A park energy monitoring method and system based on the Internet of Things

Abstract

This technology provides a campus energy monitoring method and system based on the Internet of Things, which relates to the field of energy monitoring technology of the Internet of Things technology, and includes: a path planning module, a VR / AR interface module, a visual image module, an emotional computing module, and a blockchain module. The monitoring method covers steps such as energy distribution path planning, VR / AR interactive monitoring, visual image-assisted analysis, emotional computing optimization distribution, and blockchain-based data security protection. It effectively solves the problems of distribution, monitoring, analysis, allocation, and data security in campus energy management, and improves the intelligent level of campus energy management and energy utilization efficiency.

Description

Technical Field

[0001] The present invention relates to the field of energy monitoring technology of Internet of Things technology, and more specifically, to a campus energy monitoring method and system based on Internet of Things. Background Art

[0002] With the development of the global economy and the acceleration of urbanization, industrial parks, as an important area of ​​concentrated economic activities, are growing in scale and complexity, and energy consumption is also increasing. In this context, effective monitoring and management of industrial park energy has become crucial.

[0003] Traditional campus energy management methods rely primarily on manual inspections and simple metering equipment, which have many limitations. Manual data collection is inefficient and difficult to guarantee accuracy, making it impossible to obtain real-time, continuous data. This results in a lack of timely and accurate data support for energy management decisions. Data transmission mostly uses wired methods, which are costly, inflexible, and susceptible to interference during transmission, resulting in low data security. Traditional data analysis methods are primarily based on experience and simple statistics, making it difficult to deeply explore the potential value of energy data, accurately predict and analyze energy consumption trends and equipment operating status, and identify potential energy waste and equipment failure hazards. In terms of energy distribution, the lack of scientific route planning leads to increased distribution costs and low efficiency. Furthermore, traditional systems have shortcomings in collecting and utilizing user feedback, making it impossible to optimize energy distribution strategies based on actual user experience, resulting in low user satisfaction. Furthermore, data security measures are weak, energy monitoring data is easily tampered with, and its credibility is low. Furthermore, data sharing and interaction are difficult, making it impossible to meet the needs of multi-department collaboration in campus energy management.

[0004] Existing technologies have problems such as low energy monitoring efficiency, poor data security, insufficient user interaction experience, and extensive energy allocation strategies. Summary of the Invention

[0005] In order to overcome the problems of low energy monitoring efficiency, poor data security, insufficient user interaction experience, and extensive energy allocation strategy in the existing technology, the present invention designs a campus energy monitoring method and system based on the Internet of Things to effectively solve the above technical problems.

[0006] In order to solve the above technical problems, the technical solutions of the present invention are as follows:

[0007] An Internet of Things-based campus energy monitoring system, including:

[0008] The path planning module builds an energy distribution network model, uses the ant colony algorithm to determine the optimal distribution path, and dynamically adjusts the distribution path selection probability;

[0009] VR / AR interface module, which creates a 3D model of energy facilities and integrates real-time energy facility monitoring data with the 3D model for display, enabling user-interactive energy monitoring and control;

[0010] Visual image module, monitors the operating status of energy facilities, analyzes energy efficiency, and warns of abnormal situations;

[0011] Affective computing module, which collects and analyzes user feedback and adjusts energy allocation strategies;

[0012] The blockchain module encrypts and stores energy facility monitoring data to ensure that the data cannot be tampered with.

[0013] Preferably, the path planning module further includes:

[0014] The network model building unit is used to build the energy distribution network model, including investigating the energy supply sources and consumption nodes in the park, and assigning attribute information to each edge;

[0015] Path optimization unit, used to determine the optimal energy distribution path through ant colony algorithm, including initializing algorithm parameters and calculating the total cost of the distribution path;

[0016] The pheromone updating unit is used to adjust the pheromone concentration according to the optimal delivery path information, simulate the pheromone volatilization process, and dynamically adjust the pheromone volatilization speed and increase amount.

[0017] Preferably, the VR / AR interface module further includes:

[0018] A 3D model building unit, which uses laser scanning technology and drone aerial photography to obtain the geometric shape and spatial location information of energy facilities and generate a 3D model;

[0019] The data fusion display unit is used to deploy Internet of Things sensor nodes to collect operating data of energy facilities and map real-time energy facility monitoring data onto the three-dimensional model.

[0020] Preferably, the visual image module further comprises:

[0021] Camera deployment unit, used to select camera sites and plan layouts based on energy facility distribution and monitoring priorities;

[0022] An image recognition unit, which uses target detection algorithms to identify key equipment and components in energy facilities and applies feature extraction algorithms to extract equipment operating parameters;

[0023] The deep learning early warning unit is used to build an abnormal situation early warning model suitable for park energy monitoring and deploy the trained early warning model into the energy monitoring system.

