Smart campus energy-saving management method and system based on Internet of Things

Abstract

The invention relates to the field of campus energy-saving management, and discloses a smart campus energy-saving management method and system based on the Internet of Things, and the method comprises the following steps: transmitting collected power utilization data to a cloud server for storage; ultrasonic signals of the campus building are obtained and transmitted to the cloud server; defects existing in the campus building are recognized, and defect repairing is carried out; formulating energy-saving strategies of classes and public places; if the daily power consumption of the class or the public place exceeds the daily energy-saving power consumption target power, feeding back to a manager; the system comprises a power utilization data acquisition module, an ultrasonic data acquisition module, a model construction module, a power utilization equipment adjustment module and an energy-saving feedback module. The defects of the building structure can be found and repaired in time, potential safety hazards can be prevented, the thermal insulation performance of the campus building can be guaranteed by repairing the campus building, the place where water possibly leaks can be found in time, and energy consumption of the campus building is reduced.

Description

Technical Field

[0001] The present invention relates to the field of campus energy conservation management, and in particular to a method and system for smart campus energy conservation management based on the Internet of Things. Background Art

[0002] Educational institutions not only need to provide high-quality education, but also need to introduce advanced scientific and technological means in campus management to improve efficiency, reduce costs, and achieve sustainable development. The smart campus energy-saving management method is an innovative solution based on Internet of Things technology, which aims to achieve intelligent scheduling and rational use of energy resources on campus through intelligent equipment, data analysis and remote monitoring.

[0003] With the development of society and the advancement of science and technology, the Internet of Things technology has been widely used in various fields, including education. Smart campus is a modern campus management model that comprehensively uses advanced technologies such as the Internet of Things, big data, and cloud computing to improve school management efficiency, provide better educational services, and achieve resource sharing and energy conservation and emission reduction. In a smart campus, energy-saving management is an important aspect, aiming to minimize energy consumption through intelligent means.

[0004] For example, Chinese patent 202310033422.8 discloses a method and system for energy-saving management of a smart campus, which uses the target energy-saving campus information to perform energy-saving management on the target campus, solving the problem of low refinement of campus electricity management, and realizing the use of self-generated electricity to compensate for the excess electricity consumption in classes that waste electricity resources, providing support for completely eliminating the waste of electricity resources. However, the above method still has the following shortcomings: the electricity consumption data on campus cannot be accessed anytime and anywhere, resulting in the staff's lack of timely understanding of the electricity consumption situation; at the same time, when conducting campus energy-saving management, it does not take into account the defects of the buildings on campus for detection, and does not comprehensively manage the building defects and campus energy conservation, which is not conducive to reducing the energy consumption of campus buildings.

[0005] Currently, no effective solution has been proposed for the problems in the related technologies. Summary of the invention

[0006] In view of this, the purpose of the embodiments of the present application is to provide a method and system for energy-saving management of a smart campus based on the Internet of Things to overcome the above-mentioned technical problems existing in the existing related technologies.

[0007] To this end, the specific technical solution adopted by the present invention is as follows: According to one aspect of the present invention, a method for energy-saving management of a smart campus based on the Internet of Things is provided, and the method for energy-saving management of a smart campus based on the Internet of Things comprises the following steps: S1. IoT devices are deployed in classrooms and public places on campus. Real-time collection of electricity consumption data is achieved through IoT devices, and the collected electricity consumption data is transmitted to the cloud server for storage.

[0008] S2. Perform ultrasonic detection on each campus building on campus, obtain the ultrasonic signals of the campus buildings, and transmit the ultrasonic signals to the cloud server through the Internet of Things technology.

[0009] S3. Build a detection model and deploy it on a cloud server. Use the detection model to process and analyze the ultrasonic signals of campus buildings, identify defects in campus buildings, and repair them to ensure that energy consumption of campus buildings is reduced after the defects are repaired.

[0010] S4. Adjust the working status of campus electrical equipment in real time according to the electricity consumption data of classes and public places, and formulate energy-saving strategies for classes and public places based on the energy consumption data before and after the restoration of campus buildings.

[0011] S5. Obtain the daily energy-saving electricity target for each class and public place on campus, and obtain the electricity consumption of each class and public place on campus in real time. If the daily electricity consumption of a class or public place exceeds the daily energy-saving electricity target, feedback will be provided to the management staff.

[0012] Among them, the working status of campus electrical equipment is adjusted in real time according to the electricity consumption data of classes and public places, and energy-saving strategies for classes and public places are formulated in combination with the energy consumption data before and after the restoration of campus buildings, including: S41. Based on the collected electricity consumption data of classes and public places, identify the peak and valley periods of electricity consumption, and obtain the electricity consumption patterns of classes and public places; S42. Combine the electricity consumption patterns of classrooms and public places and the energy consumption data of campus buildings before and after restoration to evaluate the impact of campus building defects on campus building electricity consumption and obtain the correlation model between building defects and electricity consumption; S43. Formulate energy-saving strategies based on the correlation pattern between building defects and electricity consumption; S44: Monitor the operating status of electrical equipment in real time and automatically adjust the working status of electrical equipment to match energy-saving strategies through Internet of Things technology.

