Intelligent campus integrated management and service system

Abstract

The invention relates to the technical field of smart campus management, in particular to a smart campus integrated management and service system, which comprises an energy consumption monitoring module, a carbon footprint calculation module, a behavior data integration module, an energy scheduling optimization module, an energy consumption prediction module, a self-adaptive energy efficiency improvement module and a multi-dimensional energy-saving strategy evaluation module. Wherein the energy consumption monitoring module is used for collecting energy consumption data of various energy consumption devices in a campus in real time through a sensor network; the carbon footprint calculation module is used for calculating the carbon footprint of the campus and generating a carbon emission report; the behavior data integration module is used for identifying an energy consumption peak period and a behavior mode; and the energy scheduling optimization module is used for dynamically adjusting the operation state of the energy consumption equipment through an optimization algorithm. According to the invention, accurate scheduling of campus energy consumption and optimal selection of energy-saving schemes are realized, and energy consumption and carbon emission are significantly reduced while use requirements are ensured to be met, and intelligence and efficiency of energy management are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of smart campus management, and in particular to a smart campus integrated management and service system. Background Art

[0002] With the continuous development of the concept of smart campus, energy consumption management on campus has gradually become an important research and application field. Various energy-consuming equipment (such as air conditioning, lighting, heating systems, etc.) are frequently used on campus, and the combined effects of multiple factors such as teachers' and students' behavior patterns, equipment scheduling and weather changes make energy consumption management complicated. Existing campus energy management systems usually rely on traditional equipment monitoring and timing scheduling. Although they can monitor and control the use of some equipment, they are less efficient when dealing with complex and changeable campus environments, and it is difficult to achieve accurate energy scheduling and management. In addition, with the increasing requirements for carbon emissions, campuses need to actively reduce their carbon footprint while maintaining daily operations to respond to policy requirements for energy conservation and emission reduction.

[0003] However, the existing smart campus energy consumption management system has the following problems that need to be solved urgently. First, the operation and scheduling of energy-consuming equipment often lacks an intelligent optimization mechanism based on behavior patterns, weather changes, and carbon footprint analysis, which causes the equipment to maintain high power consumption during non-essential periods, resulting in serious energy waste. Secondly, although some systems can provide energy-saving solutions, they lack effective multi-dimensional evaluation methods and cannot comprehensively measure the actual effects, operating costs, and user satisfaction of energy-saving solutions, resulting in the inability to select the optimal energy-saving solution for implementation. In addition, it is difficult to form an effective correlation between carbon emission data and energy consumption data, and it is impossible to provide accurate optimization strategies for high-carbon emission equipment. Therefore, it is necessary to develop an energy management system based on multi-dimensional evaluation and intelligent optimization to solve the above problems. Summary of the invention

[0004] Based on the above objectives, the present invention provides an integrated management and service system for a smart campus.

[0005] The integrated management and service system of smart campus includes energy consumption monitoring module, carbon footprint calculation module, behavior data integration module, energy scheduling optimization module, energy consumption prediction module, adaptive energy efficiency improvement module and multi-dimensional energy-saving strategy evaluation module; among which:

[0006] Energy consumption monitoring module: used to collect energy consumption data of various energy-consuming devices on campus in real time through the sensor network, and transmit the collected data to the data center;

[0007] Carbon footprint calculation module: Based on the energy consumption data in the data center and the daily operation activities of the campus, the campus's carbon footprint is calculated in real time and a carbon emission report is generated;

[0008] Behavior data integration module: collects teacher and student behavior data from campus access control systems, smart devices, and campus applications, and integrates the behavior data with the energy consumption data in the energy consumption monitoring module. By analyzing the user's daily behavior patterns and activity time, it identifies the peak energy consumption time periods and behavior patterns.

[0009] Energy scheduling optimization module: Based on the carbon emission report output by the carbon footprint calculation module and the behavior model provided by the behavior data integration module, combined with the equipment usage and real-time weather data on campus, the operating status of energy-consuming equipment is dynamically adjusted through the optimization algorithm to ensure that energy consumption is minimized while meeting usage needs;

[0010] Energy consumption prediction module: Based on energy consumption data, behavior patterns and current dispatch status, it uses machine learning algorithms to predict future energy consumption trends. When energy consumption is too high or carbon emissions exceed the standard, it automatically triggers an early warning and sends an energy consumption reminder to managers.

[0011] Adaptive Energy Efficiency Improvement Module: Through continuous learning and analysis of historical energy consumption data and carbon footprint reports, it identifies inefficient links in long-term energy use and proposes energy-saving solutions to improve energy efficiency;

[0012] Multi-dimensional energy-saving strategy evaluation module: Based on the execution results of different energy-saving plans, the module conducts a multi-dimensional evaluation of the energy-saving effect, operating cost, and user satisfaction of each plan, and automatically selects and implements the optimal energy-saving plan.

[0013] Optionally, the energy consumption monitoring module includes multiple types of sensor units, a data acquisition and processing unit, and a data transmission unit; wherein:

[0014] Multi-type sensor unit: by connecting multiple energy consumption sensor networks, including power sensors, temperature and humidity sensors, light sensors and flow sensors, it is used to collect real-time energy consumption data of various energy consumption equipment on campus, including power consumption, ambient temperature changes, water supply usage and lighting brightness usage;

[0015] Data acquisition and processing unit: Receives data from multiple types of sensor units and performs preliminary processing on the raw signals output by each sensor through an integrated processor, including denoising, data filtering, and format conversion to ensure data accuracy and consistency;

[0016] Data transmission unit: used to transmit the energy consumption data processed by the data acquisition and processing unit to the campus data center in real time through wired or wireless communication protocols. The data transmission unit also includes a redundant transmission mechanism, which is specifically implemented through dual-path transmission technology. The data is divided into a main channel and a backup channel during transmission. When a failure or interruption occurs in the main channel, the backup channel automatically starts to perform seamless switching to ensure uninterrupted data transmission.

[0017] Optionally, the carbon footprint calculation module includes an energy consumption data parsing unit, a carbon emission calculation unit, a daily operation activity integration unit and a carbon emission report generation unit; wherein:

[0018] Energy consumption data analysis unit: used to obtain real-time energy consumption data transmitted by the energy consumption monitoring module from the data center, including energy consumption information of power equipment, lighting equipment, and water supply system, and sort the data through energy consumption classification algorithm, and classify the energy consumption data according to equipment category, regional distribution and time period;

[0019] Carbon emission calculation unit: Based on the classified energy consumption data provided by the energy consumption data analysis unit, the carbon emission coefficient is used to calculate the carbon emissions of different equipment and regions;

[0020] Daily operation activity integration unit: used to obtain energy consumption data of daily operation activities from the campus's transportation system and canteen system, and integrate it with the carbon emission calculation unit;

[0021] Carbon emission report generation unit: Generates a detailed carbon emission report based on the output data of the carbon emission calculation unit and the daily operation activity integration unit. The carbon emission report includes the total carbon emission of the campus as a whole, the carbon emission breakdown data of each equipment category and region, and the carbon emission details of daily operation activities.