[0024] Preferably, the emotion calculation module further includes:

[0025] Feedback collection unit, used to set up feedback collection terminals and online questionnaire platforms, as well as establish a customer service hotline;

[0026] Sentiment analysis unit, used to pre-process and classify the sentiment of feedback information in the form of text, voice and images;

[0027] The strategy adjustment unit is used to establish a correlation model between user emotions and energy allocation strategies and formulate energy allocation adjustment plans.

[0028] Preferably, the blockchain module further includes:

[0029] An encryption storage unit, used to pre-process and hash the energy facility monitoring data collected by IoT sensors, and encrypt the energy facility monitoring data using an asymmetric encryption algorithm;

[0030] The consensus verification unit is used to ensure the consistency and non-tamperability of energy facility monitoring data through the consensus mechanism of the blockchain network.

[0031] A campus energy monitoring method based on the Internet of Things includes the following steps:

[0032] S1. Construct an energy distribution network model. By investigating the energy supply sources and consumption nodes within the park, a distribution path network is constructed based on their geographical distribution and infrastructure layout. The ant colony algorithm is applied to determine the optimal distribution path. The ant colony algorithm parameters are initialized, and the path selection is simulated by ant foraging behavior. The total cost of the distribution path is calculated, and the distribution path selection probability is dynamically adjusted. The pheromone concentration is adjusted according to the optimal distribution path. The pheromone volatilization process is simulated and the pheromone volatilization speed and increase are dynamically adjusted according to the distribution path network status.

[0033] S2. Create a three-dimensional model of the park's energy facilities, using laser scanning technology and drone aerial photography to obtain the geometric shape and spatial location information of the energy facilities. Integrate energy facility monitoring data with the three-dimensional model for display. Deploy IoT sensor nodes to collect operational data from the energy facilities. Implement interactive energy monitoring and control through data mapping algorithms, and provide real-time feedback through the user interface.

[0034] S3. Select camera locations and layouts based on the distribution of energy facilities, analyze energy efficiency, use target detection algorithms to identify key equipment and components, extract equipment operating parameters, issue warnings for abnormalities, collect image and video data of normal operation and abnormalities, build abnormality warning models, and conduct real-time analysis.

[0035] S4. Collect and analyze user feedback, set up a feedback collection terminal and online questionnaire platform, adjust the energy allocation strategy, establish a correlation model between user sentiment and energy allocation strategy, and adjust the energy allocation plan based on the feedback information;

[0036] S5. Preprocess and hash the energy facility monitoring data collected by IoT sensors, and encrypt the energy facility monitoring data using an asymmetric encryption algorithm to ensure that the energy facility monitoring data cannot be tampered with. After verification and consensus, the energy facility monitoring data block is added to the blockchain.

[0037] An electronic device, comprising:

[0038] a memory storing executable program code;

[0039] a processor coupled to the memory;

[0040] The processor calls the executable program code stored in the memory to execute the campus energy monitoring method based on the Internet of Things as described above.

[0041] A computer storage medium stores computer instructions, which, when called, are used to execute the above-mentioned campus energy monitoring method based on the Internet of Things.

[0042] Compared with the existing technology, the present invention has the following advantages: the present invention optimizes energy distribution routes using an ant colony algorithm through a path planning module, thereby improving the efficiency and accuracy of energy distribution. It can dynamically adjust the distribution route to respond to changes in energy demand within the park, thereby reducing energy waste and improving energy utilization efficiency. The introduction of the VR / AR interface module allows users to intuitively monitor the operating status of energy facilities through the creation of three-dimensional models and the integrated display of real-time data, achieving more intuitive and convenient energy management. This immersive interactive method enables non-professional users to easily understand and operate complex energy monitoring systems. The encrypted storage and consensus verification mechanism of the blockchain module ensures the immutability and consistency of energy monitoring data, and guarantees the integrity and reliability of the data. To address the problem of insufficient user interaction experience, the emotional computing module collects and analyzes user feedback and adjusts the energy allocation strategy, achieving personalized and refined energy management, which not only improves user satisfaction but also helps to improve the efficiency and rationality of energy use. The visual image module improves the safety and reliability of energy use by monitoring the operating status of energy facilities and warning of abnormal conditions. The real-time analysis capability of the deep learning warning unit enables the system to promptly detect and respond to potential energy problems, reduce the occurrence of energy accidents, and ensure the energy security of the park. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the implementation methods of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the implementation methods or the description of the prior art. Obviously, the drawings described below are merely exemplary. For ordinary technicians in this field, other implementation drawings can be derived based on the provided drawings without any creative work.

[0044] Figure 1 This is a structural diagram of a campus energy monitoring system based on the Internet of Things;

[0045] Figure 2 This is a step-by-step diagram of a campus energy monitoring method based on the Internet of Things. DETAILED DESCRIPTION

[0046] The accompanying drawings are for illustrative purposes only and are not to be construed as limiting this patent;

[0047] In order to better illustrate this embodiment, some parts in the drawings may be omitted, enlarged, or reduced, and do not represent the actual product size;

[0048] It is understandable to those skilled in the art that some well-known structures and descriptions thereof may be omitted in the drawings.

