the policy function to maximize the objective function; The expression for maximizing the objective function is: where denotes the gradient of the objective function J(π) with respect to the parameter θ, logπ(a t |s t ; θ) denotes the log probability of the policy function π for the action vector a t at the state vector s t , E denotes the expectation, ρ π denotes the interior of the state under the policy function π, s t denotes the state vector, a t denotes the action vector, π denotes the policy function, θ denotes the neural network parameters, R t′ denotes the cumulative reward from time step t to the future, γ denotes the discount factor, t′ denotes the time period from time step t to the future, and T denotes the maximum value of the time step.

2. The intelligent regulation system based on resource and environmental data according to claim 1, characterized in that, The energy management unit includes: A sensor network deployment module, configured to deploy energy information sensors within a highway area and collect energy consumption data of the highway by using the energy information sensors; An energy data processing module, configured to perform denoising and filtering processing on the energy consumption data and then construct an energy consumption prediction model, and output an energy predicted consumption amount based on the energy consumption prediction model; A decision instruction formulation module, configured to determine an energy adjustment parameter according to the energy predicted consumption amount and the energy usage demand, and calculate an adjustment control instruction based on the energy adjustment parameter and a control algorithm; An instruction execution control module, configured to receive the adjustment control instruction by using an actuator and regulate the operation status of an energy usage device according to the adjustment control instruction.

3. The intelligent regulation system based on resource environment data according to claim 1, wherein The environment perception unit includes: An environment data processing module, configured to collect environment data at a highway through an environment sensor network and perform a preprocessing operation on the environment data by using a denoising processing technology; An environment data fusion module, configured to fuse the environment data by using a Kalman filtering technology, determine environmental parameters based on the fusion result, and evaluate the environmental condition at the highway according to the environmental parameters; A fuzzy rule determination block, configured to generate a fuzzy set according to the error between the environmental condition evaluation result and a preset environmental condition value, and determine fuzzy rules based on the fuzzy set and actual control requirements; an operating equipment regulation module, configured to perform fuzzy inference based on the fuzzy rules and the fuzzy set to generate a fuzzy output, and convert the fuzzy output into an actual control quantity to adjust the usage status of operating equipment at the highway.

4. A smart regulation system based on resource and environment data according to claim 1, characterized in that, The central control unit further includes: A data receiving module, configured to receive real-time energy usage data, carbon emission data and environment data collected by energy information sensors, energy consumption sensors and environment sensors, and generate real-time operation data; A control instruction generation module, which is used to convert the energy scheduling and carbon emission control strategies into control instructions, and dynamically adjust the operating parameters of the energy management unit and the carbon emission monitoring unit based on the control instructions.

5. The intelligent regulation system based on resource and environmental data according to claim 1, characterized in that The expression for the linear relationship between the real-time operation data and the abnormal operation conditions at the highway obtained based on the Bayesian framework and the sparse prior includes: Using the Bayesian framework structure and the preset parameter vector to generate the expression for the linear relationship between the real-time operation data and the abnormal operation conditions at the highway; Introducing a sparse prior operation to the preset parameter vector, and optimizing the hyperparameters for controlling sparsity by maximizing the marginal approximation function during the sparse prior process; Solving for the optimal hyperparameters based on the iterative optimization process, and obtaining the updated parameter vector with sparse completion based on the optimal hyperparameters to update the linear relationship expression.

6. The intelligent control system based on resource environment data according to claim 1, wherein The defining of the state vector space based on the abnormal operation conditions to obtain parameter information, and the mapping process of the state vector space by combining the regulation optimization space and the approximation technology to generate the policy function includes: Defining the state vector space based on the abnormal operation conditions to obtain the energy usage, carbon emission level, and environmental parameters, and defining the action vector space for the available regulation actions according to the regulation optimization space; Defining the reward function based on the action vector and the state vector to judge the advantages and disadvantages of the energy scheduling and carbon emission control strategies, and using the deep neural network approximation technology to map the state vector space to the action vector space to generate the policy function; After defining the objective function based on the reward function, and using the policy gradient method and the policy function to update the parameters of the deep neural network approximation technology to maximize the objective function, it further includes: Finding the optimal regulation actions available in the regulation optimization space according to the maximized objective function to generate the optimization strategy for energy scheduling and carbon emission control, so as to achieve the purpose of dynamically allocating energy.

7. An intelligent regulation system based on resource and environment data according to claim 4, characterized in that, The control instruction generation module includes: An optimization strategy parsing sub-module, which is used to parse the energy scheduling and carbon emission control optimization strategy into the execution tasks required by the energy management unit and the carbon emission monitoring unit; An instruction generation selection sub-module, which is used to calculate the control signal after selecting the control method according to the nature of the execution task, and perform digital-to-analog conversion and encapsulation operations on the control signal to generate control instructions; A control instruction sending sub-module, which is used to perform encryption processing on the control instructions and send them to the corresponding units; An execution feedback adjustment module, which is used to monitor the execution status of the control instructions, start the correction instructions when abnormal execution status is found, dynamically adjust the control instructions, and analyze the energy and carbon emission status after the strategy adjustment according to the execution status.

8. A smart regulation system based on resource environment data according to claim 7, characterized in that, The calculating of the control signal after selecting the control method according to the nature of the execution task, and performing digital-to-analog conversion and encapsulation operations on the control signal to generate control instructions includes: Selecting the corresponding control method based on the nature of the execution task, setting the parameters of the control method, and calculating the specific control signal according to the control method and the strategy requirements; Converting the control signal into an analog signal through digital-to-analog conversion technology, and after performing amplification and filtering processing on the analog signal, converting the analog signal into a binary coding format; Perform protocol encapsulation and packaging processing on binary signals according to a pre-set communication protocol to convert them into parameterized control instructions, and append an error detection code at the end of the control instructions; Configure an acknowledgement mechanism for the control instructions, and use the acknowledgement mechanism to detect whether the feedback control instructions are received and executed by the energy management unit and the carbon emission monitoring unit during subsequent distribution, and adjust the control instruction distribution sub-module according to the feedback results.

9. The intelligent regulation system based on resource environment data according to claim 7, characterized in that, The execution of encryption processing on the control instructions and distribution to the corresponding units includes: Generate an additional check code based on the control instructions, encrypt the control instructions and the additional check code using an encryption algorithm to generate a key, and distribute the key to the energy management unit and the carbon emission monitoring unit through a secure channel; Use a real-time communication protocol to transmit and distribute the control instructions, and deploy a firewall at the relay nodes in the transmission path to detect the status of the instruction transmission; After the energy management unit and the carbon emission monitoring unit receive the corresponding encrypted control instructions, use the acknowledgement mechanism to feedback instruction reception acknowledgement information to the instruction generation selection sub-module; The energy management unit and the carbon emission monitoring unit decrypt the control instructions and the additional check code according to the key, recalculate the check code of the decrypted control instructions, compare the additional check code with the check code, and verify the consistency of the control instructions; If the check codes are consistent, it means the control instructions are executable. If the check codes are inconsistent, reject the execution of the control instructions and feedback to the central control unit to regenerate the control instructions.

Images