[0022] Optionally, the behavior data integration module includes a behavior data acquisition unit, a behavior and energy consumption data fusion unit, a behavior pattern analysis unit, and a peak behavior pattern recognition unit; wherein:

[0023] Behavior data collection unit: collects the behavior data of teachers and students in real time by integrating the campus access control system, smart devices and campus applications; the behavior data includes access control card swiping records, frequency of use of smart devices, geographic location of personal terminals, login and use time of campus applications; each piece of behavior data is timestamped;

[0024] Behavior and energy consumption data fusion unit: used to fuse the teacher and student behavior data acquired by the behavior data acquisition unit with the energy consumption data provided by the energy consumption monitoring module, specifically matching the timestamp with the timestamp of the energy consumption data to form an energy consumption behavior mapping within a time period;

[0025] Behavior pattern analysis unit: By analyzing the fused behavior and energy consumption data, clustering algorithms are used to identify the peak energy consumption periods of teachers and students;

[0026] Peak behavior pattern recognition unit: Based on the output of the behavior pattern analysis unit, the specific behavior pattern corresponding to the peak energy consumption period is identified, and it is associated with the energy consumption of the equipment to determine the cause of the specific equipment energy consumption peak.

[0027] Optionally, the peak behavior pattern recognition unit specifically includes:

[0028] Peak behavior pattern screening: Based on the peak energy consumption period provided by the behavior pattern analysis unit, the behavior patterns of teachers and students occurring during that period are screened out. Each behavior data is matched according to the time period in which it occurs, so as to lock in the behavior patterns related to the peak energy consumption period;

[0029] Equipment energy consumption peak data extraction: Extract equipment energy consumption data corresponding to the peak period from the energy consumption monitoring module, clarify the energy consumption of each device during this period, and extract all equipment energy consumption data during the peak period through screening to identify the equipment with the highest energy consumption value;

[0030] Behavior and equipment energy consumption correlation analysis: After obtaining the behavior pattern and equipment energy consumption data, the two are correlated and analyzed to calculate the correlation between the behavior pattern and the equipment energy consumption, so as to reveal the influence of the specific behavior pattern on the energy consumption peak of certain equipment and identify the behavior that affects the energy consumption peak of the equipment;

[0031] Determination of the cause of energy consumption peak: Finally, based on the correlation results between behavior patterns and equipment energy consumption, in-depth analysis is performed on highly correlated behaviors to determine whether the behaviors are the cause of the equipment energy consumption peak; if the correlation between a behavior pattern and equipment energy consumption reaches the set threshold, the behavior is determined to be the main cause of the energy consumption peak.

[0032] Optionally, the energy scheduling optimization module includes an equipment usage monitoring unit, a weather data acquisition unit, a carbon emission analysis unit and an optimization algorithm unit; wherein:

[0033] Equipment usage monitoring unit: used to monitor the operation of all energy-consuming equipment on campus in real time, including the start and stop status of the equipment, current power and operating time. The equipment usage monitoring unit continuously obtains the real-time status data of the equipment by connecting to sensors of various types of equipment;

[0034] Weather data acquisition unit: by connecting with external weather stations or internal environmental sensors, it can obtain current weather information in real time, including climate data of temperature, humidity, and wind speed;

[0035] Carbon emission analysis unit: Analyze the carbon emission level of the current equipment according to the carbon emission report provided by the carbon footprint calculation module, identify high carbon emission equipment or areas, and determine the carbon emission contribution of the equipment in combination with the energy consumption data of the equipment usage monitoring unit;

[0036] Optimization algorithm unit: Through a preset optimization algorithm, based on the data provided by the equipment usage monitoring unit, the weather data acquisition unit and the carbon emission analysis unit, the operating status of the energy-consuming equipment is dynamically adjusted to minimize the energy consumption of the equipment.

[0037] Optionally, the optimization algorithm unit specifically includes:

[0038] Objective function: Assume that the goal of the optimization algorithm is to minimize the total energy consumption E total , its objective function expression is: Among them, P i (t) is the power of the i-th device at time t, T i is the running time of the device, and n is the total number of devices;

[0039] Constraints: define the constraints on equipment operation, including usage demand constraints and weather impact constraints;

[0040] Usage demand constraints: the equipment must meet the actual usage needs of teachers and students. The equipment operation time T i and power P i (t) It needs to be adjusted dynamically according to the device type and usage requirements;

[0041] Weather impact constraints, for weather-sensitive equipment constraints, power P i (t) needs to be adjusted according to weather data, the formula is: Among them, P max is the maximum power of the device, T opt is the optimal operating temperature of the equipment, T actual is the current actual temperature;

[0042] Optimization process: According to the objective function and constraints, the gradient descent algorithm is used to dynamically adjust the operating time and power of the equipment. After gradual iteration, it ensures that the total energy consumption is minimized while meeting the usage requirements.

[0043] Optionally, the energy consumption prediction module includes a historical data processing unit, a feature extraction unit, a machine learning model training unit, an energy consumption trend prediction unit and an early warning triggering unit; wherein:

[0044] Historical data processing unit: used to obtain historical energy consumption data, behavior patterns and equipment scheduling status from the energy consumption monitoring module, behavior data integration module and energy scheduling optimization module; the historical energy consumption data includes the operating power, start and stop time and total energy consumption of the equipment in the past, and the behavior pattern data includes the activity patterns of teachers and students and the use of equipment; the historical data processing unit also includes normalizing the acquired data and unifying the format;

[0045] Feature extraction unit: used to extract features from historical data, including behavior pattern features, energy consumption features, and weather data features;

[0046] Machine learning model training unit: Based on the regression analysis algorithm, combined with historical data and extracted feature vectors, the machine learning model is trained to predict future energy consumption trends. The regression model is used to predict energy consumption in the future period.

[0047] Energy consumption trend prediction unit: After the machine learning model is trained, the energy consumption trend prediction unit uses the current energy consumption data, behavior patterns, and weather data as input to generate energy consumption forecasts for future periods. It uses the trained regression model to output energy consumption forecasts for each device or region in the future period.

[0048] Early warning trigger unit: Based on the output results of the energy consumption trend prediction unit, the predicted energy consumption value is analyzed. If the energy consumption value in a certain period of time is found Exceeds the set energy consumption threshold E max , or the carbon emissions of the corresponding equipment exceed the carbon emission threshold C max When an alarm occurs, it will automatically trigger an early warning and notify the management personnel to take measures.