[0049] The technical solution of the present invention is further described below with reference to the accompanying drawings and embodiments.

[0050] Example 1

[0051] The IoT-based campus energy monitoring system of this embodiment is deployed in a modern industrial park covering an area of ​​approximately 10 square kilometers. The park houses multiple manufacturing companies, office buildings, data centers, and supporting public facilities. Energy consumption types are mainly electricity, natural gas, and heat. The energy supply sources include a 110kV substation, two gas boiler rooms, and several distributed solar photovoltaic power generation devices. The park has a complete network infrastructure, achieving full coverage of wired Ethernet and wireless networks (Wi-Fi and 5G signals), ensuring the data transmission needs of IoT devices.

[0052] A campus energy monitoring system based on the Internet of Things, such as Figure 1 Shown, including:

[0053] The path planning module builds an energy distribution network model, uses the ant colony algorithm to determine the optimal distribution path, and dynamically adjusts the distribution path selection probability;

[0054] VR / AR interface module, which creates a 3D model of energy facilities and integrates real-time energy facility monitoring data with the 3D model for display, enabling user-interactive energy monitoring and control;

[0055] Visual image module, monitors the operating status of energy facilities, analyzes energy efficiency, and warns of abnormal situations;

[0056] Affective computing module, which collects and analyzes user feedback and adjusts energy allocation strategies;

[0057] The blockchain module encrypts and stores energy facility monitoring data to ensure that the data cannot be tampered with.

[0058] The path planning module further includes:

[0059] The network model building unit is used to build the energy distribution network model, including investigating the energy supply sources and consumption nodes in the park, and assigning attribute information to each edge;

[0060] The park's energy management team works closely with the energy managers of each enterprise to conduct in-depth research on the park's energy supply sources and consumption nodes. For substations, their geographical location, transformer capacity, output voltage level, and power supply range are recorded in detail. For gas boiler rooms, information such as gas supply pressure, boiler thermal power, and heating area is accurately grasped. For each enterprise and public facility, comprehensive statistics on electricity, gas, and heat consumption at different time periods are collected to estimate peak and average energy consumption, and their location distribution within the park is clearly defined.

[0061] Combined with the park's geographic information system (GIS) data, supply sources such as substations and boiler rooms and various consumption points are regarded as network nodes, and roads and underground pipelines are used as connecting edges to construct an energy distribution network model. Attributes are assigned to the edges of the power distribution path. For example, the transmission loss coefficient is determined based on the resistance value calculated based on the cable material and length, and the rated transmission capacity is set according to the cable specifications. For gas pipeline edges, the transmission loss coefficient related to the friction coefficient is calculated considering the pipeline material and diameter, as well as attribute information such as the design flow rate upper limit.

[0062] Path optimization unit, used to determine the optimal energy distribution path through ant colony algorithm, including initializing algorithm parameters and calculating the total cost of the distribution path;

[0063] Initialize the ant colony algorithm parameters, set the number of ants to 50, the pheromone volatility coefficient to 0.3, the pheromone heuristic factor to 2, and the expected heuristic factor to 1. Based on the energy distribution network model provided by the network model construction unit, start the ant colony algorithm to simulate the ant foraging behavior to select a path. During the iteration process, calculate the total cost of each distribution path, taking into account factors such as path length (the actual geographical distance between nodes is calculated through the GIS system), transmission loss (calculated based on the transmission loss coefficient of the edge and the expected transmission energy), and construction and maintenance costs (estimated based on the historical construction and maintenance cost data of the park). For example, for the path to distribute electricity to a large manufacturing enterprise, a path with a shorter geographical distance but greater transmission loss due to aging of some cables may be initially selected. With iterative optimization, a more optimal path is gradually found after comprehensively considering loss and cost. After 100 iterations, the optimal energy distribution path is determined.

[0064] The pheromone updating unit is used to adjust the pheromone concentration according to the optimal delivery path information, simulate the pheromone volatilization process, and dynamically adjust the pheromone volatilization speed and increase amount.

[0065] After the path optimization unit determines the optimal delivery path, it increases the pheromone concentration on that path according to specific rules. For example, the increase in pheromone concentration is proportional to the degree of advantage of the total cost of the path (the lower the total cost, the greater the increase). At the same time, it simulates the pheromone volatilization process and, based on the set volatilization coefficient, attenuates the pheromone concentration on other paths by multiplying it by (1-volatilization coefficient) after each iteration.