[0013] Optionally, a detection model is constructed and deployed on a cloud server, and ultrasonic signals of campus buildings are processed and analyzed by the detection model to identify defects of campus buildings and repair them, thereby ensuring that energy consumption of campus buildings is reduced after the defects are repaired. The steps include: S31. Collect data of ultrasonic signals of several campus buildings, including normal signals and signals with defects; S32, performing noise reduction, filtering and normalization processing on the collected ultrasonic signals of campus buildings; S33, constructing a detection model based on a support vector machine algorithm and setting parameters; S34, using labeled or unlabeled ultrasonic signal data to train the detection model and optimize the performance of the detection model; S35, evaluating the detection model using the data of the ultrasonic signal used for the test; S36, deploying the trained detection model to a cloud server, processing and analyzing the real-time or offline ultrasonic signals of campus buildings, and outputting the defects of campus buildings; S37. Carry out corresponding repairs according to the defects of campus buildings; S38, storing the repaired building structure data in the cloud server, and updating the building model data for subsequent reference; S39. Obtain energy consumption data of campus buildings before and after restoration, and verify the restoration effect to ensure that energy consumption of campus buildings is reduced after restoration.

[0014] Optionally, when outputting defects existing in campus buildings, the defects include structural defects and functional defects.

[0015] Optionally, building a detection model based on a support vector machine algorithm and setting parameters includes the following steps: S331, using the support vector machine algorithm to build a detection model, and setting the initial penalty parameter and kernel function width parameter; S332. Use an optimization algorithm to update the penalty parameters and kernel function width parameters of the detection model.

[0016] Optionally, updating the penalty parameter and kernel function width parameter of the detection model using the optimization algorithm includes the following steps: S3321, defining a fitness function, and using the penalty parameter and kernel function width parameter of the detection model as inputs of the fitness function, and outputting a performance evaluation index of the detection model constructed using the given penalty parameter and kernel function width parameter on the training data set; S3322, configuring a number of agents, each of which includes a combination of a penalty parameter of a detection model and a kernel function width parameter, and initializing iteration parameters of an optimization algorithm, the iteration parameters including the number of agents, the number of iterations, and the trust residual rate; S3323, using roulette method to select the starting position for the agent; S3324. According to the path selection mechanism, each agent is enabled to select a path, and the trust on the path is updated according to the result of the fitness function; S3325. Select a set of penalty parameters and kernel function width parameters with the highest fitness function value as the optimal penalty parameters and kernel function width parameters.

[0017] Optionally, the trust residual rate is a value between zero and one. If the performance of the detection model in the current iteration is improved when the penalty parameter and kernel function width parameter of the detection model are updated, the trust residual rate is increased; otherwise, the trust residual rate is reduced.

[0018] Optionally, selecting a starting position for an agent using a roulette wheel method comprises the following steps: S33231. construct a number of position nodes, form edges between the position nodes, and calculate importance scores for the number of position nodes; S33232. Calculate the selection probability of a plurality of position nodes; S33233. Generate a random number between zero and one, and starting from the first position node, accumulate the selection probability until it is greater than or equal to the random number, and use the position node selected when it is greater than or equal to the random number as the starting position of the agent.

[0019] Optionally, when calculating the importance scores of several location nodes, the scores are scored using degree centrality and standardized; When calculating the selection probability of several position nodes, the selection probability formula is used for calculation; Among them, the selection probability formula is: ; In the formula, C i Represents the location node i The degree centrality score of D i Represents the location node i The betweenness centrality score of ; P i Represents the location node i The probability of selection; Represents the sum of the degree centrality scores and betweenness centrality scores of all location nodes.

[0020] Optionally, according to the path selection mechanism, each agent is enabled to select a path, and according to the result of the fitness function, the trust on the path is updated, including the following steps: S33241. Starting from the starting position of the agent, select the next location node to be reached according to the greedy strategy, and calculate the fitness function value; S33242. When the agent cannot move forward or reaches the preset path length, it stops searching and records the current path and fitness function value; S33243, configuring an initial trust for each edge between position nodes, and calculating a trust increment based on the fitness function value of the path, and multiplying the trust increment by the trust residual rate and adding the trust increment to the initial trust to obtain a new trust; S33244. Update the trust of the edges on all paths and execute a preset number of iterations.

[0021] Optionally, obtaining the daily energy-saving electricity consumption target of each class and public place on campus includes the following steps: S51, calculating future electricity consumption based on historical electricity consumption data of each class and public place; S52, quantitatively analyzing the implementation effects of various energy-saving strategies to obtain the quantitative effects of the energy-saving strategies; S53, feeding back the quantified effect of the energy-saving strategy to the future electricity consumption to obtain the corrected future electricity consumption; S54. The corrected future electricity consumption is used as the energy-saving electricity consumption target on the corresponding date.