[0049] Optionally, the adaptive energy efficiency improvement module includes an energy consumption history data analysis unit, a carbon footprint report analysis unit, an inefficient link identification unit, and an energy-saving solution generation unit; wherein:

[0050] Energy consumption historical data analysis unit: By continuously analyzing the energy consumption historical data of all equipment on campus, identify equipment or areas with high energy consumption. During the analysis process, the energy consumption data is divided into different time periods and classified by equipment type and area to identify the energy efficiency performance in different time periods and equipment categories; and by calculating the difference between the average energy consumption and the actual energy consumption of each device, it is determined whether the device is in a high energy consumption state;

[0051] Carbon footprint report analysis unit: Based on the carbon footprint report generated by the carbon footprint calculation module and combined with the results of the energy consumption history data analysis unit, the carbon emission contribution of each device and region is analyzed. By calculating the relationship between the carbon emissions of each device and its corresponding energy consumption, the device or region with excessively high carbon emissions but low energy efficiency is identified;

[0052] Inefficient Link Identification Unit: By analyzing the historical energy consumption data and carbon footprint reports, it identifies the inefficient links that have existed on campus for a long time, including aging equipment, equipment that is used too frequently, equipment that is not shut down in time, and equipment that is idling too much.

[0053] Energy-saving solution generation unit: used to propose corresponding energy efficiency improvement solutions after identifying low-efficiency links. The energy-saving solutions include adjusting the equipment operation time, reducing the power of the equipment, optimizing the equipment scheduling strategy, and regular equipment maintenance and upgrades.

[0054] Optionally, the multi-dimensional energy-saving strategy evaluation module includes an energy-saving effect evaluation unit, an operation cost evaluation unit, a user satisfaction evaluation unit and an optimal solution selection unit; wherein:

[0055] Energy-saving effect evaluation unit: used to monitor the energy consumption changes after the implementation of each energy-saving plan and calculate the actual energy-saving effect of each plan;

[0056] Operation cost evaluation unit: evaluates the economic feasibility of each energy-saving plan by analyzing the implementation cost and long-term operation cost of each plan. The operation cost calculation includes the initial equipment adjustment cost, the labor cost of plan execution, the equipment maintenance cost and the long-term energy saving cost;

[0057] User satisfaction evaluation unit: By collecting feedback from teachers and students, the impact of each energy-saving solution on user experience is evaluated. The specific evaluation includes comfort, convenience of equipment use, and satisfaction with the working and learning environment;

[0058] Optimal solution selection unit: Based on the comprehensive evaluation results of three indicators, namely energy-saving effect, operating cost and user satisfaction, the optimal energy-saving solution is selected using a weighted scoring method.

[0059] Beneficial effects of the present invention:

[0060] The present invention solves the problem of lack of precise scheduling and efficient management in the existing smart campus energy consumption management by introducing multi-dimensional evaluation and intelligent optimization algorithms. Through the collaborative work of modules such as energy consumption monitoring, behavior data integration, and carbon emission analysis, it can collect and integrate various energy consumption data, user behavior patterns, and environmental factors in real time, dynamically predict energy consumption trends using machine learning algorithms, and optimize the operating status of equipment based on carbon emissions and energy-saving needs. The system can not only significantly reduce energy consumption while meeting the daily needs of teachers and students, but also effectively reduce carbon emissions on campus and improve the level of intelligent energy management.

[0061] The present invention automatically selects the best energy-saving plan for implementation by comprehensively evaluating the energy-saving effects, operating costs, and user satisfaction of various energy-saving plans. This innovative design can ensure that the implementation of the energy-saving plan will not reduce user experience while saving energy, and provides the most economical management plan. Through the accurate identification and optimization of low-efficiency equipment and high-carbon emission areas, the efficiency of energy use is significantly improved, providing a more scientific and intelligent solution for campus energy management. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0063] Figure 1 A schematic diagram of a smart campus integrated management and service system according to an embodiment of the present invention;

[0064] Figure 2 Schematic diagram of an energy scheduling optimization module according to an embodiment of the present invention. DETAILED DESCRIPTION

[0065] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0066] like Figure 1-Figure 2 As shown in the figure, the integrated management and service system of smart campus includes energy consumption monitoring module, carbon footprint calculation module, behavior data integration module, energy scheduling optimization module, energy consumption prediction module, adaptive energy efficiency improvement module and multi-dimensional energy-saving strategy evaluation module; among which:

[0067] Energy consumption monitoring module: used to collect energy consumption data of various energy-consuming devices (such as air conditioners, lighting, computing equipment, etc.) on campus in real time through the sensor network, and transmit the collected data to the data center;

[0068] Carbon footprint calculation module: Based on the energy consumption data in the data center and combined with the daily operation activities of the campus (such as transportation, canteen, equipment use, etc.), the campus's carbon footprint is calculated in real time and a carbon emission report is generated;

[0069] Behavior data integration module: collects teacher and student behavior data from campus access control systems, smart devices, and campus applications, and integrates the behavior data with the energy consumption data in the energy consumption monitoring module. By analyzing the user's daily behavior patterns and activity time, it identifies the peak energy consumption time periods and behavior patterns.

[0070] Energy scheduling optimization module: Based on the carbon emission report output by the carbon footprint calculation module and the behavior model provided by the behavior data integration module, combined with the equipment usage and real-time weather data on campus, the operating status of energy-consuming equipment is dynamically adjusted through the optimization algorithm to ensure that energy consumption is minimized while meeting usage needs;

[0071] Energy consumption prediction module: Based on energy consumption data, behavior patterns and current dispatch status, it uses machine learning algorithms to predict future energy consumption trends. When energy consumption is too high or carbon emissions exceed the standard, it automatically triggers an early warning and sends an energy consumption reminder to managers.

[0072] Adaptive Energy Efficiency Improvement Module: Through continuous learning and analysis of historical energy consumption data and carbon footprint reports, it identifies inefficient links in long-term energy use and proposes energy-saving solutions to improve energy efficiency, such as equipment upgrades and optimized usage strategies, so as to continuously reduce the overall energy consumption level of the campus;

[0073] Multi-dimensional energy-saving strategy evaluation module: Based on the execution results of different energy-saving plans, the module conducts a multi-dimensional evaluation of the energy-saving effect, operating cost, and user satisfaction of each plan, automatically selects the optimal energy-saving plan and implements it to ensure a balance between energy-saving measures and daily campus operations.