[0066] Real-time monitoring of the distribution path network status, such as obtaining information such as changes in power line load and gas pipeline pressure fluctuations through sensors. When a sudden increase in energy demand in a certain area is found, such as an increase in electricity demand caused by an enterprise expanding production, the pheromone volatilization speed on the relevant paths in the area is appropriately increased to encourage ants to explore new paths faster. When the overall energy distribution system is in a stable low-load state, the pheromone volatilization speed is appropriately reduced to facilitate ants to conduct detailed searches near the better paths they have found. For example, if the business volume of a data center in the park suddenly increases, the pheromone update unit will speed up the volatilization speed of pheromones on the path leading to the substation in the area, guiding the ant colony to re-evaluate the path selection, and ultimately optimize the distribution path to ensure a stable and efficient energy supply for the data center.

[0067] The VR / AR interface module further includes:

[0068] A 3D model building unit, which uses laser scanning technology and drone aerial photography to obtain the geometric shape and spatial location information of energy facilities and generate a 3D model;

[0069] High-precision laser scanning equipment is used to conduct all-round scans of large energy facilities such as substations and gas boiler rooms, obtaining geometric shape and spatial position information accurate to the millimeter level, generating detailed point cloud data. For distributed solar photovoltaic power generation devices that are widely distributed and complex in structure, drones equipped with high-definition cameras are used to conduct multi-angle aerial photography. After obtaining image data, professional 3D reconstruction algorithms are used to convert it into 3D model data.

[0070] The three-dimensional model data is deeply associated and bound with the attribute information of energy facilities. In the three-dimensional model of the substation, key information such as the model, rated capacity, production date, and last maintenance time of each transformer is marked in detail; in the gas boiler room model, parameters such as the boiler's thermal efficiency, gas consumption rate, and safety valve set pressure are accurately recorded; for photovoltaic power generation equipment, data such as the photovoltaic panel's photoelectric conversion efficiency, inverter model and efficiency are noted, making it convenient for users to quickly query and understand the equipment details during the interaction process.

[0071] The data fusion display unit is used to deploy Internet of Things sensor nodes to collect operating data of energy facilities and map real-time energy facility monitoring data onto the three-dimensional model.

[0072] IoT sensor nodes are deployed at the park's energy supply sources, major energy consumption areas, and key equipment nodes. High-precision current and voltage sensors, as well as temperature sensors for monitoring transformer oil temperature and winding temperature, are installed in each switch cabinet of the substation. Gas flow sensors, steam pressure sensors, flue gas composition sensors, etc. are installed in the gas boiler room. Smart meters are installed in the power distribution rooms of each enterprise and the distribution boxes of public facilities. Heat meters are installed on heating pipes. Temperature and humidity sensors are installed in the air-conditioning system to collect operating data of energy facilities.

[0073] The data collected by the sensors is transmitted in real time to the data fusion display unit via Wi-Fi or 5G networks. An intelligent data mapping algorithm has been developed to accurately map the real-time data to the corresponding positions and objects in the 3D model based on the correspondence between the sensor data type and the equipment and areas in the 3D model. For example, in the 3D model of the substation, the load condition of the transformer is intuitively displayed through color changes, with green indicating normal load, yellow indicating mild overload, and red indicating severe overload. The curves of voltage and current changes over time are presented in the form of dynamic charts. In the gas boiler room model, parameters such as gas flow and steam pressure are displayed with real-time updated numerical values, and the working status of the burner is displayed with animation effects.

[0074] Different update cycles are set according to the frequency of changes and importance of sensor data. For data that changes rapidly and has a greater impact on energy management decisions, such as power load and gas flow, updates are performed every 5 seconds; for data that changes relatively slowly, such as temperature and pressure, updates are performed every 30 seconds to ensure the timeliness and accuracy of the data.

[0075] The visual image module further comprises:

[0076] Camera deployment unit, used to select camera sites and plan layouts based on energy facility distribution and monitoring priorities;

[0077] Camera site selection and layout planning are carried out based on the distribution of energy facilities in the park and monitoring priorities. Multiple high-definition surveillance cameras are installed around the substation at different angles and distances to ensure full coverage of key equipment such as transformers, switchgear, busbars, etc., and to monitor their operating status and potential safety hazards without blind spots, such as whether there are abnormal phenomena such as equipment smoking, discharge, oil spraying, and whether personnel are operating in violation of regulations.

[0078] Inside the gas boiler room, high-definition cameras with explosion-proof functions are installed at key locations such as the boiler body, burner, gas pipelines, and valves to monitor equipment operation in real time and detect gas leaks in a timely manner, such as by observing whether there are abnormal phenomena such as smoke and fog at the pipeline connections, and flame abnormalities such as abnormal flame color and unstable combustion. Cameras are installed at the external entrances and exits of the boiler room and surrounding areas to monitor the entry and exit of personnel and the transportation of materials to prevent unauthorized personnel from entering dangerous areas.