[0022] According to another aspect of the present invention, a system for energy-saving management of a smart campus based on the Internet of Things is provided, and the system for energy-saving management of a smart campus based on the Internet of Things includes an electricity consumption data acquisition module, an ultrasonic data acquisition module, a model building module, an electricity equipment adjustment module and an energy-saving feedback module; wherein the electricity consumption data acquisition module is connected to the ultrasonic data acquisition module, the electricity equipment adjustment module and the energy-saving feedback module, and the ultrasonic data acquisition module is connected to the model building module.

[0023] The electricity consumption data collection module is used to deploy IoT devices in classrooms and public places on campus, and to realize real-time collection of electricity consumption data through IoT devices, and transmit the collected electricity consumption data to the cloud server for storage.

[0024] The ultrasonic data acquisition module is used to perform ultrasonic detection on each campus building, obtain the ultrasonic signals of the campus buildings, and transmit the ultrasonic signals to the cloud server through the Internet of Things technology.

[0025] The model building module is used to build a detection model and deploy the detection model on a cloud server. The detection model is used to process and analyze the ultrasonic signals of campus buildings, identify defects in campus buildings, and repair them.

[0026] The power equipment adjustment module is used to adjust the working status of campus power equipment in real time according to the power consumption data of classes and public places, and to formulate energy-saving strategies for classes and public places.

[0027] The energy-saving feedback module is used to obtain the daily energy-saving power target of each class and public place on campus, and obtain the power consumption of each class and public place on campus in real time. If the daily power consumption of a class or public place exceeds the daily energy-saving power target, feedback will be given to the management personnel.

[0028] Embodiments of the present invention include the following benefits: (1) The present invention provides a method and system for energy-saving management of smart campuses based on the Internet of Things. The collected campus electricity consumption data is uploaded to the cloud server through the Internet of Things device. School personnel can access the real-time data anytime and anywhere to understand the campus electricity consumption situation. By acquiring the ultrasonic signal of the campus building, transmitting the ultrasonic signal to the cloud server through the Internet of Things technology, and performing defect detection, school personnel can understand the defects of the campus buildings.

[0029] (2) The present invention processes and analyzes the ultrasonic signals of campus buildings through the detection model, identifies the defects of campus buildings and repairs them, thereby timely discovering and repairing the defects of the building structure, which can prevent potential safety hazards. In addition, by repairing the campus buildings, the thermal insulation performance of the campus buildings is guaranteed, and possible leaks are discovered in time, thereby reducing the energy consumption of campus buildings and improving energy-saving effects.

[0030] (3) The present invention uses a support vector machine algorithm to construct a detection model, and dynamically adjusts the penalty parameter and kernel function width parameter through an optimization algorithm, so that the detection model can better adapt to different types of campus building defects and improve the generalization performance of the model; by continuously optimizing the model parameters, the detection model can more accurately identify various types of defects in campus buildings, reduce the false recognition rate, and improve the accuracy of detection; the optimization algorithm can make the detection model have better robustness, that is, when facing various complex and changeable campus building environments, the model can stably maintain good performance and is not easily affected by noise and interference. By automatically adjusting the parameters, the need for manual parameter adjustment is reduced, the degree of automation of the model is improved, and the cost and complexity of manual intervention are reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0032] Figure 1 is a flow chart of a method for energy-saving management of a smart campus based on the Internet of Things according to an embodiment of the present invention; Figure 2It is a principle block diagram of a system for energy-saving management of a smart campus based on the Internet of Things according to an embodiment of the present invention.

[0033] In the figure: 1. Electricity consumption data acquisition module; 2. Ultrasonic data acquisition module; 3. Model building module; 4. Electricity equipment adjustment module; 5. Energy-saving feedback module. DETAILED DESCRIPTION

[0034] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0035] To further illustrate each embodiment, the present invention provides drawings, which are part of the disclosure of the present invention and are mainly used to illustrate the embodiments and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these contents, ordinary technicians in the field should be able to understand other possible implementations and advantages of the present invention. The components in the figures are not drawn to scale, and similar component symbols are generally used to represent similar components.

[0036] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0037] According to an embodiment of the present invention, a method and system for energy-saving management of a smart campus based on the Internet of Things are provided.

[0038] The present invention is further described with reference to the accompanying drawings and specific embodiments. Figure 1 As shown, according to an embodiment of the present invention, a method for energy-saving management of a smart campus based on the Internet of Things is provided, and the method for energy-saving management of a smart campus based on the Internet of Things comprises the following steps: S1. IoT devices are deployed in classrooms and public places on campus, and real-time electricity consumption data is collected through IoT devices. The collected electricity consumption data is transmitted to the cloud server for storage. At the same time, electricity consumption data can also be collected regularly, so that relevant campus personnel can obtain campus electricity consumption information in a timely manner.