[0074] The energy consumption monitoring module includes multiple types of sensor units, data acquisition and processing units, and data transmission units; among which:

[0075] Multi-type sensor unit: By connecting multiple energy consumption sensor networks, including power sensors, temperature and humidity sensors, light sensors and flow sensors, it is used to collect real-time energy consumption data of various energy-consuming equipment on campus (such as air conditioners, lighting equipment, computing equipment, water supply systems, etc.). The energy consumption data includes power consumption, ambient temperature changes, water supply usage and lighting brightness usage; the power sensor is used to detect the actual power consumption of the equipment; the temperature and humidity sensor is used to monitor the temperature and humidity changes of the environment; the light sensor is responsible for measuring the brightness level of the lighting equipment; the flow sensor collects the usage of the water supply equipment. The collected data of each sensor is converted into a standardized electrical signal through the built-in data interface;

[0076] Data acquisition and processing unit: Receives data from multiple types of sensor units and performs preliminary processing on the raw signals output by each sensor through an integrated processor, including denoising, data filtering, and format conversion to ensure data accuracy and consistency;

[0077] Data transmission unit: used to transmit the energy consumption data processed by the data acquisition and processing unit to the campus data center in real time through wired or wireless communication protocols (such as Ethernet, Wi-Fi or 5G network), ensuring the stability and security of data transmission. The data transmission unit also includes a redundant transmission mechanism, which is specifically implemented through dual-path transmission technology. The data is divided into a main channel and a backup channel during transmission. When the main channel fails or is interrupted, the backup channel automatically starts to switch seamlessly to ensure uninterrupted data transmission. Through the combination of the above units, the system can efficiently and accurately obtain real-time energy consumption data of various equipment on campus through multiple types of sensor units, and standardize and synchronize the data through the data acquisition and processing unit to ensure accurate and error-free transmission of the data. The data transmission unit adopts a redundant transmission mechanism to ensure the stability of data transmission through switching between the main and backup channels, effectively avoiding data loss or delay caused by network problems, thereby providing highly reliable data support for subsequent energy consumption analysis and optimization scheduling.

[0078] The carbon footprint calculation module includes an energy consumption data analysis unit, a carbon emission calculation unit, a daily operation activity integration unit, and a carbon emission report generation unit; among which:

[0079] Energy consumption data analysis unit: used to obtain real-time energy consumption data transmitted by the energy consumption monitoring module from the data center, including energy consumption information of power equipment, lighting equipment, and water supply system, and sort the data through energy consumption classification algorithm, and classify the energy consumption data according to equipment category, regional distribution and time period; the specific classification formula is: Among them, E(t) represents the total energy consumption data in a certain period of time, E x (t) represents the energy consumption data of the xth type of equipment, E y (t) represents the energy consumption data of the yth area, N represents the total number of equipment categories, M represents the total number of areas, and t represents the time period. The energy consumption data is marked by equipment labels and area labels and divided into different time periods to ensure the accuracy of data collation;

[0080] Carbon emission calculation unit: Based on the classified energy consumption data provided by the energy consumption data analysis unit, the carbon emission coefficient is used to calculate the carbon emissions of different equipment and regions; the carbon emission calculation formula is:

[0081] Among them, C(t) represents the total carbon emissions in a certain period of time, E x (t) represents the energy consumption data of the xth type of equipment, E y (t) represents the energy consumption data of the yth area, α x is the carbon emission coefficient corresponding to the x-th type of equipment, α yis the carbon emission coefficient corresponding to the yth area. Through the above calculation, the carbon footprint of the campus as a whole and each area can be calculated and dynamically updated in real time;

[0082] Daily operation activity integration unit: used to obtain energy consumption data of daily operation activities from the campus transportation system and canteen system, and integrate it with the carbon emission calculation unit; the energy consumption data of daily operation activities is calculated using the following formula: Among them, O(t) represents the total carbon emissions of daily operating activities in a certain period of time, O z (t) represents the energy consumption data of the zth type of daily activities, α z is the carbon emission coefficient corresponding to the zth type of daily activities, and P represents the total number of categories of daily operating activities. Through this unit, the carbon emissions of daily operating activities can be effectively integrated with the carbon emissions of equipment energy consumption;

[0083] Carbon emission report generation unit: Based on the output data of the carbon emission calculation unit and the daily operation activity integration unit, a detailed carbon emission report is generated. The carbon emission report includes the total carbon emission of the campus as a whole, the carbon emission breakdown data of each equipment category and region, and the carbon emission details of daily operation activities; the carbon emission report also provides carbon emission trend analysis within a certain period of time in the past (such as daily or monthly) to help campus managers optimize their decisions; through the design of the above-mentioned carbon footprint calculation module, the energy consumption data analysis unit can accurately process energy consumption data through the classification algorithm of equipment and region, and provide high-quality input for the carbon emission calculation unit; the carbon emission calculation unit combines the carbon emission coefficients of different equipment and regions to accurately calculate the overall carbon footprint of the campus; the daily operation activity integration unit organically integrates the carbon emissions of the campus's daily operation activities with the use of equipment, and the generated carbon emission report provides managers with comprehensive, real-time and historical carbon emission data support, further optimizing the campus' energy use and management.

[0084] The behavior data integration module includes a behavior data acquisition unit, a behavior and energy consumption data fusion unit, a behavior pattern analysis unit, and a peak behavior pattern recognition unit; wherein:

[0085] Behavior data collection unit: By integrating the campus access control system, smart devices (such as smart classroom equipment, personal smart terminals) and campus applications, the behavior data of teachers and students are collected in real time; the behavior data includes access control card swiping records, frequency of use of smart devices, geographic location of personal terminals, login and use time of campus applications; each piece of behavior data is timestamped T b ;

[0086] Behavior and energy consumption data fusion unit: used to fuse the teacher and student behavior data obtained by the behavior data collection unit with the energy consumption data provided by the energy consumption monitoring module. Specifically, the timestamp T bThe timestamp T of the energy consumption data e Matching is performed to form an energy consumption behavior mapping within a time period; the fusion formula is: Among them, F(t) represents the fusion data of behavior and energy consumption in time period t, B i (T b ) is the behavior data of the i-th user, E i (T e ) is the energy consumption data of the ith device, and R is the logarithm of the association between behavior and device in the fused data;

[0087] Behavior pattern analysis unit: By analyzing the fused behavior and energy consumption data, clustering algorithms are used to identify the peak energy consumption periods of teachers and students. The behavior pattern analysis includes the activity patterns of teachers and students (such as class and rest time), activity areas (such as teaching buildings and dormitory areas), and equipment usage. The identification formula for the peak energy consumption period is: Among them, T p Indicates the time period of peak energy consumption, F j (t) is the energy consumption fusion data of the jth behavior-energy consumption association pair in time period t, and Q is the number of all behavior-device association pairs; by analyzing the user's behavior pattern and device usage time, the peak energy consumption period is identified to facilitate subsequent energy optimization;

[0088] Peak behavior pattern recognition unit: Based on the output of the behavior pattern analysis unit, it identifies the specific behavior pattern corresponding to the peak energy consumption period and associates it with the equipment energy consumption situation to determine the cause of the specific equipment energy consumption peak, so that managers can take effective measures to optimize energy allocation during peak periods.