[0079] For distributed photovoltaic power stations, panoramic cameras and high-definition cameras with automatic zoom are installed in the photovoltaic panel array area to monitor the surface condition of the photovoltaic panels, whether there are obstructions such as dust, snow, bird droppings, whether the photovoltaic panels are damaged or deformed, the operating status of the inverter, whether there are any abnormalities such as overheating and alarm lights, and the surrounding environment, such as whether there are trees growing that affect light.

[0080] For interiors of substations and boiler rooms, use low-light, high-resolution cameras, such as 4K and above, with automatic zoom and focus functions and wide dynamic range. These cameras can adapt to dimly lit environments where equipment details need to be clearly observed, and can accurately capture image details in conditions with strong contrast between strong light and shadows. For outdoor photovoltaic power stations, use cameras with waterproof and dustproof functions, wide temperature range adaptability, and high reliability, which can operate stably in adverse weather conditions such as high temperatures, heavy rain, and windy sand.

[0081] Establish a camera network management system to achieve centralized management and remote control of all cameras. Through the network management system, administrators can remotely adjust camera parameters, such as resolution, and switch between different scenarios according to actual monitoring needs. For example, use a lower resolution to save network bandwidth during normal monitoring, and switch to high resolution for detailed observation when an abnormality is detected. Frame rate: increase the frame rate when an event is triggered to obtain clearer dynamic images. Exposure time: automatically adjust according to light changes to ensure image clarity. Develop flexible image acquisition plans to support scheduled acquisition, such as taking a group of images at regular intervals for daily inspection records, and event-triggered acquisition, such as automatically starting continuous image and video acquisition when the camera detects a moving object or a specific abnormality. Optimize data transmission management, adopt data caching and breakpoint resumption technology to ensure that image and video data are stably and efficiently transmitted to the image processing server under network fluctuations. Monitor camera status in real time. When a camera fails, such as disconnection, image blur, or device hardware failure, the system immediately issues an alarm to notify the administrator and records the fault information and time for timely maintenance.

[0082] An image recognition unit, which uses target detection algorithms to identify key equipment and components in energy facilities and applies feature extraction algorithms to extract equipment operating parameters;

[0083] Advanced target detection algorithms based on deep learning, such as the improved YOLOv5 algorithm, are used to process images and video data collected by cameras in real time to identify various key equipment and components in energy facilities. In substations, it can accurately identify transformers, circuit breakers, mutual inductors, lightning arresters, capacitors and other equipment, and precisely locate their positions in the image; in gas boiler rooms, it can identify boiler bodies, burners, fans, water pumps, various valves, instruments and other components; in photovoltaic power stations, it can identify photovoltaic panels, inverters, junction boxes, tracking brackets and other equipment.

[0084] For the identified equipment and components, feature extraction algorithms are used, such as combining the advantages of the scale-invariant feature transform (SIFT) and speeded up robust feature (SURF) algorithms to extract their key feature information. For example, the appearance shape and texture features of the transformer are used to determine whether it has deformation, oil leakage, etc.; the color, shape, and brightness distribution characteristics of the burner flame are used to analyze the combustion efficiency and stability; the surface color and texture uniformity characteristics of the photovoltaic panel are used to detect whether there are obstructions or damage. Combined with the equipment operation principle and relevant knowledge, the operating parameters of the equipment are calculated by analyzing the changes in feature information. For example, the transformer oil temperature rise rate is calculated by monitoring the changes in the surface temperature characteristics of the transformer oil tank, and the heat dissipation performance of the transformer is evaluated in combination with the load current data; the mixture ratio of gas and air is calculated based on the burner flame characteristics, and then the combustion efficiency is judged; the change trend of the photovoltaic panel's power generation efficiency is calculated by analyzing the changes in the reflected light characteristics of the photovoltaic panel surface, so as to promptly discover inefficient links and potential problems in the energy use process.

[0085] The deep learning early warning unit is used to build an abnormal situation early warning model suitable for park energy monitoring and deploy the trained early warning model into the energy monitoring system.

[0086] When collecting a large amount of image and video data of the normal operation of the park's energy facilities and various abnormal situations, such as transformer failure causing oil spraying and fire, gas leakage causing explosion, photovoltaic panels being blocked by foreign objects causing a significant drop in power generation efficiency, etc., professionals were organized to annotate the data in detail, clarifying the type of each abnormal situation, such as fire, leakage, blockage, etc., the severity, divided into mild, moderate, severe levels and the location of occurrence, accurate to the specific components or areas of the equipment, and constructed a training data set containing several images and several video data.

[0087] Based on deep learning frameworks such as TensorFlow or PyTorch, an abnormal situation warning model for campus energy monitoring is constructed. It adopts an optimized convolutional neural network (CNN) structure, which includes multiple convolutional layers (for extracting image features), pooling layers (for reducing data dimensions) and fully connected layers (for classification and prediction). Network parameters are carefully selected according to the characteristics of the abnormal situation and data features, such as the convolution kernel size (selecting the appropriate size according to the size of the equipment components and the feature scale, such as 3x3 or 5x5), step size (controlling the reduction ratio of the feature map), and activation function (using the ReLU function to improve model training efficiency).