[0039] S2, conduct ultrasonic detection on each campus building, obtain ultrasonic signals of the campus buildings, and transmit the ultrasonic signals to the cloud server through the Internet of Things technology; S3. Build a detection model and deploy it on a cloud server. Use the detection model to process and analyze the ultrasonic signals of campus buildings, identify defects in campus buildings, and repair them to ensure that energy consumption of campus buildings is reduced after the defects are repaired. It should be noted that the types of campus building defects include structural defects and functional defects; Structural defects: refers to cracks, deformation, damage and other phenomena in the walls of campus buildings, which affect the stability and safety of campus buildings. Functional defects: refers to malfunctions, failures, aging and other phenomena in the walls of campus buildings, which affect the usability and comfort of campus buildings. These defects cause the thermal insulation performance to decline, making campus buildings require more energy to maintain indoor temperature.

[0040] In a further embodiment, a detection model is constructed and deployed on a cloud server, and ultrasonic signals of campus buildings are processed and analyzed by the detection model to identify defects in campus buildings and repair them, thereby ensuring that energy consumption of campus buildings is reduced after the defects are repaired. The steps include: S31. Collect data of ultrasonic signals of several campus buildings, including normal signals and signals with defects; use some professional equipment, such as ultrasonic transmitters and receivers, to collect ultrasonic signals of campus buildings; S32, performing noise reduction, filtering and normalization processing on the collected ultrasonic signals of campus buildings to improve the quality and availability of the ultrasonic signals; S33, constructing a detection model based on a support vector machine algorithm and setting parameters; S34, using labeled or unlabeled ultrasonic signal data to train the detection model and optimize the performance of the detection model; S35, using the data of the ultrasonic signal used for the test to evaluate the detection model, and checking the accuracy, recall rate, F1 value and other indicators of the detection model; S36. Deploy the trained detection model to the cloud server, process and analyze the real-time or offline ultrasonic signals of campus buildings, and output the defects of the campus buildings.

[0041] S37. Carry out corresponding repairs according to the defects of campus buildings; S38, storing the repaired building structure data in the cloud server, and updating the building model data for subsequent reference; S39. Obtain energy consumption data of campus buildings before and after restoration, and verify the restoration effect to ensure that energy consumption of campus buildings is reduced after restoration.

[0042] Features are extracted from the collected ultrasonic signals. These features can be the frequency domain features, time domain features, amplitude features, etc. of the signal, which are used to describe different aspects of the signal. The ultrasonic signal data is annotated (the types of campus building defects are annotated), and the new ultrasonic signal can be predicted through the detection model built based on the support vector machine algorithm.

[0043] In a further embodiment, when outputting defects existing in campus buildings, the defects include structural defects and functional defects.

[0044] In a further embodiment, constructing a detection model based on a support vector machine algorithm and setting parameters includes the following steps: S331, using the support vector machine algorithm to build a detection model, and setting the initial penalty parameter and kernel function width parameter; S332. Use an optimization algorithm to update the penalty parameters and kernel function width parameters of the detection model.

[0045] In a further embodiment, updating the penalty parameter and kernel function width parameter of the detection model using the optimization algorithm comprises the following steps: S3321, defining a fitness function, that is, defining an evaluation index, and taking a penalty parameter and a kernel function width parameter of the detection model as inputs of the fitness function, and outputting a performance evaluation index of the detection model constructed using the given penalty parameter and kernel function width parameter on the training data set; In addition, the fitness function can be set as: ; In the formula, A represents the penalty parameter of the detection model, B Represents the kernel function width parameter; n represents the number of samples in the training data set, y j Indicates j The true labels of samples, Indicates j The predicted label of each sample. The accuracy of the detection model on the training data set is output through the fitness function, that is, the proportion of correct classification. The samples in the training data set are labeled or unlabeled ultrasonic signal data, marking whether there are defects and the type of defects.

[0046] S3322. Configure several agents, each of which includes a combination of a penalty parameter of a detection model and a kernel function width parameter, and initialize the iteration parameters of the optimization algorithm, the iteration parameters including the number of agents, the number of iterations, and the trust residual rate.

[0047] S3323. Use a roulette wheel method to select a starting position for the agent in order to increase the probability of selecting a better solution.

[0048] S3324. According to the path selection mechanism, each agent selects a path and updates the trust on the path according to the result of the fitness function. This step is an optimization process, which searches for a better solution through path selection and trust update. In this step, the agent selects a better path, that is, a better parameter combination, so its fitness function value will be higher. In S3325, the set of parameters with the highest fitness function value will be selected as the final penalty parameter and kernel function width parameter, so the path selection and trust update in S3324 directly affect the final result of S3325.