[0089] The peak behavior pattern recognition unit specifically includes:

[0090] Peak behavior pattern screening: Based on the peak energy consumption period provided by the behavior pattern analysis unit, the behavior patterns of teachers and students occurring during that period are screened out. Each behavior data is matched according to the time period in which it occurs, so as to lock in the behavior patterns related to the peak energy consumption period;

[0091] Equipment energy consumption peak data extraction: Extract equipment energy consumption data corresponding to the peak period from the energy consumption monitoring module, clarify the energy consumption of each device during this period, and extract all equipment energy consumption data during the peak period through screening to identify the equipment with the highest energy consumption value;

[0092] Behavior and equipment energy consumption correlation analysis: After obtaining the behavior pattern and equipment energy consumption data, the two are correlated and analyzed to calculate the correlation between the behavior pattern and the equipment energy consumption, so as to reveal the influence of the specific behavior pattern on the energy consumption peak of certain equipment and identify the behavior that affects the energy consumption peak of the equipment;

[0093] Determination of the cause of energy consumption peak: Finally, based on the correlation results between behavior patterns and equipment energy consumption, in-depth analysis is performed on highly correlated behaviors to determine whether the behaviors are the cause of the equipment energy consumption peak; if the correlation between a behavior pattern and equipment energy consumption reaches the set threshold, the behavior is determined to be the main cause of the energy consumption peak.

[0094] The specific calculation steps of the peak behavior pattern recognition unit are as follows:

[0095] Step 1: Based on the energy consumption peak period T provided by the behavior pattern analysis unit p , filter out the teacher-student behavior pattern P in this period from the behavior data b , the behavior pattern screening formula is as follows: P b (T p )={P i |T b ∈T p}, where P b (T p ) represents the peak energy consumption period T p The set of all behavior patterns in P i represents the behavior pattern of the i-th user, T b is the timestamp of the behavior; the goal of this step is to lock the behavior pattern corresponding to the peak energy consumption period for subsequent analysis;

[0096] Step 2: Extract T during peak hours from the energy consumption monitoring module p Corresponding equipment energy consumption data E p (t), specifically, the peak energy consumption of each device during this period; the energy consumption data extraction formula is as follows: E p (t) = {E j |T e ∈T p}, where E p (t) represents the energy consumption data set of all devices during the peak energy consumption period, E j is the energy consumption value of the jth device, T e The energy consumption timestamp of the device. This step is used to clarify the energy consumption performance of each device during the peak energy consumption period and determine which devices contribute the most to the peak energy consumption.

[0097] Step 3: By matching the peak time T p Behavior patterns within b (T p ) and equipment energy consumption data E p (t), and use the correlation analysis algorithm to calculate the correlation between the behavior and the energy consumption of the device. The specific formula is as follows:

[0098] Among them, R(p, e) represents the behavior pattern P i and equipment energy consumption E j The correlation between them, N represents the number of behaviors and devices participating in the activities during the peak period. The correlation represents the impact of a specific behavior pattern on the peak energy consumption of a certain device. Through this calculation, it can be determined which behaviors have a major impact on the peak energy consumption of the device.

[0099] Step 4: Based on the correlation between behavior and equipment calculated in step 3, conduct in-depth analysis on the behavior patterns with high correlation to determine their contribution to the peak energy consumption of the equipment. If the correlation exceeds the set threshold λ, it can be determined that the behavior pattern is the main cause of the peak energy consumption of the equipment. The above steps can effectively screen out specific behavior patterns related to the peak energy consumption period, and identify the main behavior patterns that lead to the peak energy consumption of the equipment through the correlation analysis between behavior and equipment energy consumption. This provides an important basis for subsequent energy optimization and management, helps to reduce the frequency of peak energy consumption periods in the future, and improves the overall energy consumption management efficiency of the campus.

[0100] The energy scheduling optimization module includes an equipment usage monitoring unit, a weather data acquisition unit, a carbon emission analysis unit, and an optimization algorithm unit; among which:

[0101] Equipment usage monitoring unit: used to monitor the operation of all energy-consuming equipment on campus in real time, including the start and stop status of the equipment, current power and operating time. The equipment usage monitoring unit continuously obtains the real-time status data of the equipment by connecting to sensors of various types of equipment;

[0102] Weather data acquisition unit: by connecting with external weather stations or internal environmental sensors, it can obtain current weather information in real time, including climate data of temperature, humidity, and wind speed;

[0103] Carbon emission analysis unit: According to the carbon emission report provided by the carbon footprint calculation module, analyze the carbon emission level of the current equipment, identify high carbon emission equipment or areas, and determine the carbon emission contribution of the equipment in combination with the energy consumption data of the equipment usage monitoring unit; specifically, the carbon emission calculation is based on the following formula: C device =P i (t)·T i α i , where C device is the carbon emission of the i-th device, P i (t) is the power of the device at time t, T i is the running time of the device, α i The carbon emission coefficient of the energy used by the equipment. This unit summarizes the carbon emission data of each device by calculating the energy consumption and carbon emission coefficient of the equipment. The total carbon emission calculation formula of the equipment is: Among them, C totalis the total carbon emissions of all energy-consuming equipment on campus, and n is the total number of equipment. This unit can identify high-carbon emission equipment or areas, and combine the data from the equipment usage monitoring unit to analyze the contribution of each equipment to the overall carbon emissions of the campus;

[0104] Optimization algorithm unit: Through the preset optimization algorithm, based on the data provided by the equipment usage monitoring unit, the weather data acquisition unit and the carbon emission analysis unit, the operating status of the energy-consuming equipment is dynamically adjusted to minimize the energy consumption of the equipment; through the disclosure of the above-mentioned energy scheduling optimization module, the equipment usage monitoring unit, the weather data acquisition unit and the carbon emission analysis unit can provide comprehensive input data for the optimization algorithm. The carbon emission analysis unit calculates the carbon emissions of each device in detail and combines the energy consumption data to provide accurate carbon emission information for subsequent optimization; the optimization algorithm unit is based on the energy consumption minimization goal, combined with the equipment usage requirements and weather conditions, to dynamically adjust the operating time and power of the equipment to ensure that energy consumption is minimized while ensuring functional requirements.

[0105] The optimization algorithms in the optimization algorithm unit specifically include:

[0106] Objective function: Assume that the goal of the optimization algorithm is to minimize the total energy consumption E total , its objective function expression is: Among them, P i (t) is the power of the i-th device at time t, T i is the running time of the device, n is the total number of devices, and this function is used to calculate the total energy consumption of all devices in a specific time period;

[0107] Constraints: define the constraints on equipment operation, including usage demand constraints and weather impact constraints;

[0108] Usage demand constraints: the equipment must meet the actual usage needs of teachers and students. The equipment operation time T i and power P i (t) It needs to be adjusted dynamically according to the device type and usage requirements;

[0109] Weather impact constraints: Constraints are imposed on weather-sensitive equipment (such as air conditioning and heating systems). Power P i (t) needs to be adjusted according to weather data, the formula is: Among them, P max is the maximum power of the device, T opt is the optimal operating temperature of the equipment, T actual is the current actual temperature. When the difference between the actual temperature and the optimal temperature increases, the power is adjusted accordingly.

[0110] Optimization process: According to the objective function and constraints, the gradient descent algorithm is used to dynamically adjust the operating time and power of the equipment. After gradual iteration, it ensures that the total energy consumption is minimized while meeting the usage requirements.