[0088] The early warning model is fully trained using the training data set, and the weights and biases of the model are continuously adjusted through the back-propagation algorithm to enable the model to accurately identify different types of abnormal situations. During the training process, an adaptive learning rate adjustment strategy is adopted, such as dynamically reducing the learning rate according to the training error and regularization techniques such as L2 regularization to prevent overfitting. At the same time, data enhancement techniques such as random cropping, rotation, and flipping of images are used to expand the training data to improve the generalization ability and stability of the model.

[0089] The trained deep learning model is deployed in the energy monitoring system to perform real-time analysis on the images and video data collected by the camera. When the model detects an abnormality, it immediately issues an early warning signal. The early warning signal includes the type of abnormality, such as smoke from the transformer, gas leakage, photovoltaic panel fire, etc., the location of the occurrence, which is accurately located to the specific equipment or area through the camera position information and the coordinate positioning in the image, such as "smoke from the A-phase bushing of transformer No. 1 in the substation", and the severity, which is determined according to the model's assessment score of the abnormality, such as detailed information such as moderate severity. At the same time, the park management personnel are notified through various means, and a striking early warning pop-up window pops up on the large screen of the park monitoring center, displaying the abnormal image and detailed information, accompanied by voice A sound prompt is generated; a text message notification is sent to the manager's mobile phone, containing a summary of the abnormality and the degree of urgency; the sound and light alarm device is activated, and a strong sound and light alarm is issued at the scene of the abnormality, ensuring that the manager can obtain abnormal information in a timely manner and take corresponding measures. For example, when a gas leak is detected at a valve in the gas boiler room, the system immediately issues an early warning, and the real-time image, location information and severity rating of the leaking valve are displayed on the large screen of the monitoring center. The manager's mobile phone receives a text message notification that "Gas leak occurs at the valve at [specific location] in the gas boiler room, severity: moderate, please deal with it immediately", and the sound and light alarm device on the scene is activated, reminding nearby personnel to evacuate quickly and prompting maintenance personnel to bring professional equipment to the scene for emergency treatment.

[0090] The emotion calculation module further includes:

[0091] Feedback collection unit, used to set up feedback collection terminals and online questionnaire platforms, as well as establish a customer service hotline;

[0092] Sentiment analysis unit, used to pre-process and classify the sentiment of feedback information in the form of text, voice and images;

[0093] The strategy adjustment unit is used to establish a correlation model between user emotions and energy allocation strategies and formulate energy allocation adjustment plans.

[0094] A touch screen feedback device is set up in the lobby of the park's office building, where employees can enter their opinions on energy use, such as whether the air-conditioning temperature is comfortable. A QR code is also posted, which employees can scan to enter the online feedback page and submit text or photo feedback, such as photos of damaged lighting equipment. Energy use questionnaires are regularly sent to park enterprises via email, covering aspects such as energy supply stability and equipment ease of use. A customer service hotline is set up to record user feedback, such as power outage complaints, and classify the collected feedback into categories such as energy supply and equipment use.

[0095] For text feedback, after removing stop words, a simple bag-of-words model and naive Bayes classifier are used to perform sentiment classification, which is divided into positive, negative, and neutral. For voice feedback, it is first converted into text and then sentiment analysis is performed. For image feedback, such as photos of employees frowning, the emotional tendency is judged through a simple expression recognition algorithm. The results of multiple feedback analyses are combined. For example, if most employees report that the air conditioning in a certain area is too cold, the overall emotional tendency is determined to be negative.

[0096] A simple correlation model is established. For example, when users in a certain area give negative feedback on temperature comfort, the air conditioning temperature setting is adjusted appropriately. According to the actual energy supply situation of the park, such as the power load margin, an adjustment plan is formulated, such as increasing the air conditioning temperature setting in the area during low-load periods to save energy. The adjustment instructions are sent to the air conditioning equipment through the Internet of Things control system to achieve remote control and real-time monitoring of the effects, such as observing the temperature changes after adjustment through temperature sensor data.

[0097] The blockchain module further includes:

[0098] An encryption storage unit, used to pre-process and hash the energy facility monitoring data collected by IoT sensors, and encrypt the energy facility monitoring data using an asymmetric encryption algorithm;

[0099] The consensus verification unit is used to ensure the consistency and non-tamperability of energy facility monitoring data through the consensus mechanism of the blockchain network.

[0100] Energy data collected by sensors, such as electricity consumption, gas volume, and equipment operating status, undergoes simple preprocessing, such as removing obvious erroneous values. This preprocessed data is hashed, such as using the SHA-1 algorithm to generate a digest. Then, using an asymmetric encryption algorithm, such as RSA (with a public key and an authorized private key), the data and digest are encrypted. The encrypted data blocks are then uploaded to a simple blockchain network consisting of several servers within the park. Each data block contains the hash value of the previous data block, forming a chain structure.