[0049] S3325. Select a set of penalty parameters and kernel function width parameters with the highest fitness function value as the optimal penalty parameters and kernel function width parameters.

[0050] In a further embodiment, the trust residual rate is a value between zero and one. If the performance of the detection model in the current iteration is improved when the penalty parameters and kernel function width parameters of the detection model are updated, the trust residual rate is increased to explore the new parameter space more. Otherwise, the trust residual rate is reduced to make better use of existing experience.

[0051] In a further embodiment, selecting a starting position for an agent using a roulette wheel method comprises the following steps: S33231. construct a number of position nodes, form edges between the position nodes, and calculate importance scores for the number of position nodes; S33232. Calculate the selection probability of a plurality of position nodes; S33233. Generate a random number between zero and one, and starting from the first position node, accumulate the selection probability until it is greater than or equal to the random number, and use the position node selected when it is greater than or equal to the random number as the starting position of the agent.

[0052] In a further embodiment, when calculating the importance scores of several location nodes, the scores are scored using degree centrality and standardized; degree centrality refers to an indicator of node centrality; When calculating the selection probability of several position nodes, the selection probability formula is used for calculation; Among them, the selection probability formula is: ; In the formula, C i Represents the location node i The degree centrality score of D i Represents the location node i The betweenness centrality score of ; Pi Represents a location node i The probability of selection; Represents the sum of the degree centrality scores and betweenness centrality scores of all location nodes.

[0053] In a further embodiment, according to the path selection mechanism, each agent is made to select a path, and according to the result of the fitness function, the trust on the path is updated, including the following steps: S33241. Starting from the starting position of the agent, select the next location node to be reached according to the greedy strategy and calculate the fitness function value; select the node with the highest fitness function value on the path, that is, the node that is most likely to lead to improved model performance under the current search state.

[0054] S33242. When the agent cannot move forward or reaches the preset path length, it stops searching and records the current path and fitness function value for subsequent trust updates.

[0055] S33243. Configure the initial trust for each edge between the position nodes, and calculate the trust increment according to the fitness function value of the path. The trust increment is calculated using a linear mapping relationship, and the trust increment is multiplied by the trust residual rate and added to the initial trust to obtain a new trust; that is, if the searched path has good performance, the trust will be increased, otherwise the trust will be reduced. The trust will affect the choice of the path in subsequent searches. It ensures that a better path will have a higher trust.

[0056] S33244, update the trust of the edges on all paths and execute the preset number of iterations. That is, the trust will affect the path selection in the next iteration. After the update is completed, according to the preset number of iterations, the whole process may be repeated multiple times until the preset number of iterations is reached.

[0057] S4. Adjust the working status of campus electrical equipment in real time according to the electricity consumption data of classes and public places, and formulate energy-saving strategies for classes and public places based on the energy consumption data before and after the restoration of campus buildings, such as automatic shutdown of equipment during non-working hours, switch time, temperature setting and lighting brightness adjustment; In a further embodiment, the working state of campus electrical equipment is adjusted in real time according to the electricity consumption data of classes and public places, and energy-saving strategies for classes and public places are formulated in combination with the energy consumption data before and after the restoration of campus buildings, including: S41. Based on the collected electricity consumption data of classes and public places, identify the peak and valley periods of electricity consumption, and obtain the electricity consumption patterns of classes and public places, such as class time, breaks, lunch breaks, and non-working time; S42. Combine the electricity consumption patterns of classes and public places and the energy consumption data before and after the repair of campus buildings to evaluate the impact of campus building defects (such as insulation performance and water leakage) on campus building electricity consumption, and obtain the correlation pattern between building defects and electricity consumption; Specifically: Use the characteristics of campus building defects and other factors as independent variables of the model. For example, the number of cracks, the area of ​​insulation damage, the number of water leakage points, outdoor temperature, etc. Electricity consumption is used as the target variable. The independent variables and target variables form a data set, and the linear regression model is trained using the data set to extract the correlation pattern between building defects and electricity consumption from the trained regression model.

[0058] S43. Develop energy-saving strategies based on the correlation patterns between building defects and electricity consumption; for example, the correlation patterns include that for every 10% increase in insulation damage, the air conditioning electricity consumption increases by 20%. Each water leak causes a 5% increase in the air conditioning system electricity consumption. For every additional year of lighting system aging, the electricity consumption increases by 10%.

[0059] Strategy 1: Insulation layer maintenance strategy.

[0060] Check the insulation layer of the classroom every quarter and repair any damage in a timely manner.

[0061] Install thermal insulation curtains in classrooms to further reduce air conditioning load.

[0062] Strategy 2: Water leakage problem solution strategy Check the office pipes and ceilings monthly and repair any leaks immediately.

[0063] Install humidity sensors to monitor indoor humidity in real time to prevent excessive humidity due to water leakage and increase air conditioning load.