[0111] The energy consumption prediction module includes a historical data processing unit, a feature extraction unit, a machine learning model training unit, an energy consumption trend prediction unit, and an early warning trigger unit; wherein:

[0112] Historical data processing unit: used to obtain historical energy consumption data, behavior patterns and equipment scheduling status from the energy consumption monitoring module, behavior data integration module and energy scheduling optimization module; historical energy consumption data includes the operating power, start and stop time and total energy consumption of past equipment, and behavior pattern data includes the activity patterns of teachers and students and equipment usage; the historical data processing unit also includes normalizing the acquired data and unifying the format to ensure comparability between different data types, so as to facilitate subsequent machine learning algorithm processing;

[0113] Feature extraction unit: used to extract features from historical data, including behavioral pattern features (such as time patterns, usage frequency), energy consumption features (such as equipment power fluctuations, scheduling strategies), and weather data features; the feature extraction formula is as follows: X = {f1, f2, ..., f k}, where X represents the feature set, f k is the kth extracted feature value, such as device power, weather changes, time regularity of behavior patterns, etc. This unit inputs the extracted feature vector X into the machine learning model as the basis for model training;

[0114] Machine learning model training unit: Based on the regression analysis algorithm, combined with historical data and extracted feature vectors, the machine learning model is trained to predict future energy consumption trends. The regression model is used to predict energy consumption in the future period. The specific training formula is: in, is the predicted energy consumption value in the future period, β0 is the intercept term of the model, and β k The feature f k The regression coefficient for energy consumption, m is the number of features; through multiple iterative training, the machine learning model can accurately predict the energy consumption changes in different time periods in the future based on the input feature values;

[0115] Energy consumption trend prediction unit: After the machine learning model is trained, the energy consumption trend prediction unit uses the current energy consumption data, behavior patterns, and weather data as input to generate energy consumption forecasts for future periods. It uses the trained regression model to output energy consumption forecasts for each device or region in the future period.

[0116] Early warning trigger unit: Based on the output results of the energy consumption trend prediction unit, the predicted energy consumption value is analyzed. If the energy consumption value in a certain period of time is found Exceeds the set energy consumption threshold E max , or the carbon emissions of the corresponding equipment exceed the carbon emission threshold C max , an early warning is automatically triggered to notify the management personnel to take measures; through the disclosure of the above-mentioned energy consumption prediction module, the historical data processing unit and the feature extraction unit can effectively integrate and extract key data features; the machine learning model training unit trains the model through the regression analysis algorithm to predict future energy consumption trends; the energy consumption trend prediction unit generates future energy consumption forecast values ​​based on current data and model output; the early warning trigger unit automatically triggers an early warning according to the set energy consumption and carbon emission thresholds, ensuring that management personnel respond to energy consumption or carbon emission problems in a timely manner, thereby optimizing energy management.

[0117] The adaptive energy efficiency improvement module includes an energy consumption history data analysis unit, a carbon footprint report analysis unit, an inefficient link identification unit, and an energy-saving solution generation unit; among which:

[0118] Energy consumption history data analysis unit: By continuously analyzing the energy consumption history data of all equipment on campus, identify equipment or areas with high energy consumption. During the analysis process, the energy consumption data is divided into different time periods (such as day, week, month), and classified by equipment type and area, so as to identify the energy efficiency performance under different time periods and equipment categories; and by calculating the difference between the average energy consumption of each device and the actual energy consumption, it is determined whether the device is in a high energy consumption state;

[0119] The energy consumption difference is calculated as follows: ΔE i =E actual,i -E expected,i , where ΔE i is the energy consumption difference of the i-th device, E acyual,i is the actual energy consumption of the device, E expected,i is the expected energy consumption of the equipment under normal working conditions;

[0120] Carbon footprint report analysis unit: Based on the carbon footprint report generated by the carbon footprint calculation module and combined with the results of the energy consumption history data analysis unit, the carbon emission contribution of each device and region is analyzed. By calculating the relationship between the carbon emissions of each device and its corresponding energy consumption, the device or region with excessively high carbon emissions but low energy efficiency is identified; the calculation formula for carbon emission contribution is: Among them, C contribution,i represents the carbon emission contribution of the i-th device, C i is the carbon emission of the equipment, E i The energy consumption of the equipment can be calculated by identifying equipment or areas with high carbon emissions but low energy efficiency.

[0121] Inefficient Link Identification Unit: By analyzing the historical energy consumption data and carbon footprint reports, it identifies the long-standing inefficient links on campus, including aging equipment, equipment that is used too frequently, equipment that is not shut down in time, and equipment that is idling too much.

[0122] Energy-saving solution generation unit: used to propose corresponding energy efficiency improvement plans after identifying inefficient links. Energy-saving plans include adjusting equipment operating time, reducing equipment power, optimizing equipment scheduling strategies, and regular equipment maintenance and upgrades. Through the disclosure of the above-mentioned adaptive energy efficiency improvement module, the energy consumption history data analysis unit can identify high-energy consumption equipment through detailed data analysis. The carbon footprint report analysis unit identifies high-carbon emission but low-efficiency equipment and areas by analyzing carbon emission data. The inefficient link identification unit effectively locates long-standing inefficient equipment and areas. The energy-saving solution generation unit proposes specific plans for improving energy efficiency in combination with optimization strategies to ensure that campus energy management is more efficient and sustainable.

[0123] The multi-dimensional energy-saving strategy evaluation module includes an energy-saving effect evaluation unit, an operating cost evaluation unit, a user satisfaction evaluation unit, and an optimal solution selection unit; among which:

[0124] Energy-saving effect evaluation unit: used to monitor the energy consumption changes after the implementation of each energy-saving plan and calculate the actual energy-saving effect of each plan; the specific formula is as follows: Among them, η energy,i represents the energy saving rate of the ith solution, E baseline is the baseline energy consumption, i.e. the energy consumption value before the implementation of the scheme, E acyual,i The actual energy consumption value after the implementation of the plan. Through the evaluation of this unit, the actual improvement effect of each energy-saving plan in terms of energy consumption can be quantitatively analyzed;

[0125] Operation cost evaluation unit: By analyzing the implementation cost and long-term operation cost of each energy-saving plan, the economic feasibility of each plan is evaluated. The calculation of operation cost includes the initial equipment adjustment cost, the labor cost of plan execution, the equipment maintenance cost and the long-term energy saving cost. The cost evaluation formula is as follows: C total，，i =C initial，i +C maintenance,i -C saved,i , where C total,i represents the total operating cost of the i-th energy-saving scheme, C initial,i is the initial cost of implementing the plan, C maintenance,i is the equipment maintenance cost, C saved,i In order to save energy costs through this solution, the unit can provide decision makers with the most economical solution selection basis by evaluating the total cost;

[0126] User satisfaction evaluation unit: By collecting feedback from teachers and students, the impact of each energy-saving solution on user experience is evaluated. The specific evaluation includes comfort (such as temperature, brightness comfort), convenience of equipment use, and satisfaction with the work and study environment. The specific satisfaction calculation formula is: Among them, S user,i is the average user satisfaction score of the i-th energy-saving scheme, S j is the score of the jth user, N is the total number of users. By summarizing user feedback, the user satisfaction evaluation unit can evaluate the impact of different energy-saving solutions on the actual user experience;

[0127] Optimal solution selection unit: Based on the comprehensive evaluation results of the three indicators of energy-saving effect, operating cost and user satisfaction, the optimal energy-saving solution is selected using a weighted scoring method; the specific formula is: Score i =w1· Among them, Score i is the comprehensive score of the i-th energy-saving scheme, w1, w2, w3 are the weight coefficients of energy-saving effect, operating cost and user satisfaction, respectively, C max is the maximum operating cost among all the options, and the option with the highest comprehensive score is the optimal option.