[0101] A simple Byzantine fault-tolerant consensus mechanism is used. When a node receives a new data block, it broadcasts it to other nodes. Other nodes verify whether the hash value of the data block is correct and whether the data format is compliant. If the majority of nodes pass the verification, the data block is added to the blockchain. For example, after a certain power data block is uploaded, the nodes verify that its hash value is consistent with the calculation result and the data format is correct. After reaching a consensus, it is stored, ensuring the consistency and non-tamperability of the data. Authorized personnel can use the private key to decrypt and view the data for auditing and other work.

[0102] Example 2

[0103] A campus energy monitoring method based on the Internet of Things, such as Figure 2 As shown, the following steps are included:

[0104] S1. Construct an energy distribution network model. By investigating the energy supply sources and consumption nodes within the park, a distribution path network is constructed based on their geographical distribution and infrastructure layout. The ant colony algorithm is applied to determine the optimal distribution path. The ant colony algorithm parameters are initialized, and the path selection is simulated by ant foraging behavior. The total cost of the distribution path is calculated, and the distribution path selection probability is dynamically adjusted. The pheromone concentration is adjusted according to the optimal distribution path. The pheromone volatilization process is simulated and the pheromone volatilization speed and increase are dynamically adjusted according to the distribution path network status.

[0105] S2. Create a three-dimensional model of the park's energy facilities, using laser scanning technology and drone aerial photography to obtain the geometric shape and spatial location information of the energy facilities. Integrate energy facility monitoring data with the three-dimensional model for display. Deploy IoT sensor nodes to collect operational data from the energy facilities. Implement interactive energy monitoring and control through data mapping algorithms, and provide real-time feedback through the user interface.

[0106] S3. Select camera locations and layouts based on the distribution of energy facilities, analyze energy efficiency, use target detection algorithms to identify key equipment and components, extract equipment operating parameters, issue warnings for abnormalities, collect image and video data of normal operation and abnormalities, build abnormality warning models, and conduct real-time analysis.

[0107] S4. Collect and analyze user feedback, set up a feedback collection terminal and online questionnaire platform, adjust the energy allocation strategy, establish a correlation model between user sentiment and energy allocation strategy, and adjust the energy allocation plan based on the feedback information;

[0108] S5. Preprocess and hash the energy facility monitoring data collected by IoT sensors, and encrypt the energy facility monitoring data using an asymmetric encryption algorithm to ensure that the energy facility monitoring data cannot be tampered with. After verification and consensus, the energy facility monitoring data block is added to the blockchain.

[0109] An electronic device, comprising:

[0110] a memory storing executable program code;

[0111] a processor coupled to the memory;

[0112] The processor calls the executable program code stored in the memory to execute the campus energy monitoring method based on the Internet of Things as described above.

[0113] A computer storage medium stores computer instructions, which, when called, are used to execute the above-mentioned campus energy monitoring method based on the Internet of Things.

[0114] In the specific implementation, an energy distribution network model is constructed, the supply source and consumption nodes are determined, a distribution path network is constructed, the ant colony algorithm is used to determine the optimal distribution path, the path selection probability is dynamically adjusted, and the energy distribution efficiency is optimized.

[0115] Create a three-dimensional model of energy facilities, integrate real-time monitoring data, realize user interactive energy monitoring and control, deploy IoT sensor nodes to collect energy facility operation data, and display it on the three-dimensional model through data mapping algorithm.

[0116] Deploy cameras at key locations in energy facilities to collect image and video data, use target detection algorithms to identify key equipment and components, extract equipment operating parameters, and issue warnings for abnormal situations.

[0117] Collect user feedback, analyze emotional tendencies, establish a correlation model between user emotions and energy allocation strategies, adjust energy allocation plans based on feedback information, and optimize energy use.

[0118] The energy facility monitoring data collected by IoT sensors is preprocessed and hashed, the data is encrypted using an asymmetric encryption algorithm, and the encrypted data is uploaded to the blockchain network to ensure the data is tamper-proof and consistent.

[0119] The same or similar reference numerals correspond to the same or similar components;

[0120] The terms used in the drawings to describe positional relationships are for illustrative purposes only and should not be construed as limiting this patent;

[0121] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not limitations on the implementation methods of the present invention. For ordinary technicians in the field, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to enumerate all the implementation methods here. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the claims of the present invention.