[0064] Use high-efficiency waterproof materials in areas prone to water leakage to reduce the risk of water leakage.

[0065] Strategy 3: Lighting system optimization strategy Upgrading aging classroom lighting systems to high-efficiency LED lighting to reduce electricity usage.

[0066] Install an intelligent lighting control system to automatically adjust lighting brightness based on natural light intensity and automatically turn off lights when no one is around.

[0067] Clean lighting equipment monthly to ensure lighting efficiency and reduce insufficient brightness caused by dust accumulation.

[0068] S44: Monitor the operating status of electrical equipment in real time and automatically adjust the working status of electrical equipment to match energy-saving strategies through Internet of Things technology.

[0069] S5. Obtain the daily energy-saving electricity target for each class and public place on campus, and obtain the electricity consumption of each class and public place on campus in real time. If the daily electricity consumption of a class or public place exceeds the daily energy-saving electricity target, feedback will be provided to the management personnel to optimize the energy-saving strategy, that is, statistics on the electricity consumption of the class or public place will be collected to find out whether there is any waste of electricity or whether the daily energy-saving electricity target is unreasonable.

[0070] In a further embodiment, obtaining the daily energy-saving power consumption target of each class and public place on campus includes the following steps: S51. Calculate future power consumption based on historical power consumption data of each class and public place. For example, calculate the average power consumption of the historical day, and use the average power consumption of the historical day as the future power consumption.

[0071] S52. Quantitatively analyze the implementation effects of various energy-saving strategies to obtain the quantitative effects of energy-saving strategies; for example, a classroom saves 15 kWh through strategy 1, and public place 1 saves 20 kWh through strategy 2.

[0072] S53, feeding back the quantified effect of the energy-saving strategy to the future electricity consumption to obtain the revised future electricity consumption; for example, subtracting the quantified effect of each energy-saving strategy from the adjusted future electricity consumption to obtain the revised future electricity consumption.

[0073] S54. The corrected future electricity consumption is used as the energy-saving electricity consumption target on the corresponding date.

[0074] like Figure 2 As shown, according to another embodiment of the present invention, a system for energy-saving management of a smart campus based on the Internet of Things is provided, and the system for energy-saving management of a smart campus based on the Internet of Things includes an electricity consumption data acquisition module 1, an ultrasonic data acquisition module 2, a model building module 3, an electricity equipment adjustment module 4 and an energy-saving feedback module 5; wherein the electricity consumption data acquisition module 1 is connected to the ultrasonic data acquisition module 2, the electricity equipment adjustment module 4 and the energy-saving feedback module 5, and the ultrasonic data acquisition module 2 is connected to the model building module 3.

[0075] The electricity consumption data collection module 1 is used to deploy Internet of Things devices in classrooms and public places on campus, and to realize real-time collection of electricity consumption data through the Internet of Things devices, and to transmit the collected electricity consumption data to the cloud server for storage.

[0076] The ultrasonic data acquisition module 2 is used to perform ultrasonic detection on each campus building, obtain the ultrasonic signals of the campus buildings, and transmit the ultrasonic signals to the cloud server through the Internet of Things technology.

[0077] The model building module 3 is used to build a detection model and deploy the detection model on a cloud server. The detection model is used to process and analyze the ultrasonic signals of campus buildings, identify defects in campus buildings, and repair them.

[0078] The electrical equipment adjustment module 4 is used to adjust the working status of campus electrical equipment in real time according to the electricity consumption data of classes and public places, and formulate energy-saving strategies for classes and public places.

[0079] The energy-saving feedback module 5 is used to obtain the daily energy-saving power consumption target of each class and public place on campus, and obtain the power consumption of each class and public place on campus in real time. If the daily power consumption of a class or public place exceeds the daily energy-saving power consumption target, feedback will be given to the management personnel.

[0080] In summary, the present invention provides a method and system for energy-saving management of a smart campus based on the Internet of Things. The collected campus electricity consumption data is uploaded to a cloud server through an Internet of Things device, and school-related personnel can access real-time data anytime and anywhere to understand the campus electricity consumption situation. By obtaining the ultrasonic signal of the campus building, transmitting the ultrasonic signal to the cloud server through the Internet of Things technology, and performing defect detection, school-related personnel can understand the defects of the campus building. The present invention processes and analyzes the ultrasonic signal of the campus building through a detection model, identifies the defects of the campus building and repairs the defects, thereby timely discovering and repairing the defects of the building structure, which can prevent potential safety hazards, and through the repair of the campus building, the thermal insulation performance of the campus building is guaranteed, and possible leaks are discovered in time, reducing the energy consumption of the campus building and improving the energy-saving effect. The present invention uses a support vector machine algorithm to construct a detection model, and dynamically adjusts the penalty parameter and the kernel function width parameter through an optimization algorithm, so that the detection model can better adapt to different types of campus building defects and improve the generalization performance of the model; by continuously optimizing the model parameters, the detection model can more accurately identify various types of defects in campus buildings, reduce the false recognition rate, and improve the accuracy of detection; the optimization algorithm can make the detection model have better robustness, that is, when facing various complex and changeable campus building environments, the model can stably maintain good performance and is not easily affected by noise and interference. By automatically adjusting the parameters, the need for manual parameter adjustment is reduced, the degree of automation of the model is improved, and the cost and complexity of manual intervention are reduced.