[0128] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0129] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. Smart campus integrated management and service system, characterized by: It includes energy consumption monitoring module, carbon footprint calculation module, behavior data integration module, energy scheduling optimization module, energy consumption prediction module, adaptive energy efficiency improvement module and multi-dimensional energy-saving strategy evaluation module; among which: Energy consumption monitoring module: used to collect energy consumption data of various energy-consuming devices on campus in real time through the sensor network, and transmit the collected data to the data center; Carbon footprint calculation module: Based on the energy consumption data in the data center and the daily operation activities of the campus, the campus's carbon footprint is calculated in real time and a carbon emission report is generated; Behavior data integration module: collects teacher and student behavior data from campus access control systems, smart devices, and campus applications, and integrates the behavior data with the energy consumption data in the energy consumption monitoring module. By analyzing the user's daily behavior patterns and activity time, it identifies the peak energy consumption time periods and behavior patterns. Energy scheduling optimization module: Based on the carbon emission report output by the carbon footprint calculation module and the behavior model provided by the behavior data integration module, combined with the equipment usage and real-time weather data on campus, the operating status of energy-consuming equipment is dynamically adjusted through the optimization algorithm to ensure that energy consumption is minimized while meeting usage needs; Energy consumption prediction module: Based on energy consumption data, behavior patterns and current dispatch status, it uses machine learning algorithms to predict future energy consumption trends. When energy consumption is too high or carbon emissions exceed the standard, it automatically triggers an early warning and sends an energy consumption reminder to managers. Adaptive Energy Efficiency Improvement Module: Through continuous learning and analysis of historical energy consumption data and carbon footprint reports, it identifies inefficient links in long-term energy use and proposes energy-saving solutions to improve energy efficiency; Multi-dimensional energy-saving strategy evaluation module: Based on the execution results of different energy-saving plans, the module conducts a multi-dimensional evaluation of the energy-saving effect, operating cost, and user satisfaction of each plan, and automatically selects and implements the optimal energy-saving plan.

2. The smart campus integrated management and service system according to claim 1 is characterized in that: The energy consumption monitoring module includes multiple types of sensor units, a data acquisition and processing unit, and a data transmission unit; wherein: Multi-type sensor unit: by connecting multiple energy consumption sensor networks, including power sensors, temperature and humidity sensors, light sensors and flow sensors, it is used to collect real-time energy consumption data of various energy consumption equipment on campus, including power consumption, ambient temperature changes, water supply usage and lighting brightness usage; Data acquisition and processing unit: Receives data from multiple types of sensor units and performs preliminary processing on the raw signals output by each sensor through an integrated processor, including denoising, data filtering, and format conversion to ensure data accuracy and consistency; Data transmission unit: used to transmit the energy consumption data processed by the data acquisition and processing unit to the campus data center in real time through wired or wireless communication protocols. The data transmission unit also includes a redundant transmission mechanism, which is specifically implemented through dual-path transmission technology. The data is divided into a main channel and a backup channel during transmission. When a failure or interruption occurs in the main channel, the backup channel automatically starts to perform seamless switching to ensure uninterrupted data transmission.

3. The smart campus integrated management and service system according to claim 1 is characterized in that: The carbon footprint calculation module includes an energy consumption data analysis unit, a carbon emission calculation unit, a daily operation activity integration unit and a carbon emission report generation unit; wherein: Energy consumption data analysis unit: used to obtain real-time energy consumption data transmitted by the energy consumption monitoring module from the data center, including energy consumption information of power equipment, lighting equipment, and water supply system, and sort the data through energy consumption classification algorithm, and classify the energy consumption data according to equipment category, regional distribution and time period; Carbon emission calculation unit: Based on the classified energy consumption data provided by the energy consumption data analysis unit, the carbon emission coefficient is used to calculate the carbon emissions of different equipment and regions; Daily operation activity integration unit: used to obtain energy consumption data of daily operation activities from the campus's transportation system and canteen system, and integrate it with the carbon emission calculation unit; Carbon emission report generation unit: Generates a detailed carbon emission report based on the output data of the carbon emission calculation unit and the daily operation activity integration unit. The carbon emission report includes the total carbon emission of the campus as a whole, the carbon emission breakdown data of each equipment category and region, and the carbon emission details of daily operation activities.

4. The smart campus integrated management and service system according to claim 1 is characterized in that: The behavior data integration module includes a behavior data acquisition unit, a behavior and energy consumption data fusion unit, a behavior pattern analysis unit and a peak behavior pattern recognition unit; wherein: Behavior data collection unit: collects the behavior data of teachers and students in real time by integrating the campus access control system, smart devices and campus applications; the behavior data includes access control card swiping records, frequency of use of smart devices, geographic location of personal terminals, login and use time of campus applications; each piece of behavior data is timestamped; Behavior and energy consumption data fusion unit: used to fuse the teacher and student behavior data acquired by the behavior data acquisition unit with the energy consumption data provided by the energy consumption monitoring module, specifically matching the timestamp with the timestamp of the energy consumption data to form an energy consumption behavior mapping within a time period; Behavior pattern analysis unit: By analyzing the fused behavior and energy consumption data, clustering algorithms are used to identify the peak energy consumption periods of teachers and students; Peak behavior pattern recognition unit: Based on the output of the behavior pattern analysis unit, the specific behavior pattern corresponding to the peak energy consumption period is identified, and it is associated with the energy consumption of the equipment to determine the cause of the specific equipment energy consumption peak.

5. The smart campus integrated management and service system according to claim 4 is characterized in that: The peak behavior pattern recognition unit specifically includes: Peak behavior pattern screening: Based on the peak energy consumption period provided by the behavior pattern analysis unit, the behavior patterns of teachers and students occurring during that period are screened out. Each behavior data is matched according to the time period in which it occurs, so as to lock in the behavior patterns related to the peak energy consumption period; Equipment energy consumption peak data extraction: Extract equipment energy consumption data corresponding to the peak period from the energy consumption monitoring module, clarify the energy consumption of each device during this period, and extract all equipment energy consumption data during the peak period through screening to identify the equipment with the highest energy consumption value; Behavior and equipment energy consumption correlation analysis: After obtaining the behavior pattern and equipment energy consumption data, the two are correlated and analyzed to calculate the correlation between the behavior pattern and the equipment energy consumption, so as to reveal the influence of the specific behavior pattern on the energy consumption peak of certain equipment and identify the behavior that affects the energy consumption peak of the equipment; Determination of the cause of energy consumption peak: Finally, based on the correlation results between behavior patterns and equipment energy consumption, in-depth analysis is performed on highly correlated behaviors to determine whether the behaviors are the cause of the equipment energy consumption peak; if the correlation between a behavior pattern and equipment energy consumption reaches the set threshold, the behavior is determined to be the main cause of the energy consumption peak.