Claims

1. A campus energy monitoring system based on the Internet of Things, characterized in that: include: The path planning module builds an energy distribution network model, uses the ant colony algorithm to determine the optimal distribution path, and dynamically adjusts the distribution path selection probability; VR / AR interface module, which creates a 3D model of energy facilities and integrates real-time energy facility monitoring data with the 3D model for display, enabling user-interactive energy monitoring and control; Visual image module, monitors the operating status of energy facilities, analyzes energy efficiency, and warns of abnormal situations; The visual image module further comprises: Camera deployment unit, used to select camera sites and plan layouts based on energy facility distribution and monitoring priorities; An image recognition unit, which uses target detection algorithms to identify key equipment and components in energy facilities and applies feature extraction algorithms to extract equipment operating parameters; A deep learning early warning unit is used to build an abnormal situation early warning model suitable for campus energy monitoring and deploy the trained early warning model into the energy monitoring system; Affective computing module, which collects and analyzes user feedback and adjusts energy allocation strategies; The blockchain module encrypts and stores energy facility monitoring data to ensure that the data cannot be tampered with.

2. The campus energy monitoring system based on the Internet of Things according to claim 1, characterized in that: The path planning module further includes: The network model building unit is used to build the energy distribution network model, including investigating the energy supply sources and consumption nodes in the park, and assigning attribute information to each edge; Path optimization unit, used to determine the optimal energy distribution path through ant colony algorithm, including initializing algorithm parameters and calculating the total cost of the distribution path; The pheromone updating unit is used to adjust the pheromone concentration according to the optimal delivery path information, simulate the pheromone volatilization process, and dynamically adjust the pheromone volatilization speed and increase amount.

3. The campus energy monitoring system based on the Internet of Things according to claim 1, characterized in that: The VR / AR interface module further includes: A 3D model building unit, which uses laser scanning technology and drone aerial photography to obtain the geometric shape and spatial location information of energy facilities and generate a 3D model; The data fusion display unit is used to deploy Internet of Things sensor nodes to collect operating data of energy facilities and map real-time energy facility monitoring data onto the three-dimensional model.

4. The campus energy monitoring system based on the Internet of Things according to claim 1, characterized in that: The emotion calculation module further includes: Feedback collection unit, used to set up feedback collection terminals and online questionnaire platforms, as well as establish a customer service hotline; Sentiment analysis unit, used for preprocessing and sentiment classification of feedback information in the form of text, voice and images; The strategy adjustment unit is used to establish a correlation model between user emotions and energy allocation strategies, and to formulate energy allocation adjustment plans.

5. The campus energy monitoring system based on the Internet of Things according to claim 1 is characterized in that: The blockchain module further includes: An encryption storage unit, used to pre-process and hash the energy facility monitoring data collected by IoT sensors, and encrypt the energy facility monitoring data using an asymmetric encryption algorithm; The consensus verification unit is used to ensure the consistency and non-tamperability of energy facility monitoring data through the consensus mechanism of the blockchain network.

6. A campus energy monitoring method based on the Internet of Things (IoT)-based campus energy monitoring system according to any one of claims 1 to 5, characterized in that: The following steps are involved: S1. Construct an energy distribution network model. By investigating the energy supply sources and consumption nodes within the park, a distribution path network is constructed based on their geographical distribution and infrastructure layout. The ant colony algorithm is applied to determine the optimal distribution path. The ant colony algorithm parameters are initialized, and the path selection is simulated by ant foraging behavior. The total cost of the distribution path is calculated, and the distribution path selection probability is dynamically adjusted. The pheromone concentration is adjusted according to the optimal distribution path. The pheromone volatilization process is simulated and the pheromone volatilization speed and increase are dynamically adjusted according to the distribution path network status. S2. Create a three-dimensional model of the park's energy facilities, using laser scanning technology and drone aerial photography to obtain the geometric shape and spatial location information of the energy facilities. Integrate energy facility monitoring data with the three-dimensional model for display. Deploy IoT sensor nodes to collect operational data from the energy facilities. Implement interactive energy monitoring and control through data mapping algorithms, and provide real-time feedback through the user interface. S3. Select camera locations and layouts based on the distribution of energy facilities, analyze energy efficiency, use target detection algorithms to identify key equipment and components, extract equipment operating parameters, issue warnings for abnormalities, collect image and video data of normal operation and abnormalities, build abnormality warning models, and conduct real-time analysis. S4. Collect and analyze user feedback, set up a feedback collection terminal and online questionnaire platform, adjust the energy allocation strategy, establish a correlation model between user sentiment and energy allocation strategy, and adjust the energy allocation plan based on the feedback information; S5. Preprocess and hash the energy facility monitoring data collected by IoT sensors, and encrypt the energy facility monitoring data using an asymmetric encryption algorithm to ensure that the energy facility monitoring data cannot be tampered with. After verification and consensus, the energy facility monitoring data block is added to the blockchain.

7. An electronic device, characterized in that: The electronic device comprises: a memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the campus energy monitoring method based on the Internet of Things as described in claim 6.

8. A computer storage medium, characterized in that The computer storage medium stores computer instructions, which, when called, are used to execute the campus energy monitoring method based on the Internet of Things as described in claim 6.

Images