[0081] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional charging modules / units in the systems and devices may be implemented as software, firmware, hardware, or appropriate combinations thereof.

[0082] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0083] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for energy-saving management of a smart campus based on the Internet of Things, characterized in that: The method for energy-saving management of smart campus based on the Internet of Things comprises the following steps: S1. IoT devices are deployed in classrooms and public places on campus, and real-time electricity consumption data is collected through IoT devices, and the collected electricity consumption data is transmitted to the cloud server for storage; S2, conduct ultrasonic detection on each campus building, obtain ultrasonic signals of the campus buildings, and transmit the ultrasonic signals to the cloud server through the Internet of Things technology; S3. Build a detection model and deploy it on a cloud server. Use the detection model to process and analyze the ultrasonic signals of campus buildings, identify defects in campus buildings, and repair them to ensure that energy consumption of campus buildings is reduced after the defects are repaired. S4. Adjust the working status of campus electrical equipment in real time according to the electricity consumption data of classes and public places, and formulate energy-saving strategies for classes and public places in combination with the energy consumption data before and after the restoration of campus buildings; S5. Obtain the daily energy-saving electricity consumption target of each class and public place on campus, and obtain the electricity consumption of each class and public place on campus in real time. If the daily electricity consumption of a class or public place exceeds the daily energy-saving electricity consumption target, feedback will be given to the management personnel; The method of adjusting the working status of campus electrical equipment in real time according to the electricity consumption data of classes and public places, and formulating energy-saving strategies for classes and public places in combination with the energy consumption data of campus buildings before and after restoration includes: S41. Based on the collected electricity consumption data of classes and public places, identify the peak and valley periods of electricity consumption, and obtain the electricity consumption patterns of classes and public places; S42. Combine the electricity consumption patterns of classrooms and public places and the energy consumption data of campus buildings before and after restoration to evaluate the impact of campus building defects on campus building electricity consumption and obtain the correlation model between building defects and electricity consumption; S43. Formulate energy-saving strategies based on the correlation pattern between building defects and electricity consumption; S44: Monitor the operating status of electrical equipment in real time and automatically adjust the working status of electrical equipment to match energy-saving strategies through Internet of Things technology.

2. According to the method of energy-saving management of a smart campus based on the Internet of Things according to claim 1, it is characterized in that: The construction of the detection model and the deployment of the detection model on the cloud server, the processing and analysis of the ultrasonic signals of the campus buildings by the detection model, the identification of defects in the campus buildings and the repair of the defects, and the reduction of energy consumption of the campus buildings after the defects are repaired include the following steps: S31. Collect data of ultrasonic signals of several campus buildings, including normal signals and signals with defects; S32, performing noise reduction, filtering and normalization processing on the collected ultrasonic signals of campus buildings; S33, constructing a detection model based on a support vector machine algorithm and setting parameters; S34, using labeled or unlabeled ultrasonic signal data to train the detection model and optimize the performance of the detection model; S35, evaluating the detection model using the data of the ultrasonic signal used for the test; S36, deploying the trained detection model to a cloud server, processing and analyzing the real-time or offline ultrasonic signals of campus buildings, and outputting the defects of campus buildings; S37. Carry out corresponding repairs according to the defects of campus buildings; S38, storing the repaired building structure data in the cloud server, and updating the building model data for subsequent reference; S39. Obtain energy consumption data of campus buildings before and after restoration, and verify the restoration effect to ensure that energy consumption of campus buildings is reduced after restoration.

3. The method for energy-saving management of a smart campus based on the Internet of Things according to claim 2 is characterized in that: When outputting the defects existing in the campus buildings, the defects include structural defects and functional defects.

4. The method for energy-saving management of a smart campus based on the Internet of Things according to claim 2 is characterized in that: The construction of the detection model based on the support vector machine algorithm and setting parameters include the following steps: S331, using the support vector machine algorithm to build a detection model, and setting the initial penalty parameter and kernel function width parameter; S332. Use an optimization algorithm to update the penalty parameters and kernel function width parameters of the detection model.