6. The smart campus integrated management and service system according to claim 1 is characterized in that: The energy scheduling optimization module includes an equipment usage monitoring unit, a weather data acquisition unit, a carbon emission analysis unit and an optimization algorithm unit; wherein: Equipment usage monitoring unit: used to monitor the operation of all energy-consuming equipment on campus in real time, including the start and stop status of the equipment, current power and operating time. The equipment usage monitoring unit continuously obtains the real-time status data of the equipment by connecting to sensors of various types of equipment; Weather data acquisition unit: by connecting with external weather stations or internal environmental sensors, it can obtain current weather information in real time, including climate data of temperature, humidity, and wind speed; Carbon emission analysis unit: Analyze the carbon emission level of the current equipment according to the carbon emission report provided by the carbon footprint calculation module, identify high carbon emission equipment or areas, and determine the carbon emission contribution of the equipment in combination with the energy consumption data of the equipment usage monitoring unit; Optimization algorithm unit: Through a preset optimization algorithm, based on the data provided by the equipment usage monitoring unit, the weather data acquisition unit and the carbon emission analysis unit, the operating status of the energy-consuming equipment is dynamically adjusted to minimize the energy consumption of the equipment.

7. The smart campus integrated management and service system according to claim 6 is characterized in that: The optimization algorithm unit specifically includes: Objective function: Assume that the goal of the optimization algorithm is to minimize the total energy consumption E total , its objective function expression is: Among them, P i (t) is the power of the i-th device at time t, T i is the running time of the device, and n is the total number of devices; Constraints: define the constraints on equipment operation, including usage demand constraints and weather impact constraints; Usage demand constraints: the equipment must meet the actual usage needs of teachers and students. The equipment operation time T i and power P i (t) It needs to be adjusted dynamically according to the device type and usage requirements; Weather impact constraints, for weather-sensitive equipment constraints, power P i (t) needs to be adjusted according to weather data, the formula is: Among them, P max is the maximum power of the device, T opt is the optimal operating temperature of the equipment, T actual is the current actual temperature; Optimization process: According to the objective function and constraints, the gradient descent algorithm is used to dynamically adjust the operating time and power of the equipment. After gradual iteration, it ensures that the total energy consumption is minimized while meeting the usage requirements.

8. The smart campus integrated management and service system according to claim 1 is characterized in that: The energy consumption prediction module includes a historical data processing unit, a feature extraction unit, a machine learning model training unit, an energy consumption trend prediction unit and an early warning trigger unit; wherein: Historical data processing unit: used to obtain historical energy consumption data, behavior patterns and equipment scheduling status from the energy consumption monitoring module, behavior data integration module and energy scheduling optimization module; the historical energy consumption data includes the operating power, start and stop time and total energy consumption of the equipment in the past, and the behavior pattern data includes the activity patterns of teachers and students and the use of equipment; the historical data processing unit also includes normalizing the acquired data and unifying the format; Feature extraction unit: used to extract features from historical data, including behavior pattern features, energy consumption features, and weather data features; Machine learning model training unit: Based on the regression analysis algorithm, combined with historical data and extracted feature vectors, the machine learning model is trained to predict future energy consumption trends. The regression model is used to predict energy consumption in the future period. Energy consumption trend prediction unit: After the machine learning model is trained, the energy consumption trend prediction unit uses the current energy consumption data, behavior patterns, and weather data as input to generate energy consumption forecasts for future periods. It uses the trained regression model to output energy consumption forecasts for each device or region in the future period. Early warning trigger unit: Based on the output results of the energy consumption trend prediction unit, the predicted energy consumption value is analyzed. If the energy consumption value in a certain period of time is found Exceeds the set energy consumption threshold E max , or the carbon emissions of the corresponding equipment exceed the carbon emission threshold C max When an alarm occurs, it will automatically trigger an early warning and notify the management personnel to take measures.

9. The smart campus integrated management and service system according to claim 1 is characterized in that: The adaptive energy efficiency improvement module includes an energy consumption history data analysis unit, a carbon footprint report analysis unit, an inefficient link identification unit, and an energy-saving solution generation unit; wherein: Energy consumption historical data analysis unit: By continuously analyzing the energy consumption historical data of all equipment on campus, identify equipment or areas with high energy consumption. During the analysis process, the energy consumption data is divided into different time periods and classified by equipment type and area to identify the energy efficiency performance in different time periods and equipment categories; and by calculating the difference between the average energy consumption and the actual energy consumption of each device, it is determined whether the device is in a high energy consumption state; Carbon footprint report analysis unit: Based on the carbon footprint report generated by the carbon footprint calculation module and combined with the results of the energy consumption history data analysis unit, the carbon emission contribution of each device and region is analyzed. By calculating the relationship between the carbon emissions of each device and its corresponding energy consumption, the device or region with excessively high carbon emissions but low energy efficiency is identified; Inefficient Link Identification Unit: By analyzing the historical energy consumption data and carbon footprint reports, it identifies the inefficient links that have existed on campus for a long time, including aging equipment, equipment that is used too frequently, equipment that is not shut down in time, and equipment that is idling too much. Energy-saving solution generation unit: used to propose corresponding energy efficiency improvement solutions after identifying low-efficiency links. The energy-saving solutions include adjusting the equipment operation time, reducing the power of the equipment, optimizing the equipment scheduling strategy, and regular equipment maintenance and upgrades.

10. The smart campus integrated management and service system according to claim 1, characterized in that: The multi-dimensional energy-saving strategy evaluation module includes an energy-saving effect evaluation unit, an operation cost evaluation unit, a user satisfaction evaluation unit and an optimal solution selection unit; wherein: Energy-saving effect evaluation unit: used to monitor the energy consumption changes after the implementation of each energy-saving plan and calculate the actual energy-saving effect of each plan; Operation cost evaluation unit: evaluates the economic feasibility of each energy-saving plan by analyzing the implementation cost and long-term operation cost of each plan. The operation cost calculation includes the initial equipment adjustment cost, the labor cost of plan execution, the equipment maintenance cost and the long-term energy saving cost; User satisfaction evaluation unit: By collecting feedback from teachers and students, the impact of each energy-saving solution on user experience is evaluated. The specific evaluation includes comfort, convenience of equipment use, and satisfaction with the working and learning environment; Optimal solution selection unit: Based on the comprehensive evaluation results of three indicators, namely energy-saving effect, operating cost and user satisfaction, the optimal energy-saving solution is selected using a weighted scoring method.

Images