5. The method for energy-saving management of a smart campus based on the Internet of Things according to claim 4 is characterized in that: The method of updating the penalty parameter and kernel function width parameter of the detection model using the optimization algorithm comprises the following steps: S3321, defining a fitness function, and using the penalty parameter and kernel function width parameter of the detection model as inputs of the fitness function, and outputting a performance evaluation index of the detection model constructed using the given penalty parameter and kernel function width parameter on the training data set; S3322, configuring a number of agents, each of which includes a combination of a penalty parameter of a detection model and a kernel function width parameter, and initializing iteration parameters of an optimization algorithm, the iteration parameters including the number of agents, the number of iterations, and the trust residual rate; S3323, using roulette method to select the starting position for the agent; S3324. According to the path selection mechanism, each agent is enabled to select a path, and the trust on the path is updated according to the result of the fitness function; S3325. Select a set of penalty parameters and kernel function width parameters with the highest fitness function value as the optimal penalty parameters and kernel function width parameters.

6. The method for energy-saving management of a smart campus based on the Internet of Things according to claim 5 is characterized in that: The trust residual rate is a value between zero and one. If the performance of the detection model in the current iteration is improved when the penalty parameter and the kernel function width parameter of the detection model are updated, the trust residual rate is increased; otherwise, the trust residual rate is reduced.

7. The method for energy-saving management of a smart campus based on the Internet of Things according to claim 5 is characterized in that: The method of selecting a starting position for an agent using a roulette wheel method comprises the following steps: S33231. construct a number of position nodes, form edges between the position nodes, and calculate importance scores for the number of position nodes; S33232. Calculate the selection probability of a plurality of position nodes; S33233, generate a random number between zero and one, and starting from the first position node, accumulate the selection probability until it is greater than or equal to the random number, and use the position node selected when it is greater than or equal to the random number as the starting position of the agent; When calculating the importance scores of the plurality of location nodes, the scores are scored using degree centrality and standardized; When calculating the selection probability of the plurality of position nodes, the selection probability formula is used for calculation; Among them, the selection probability formula is: ； In the formula, C i Represents a location node i The degree centrality score of D i Represents a location node i The betweenness centrality score of P i Represents a location node i The probability of selection; Represents the sum of the degree centrality scores and betweenness centrality scores of all location nodes.

8. The method for energy-saving management of a smart campus based on the Internet of Things according to claim 7 is characterized in that: The method of enabling each agent to select a path according to the path selection mechanism and updating the trust on the path according to the result of the fitness function includes the following steps: S33241. Starting from the starting position of the agent, select the next location node to be reached according to the greedy strategy, and calculate the fitness function value; S33242. When the agent cannot move forward or reaches the preset path length, it stops searching and records the current path and fitness function value; S33243, configuring an initial trust for each edge between position nodes, and calculating a trust increment according to the fitness function value of the path, and multiplying the trust increment by the trust residual rate and adding the trust increment to the initial trust to obtain a new trust; S33244. Update the trust of the edges on all paths and execute a preset number of iterations.

9. The method for energy-saving management of a smart campus based on the Internet of Things according to claim 8 is characterized in that: The method of obtaining the daily energy-saving power consumption target of each class and public place on campus includes the following steps: S51, calculating future electricity consumption based on historical electricity consumption data of each class and public place; S52, quantitatively analyzing the implementation effects of various energy-saving strategies to obtain the quantitative effects of the energy-saving strategies; S53, feeding back the quantified effect of the energy-saving strategy to the future electricity consumption to obtain the corrected future electricity consumption; S54. The corrected future electricity consumption is used as the energy-saving electricity consumption target on the corresponding date.

10. A system for energy-saving management of a smart campus based on the Internet of Things, used to implement the method for energy-saving management of a smart campus based on the Internet of Things according to any one of claims 1 to 9, characterized in that: The smart campus energy-saving management system based on the Internet of Things includes an electricity consumption data acquisition module, an ultrasonic data acquisition module, a model building module, an electricity consumption equipment adjustment module and an energy-saving feedback module; The power consumption data acquisition module is connected to the ultrasonic data acquisition module, the power consumption equipment adjustment module and the energy-saving feedback module, and the ultrasonic data acquisition module is connected to the model building module; The electricity consumption data collection module is used to deploy IoT devices in classrooms and public places on campus, and to collect electricity consumption data in real time through IoT devices, and to transmit the collected electricity consumption data to a cloud server for storage; The ultrasonic data acquisition module is used to perform ultrasonic detection on each campus building, obtain ultrasonic signals of the campus buildings, and transmit the ultrasonic signals to the cloud server through the Internet of Things technology; The model building module is used to build a detection model and deploy the detection model on a cloud server, process and analyze the ultrasonic signals of campus buildings through the detection model, identify defects in campus buildings and repair them; The power equipment adjustment module is used to adjust the working status of campus power equipment in real time according to the power consumption data of classes and public places, and formulate energy-saving strategies for classes and public places; The energy-saving feedback module is used to obtain the daily energy-saving power consumption target of each class and public place on campus, and obtain the power consumption of each class and public place on campus in real time. If the daily power consumption of a class or public place exceeds the daily energy-saving power consumption target, feedback will be given to the management personnel.

Images