Smart park energy consumption monitoring system based on wireless network

Abstract

The invention discloses a smart park energy consumption monitoring system based on a wireless network, which relates to the technical field of energy consumption monitoring and comprises an energy consumption acquisition module, a wireless data transmission module, a data processing module and an energy consumption display module. The energy consumption acquisition module is used for collecting water, electricity and gas energy consumption data of different users in the smart park; according to the intelligent park energy consumption monitoring system, the comprehensive intelligent park energy consumption monitoring system is innovatively constructed by integrating the energy consumption acquisition module, the wireless data transmission module, the data processing module, the energy consumption display module and the like, the advanced wireless communication technology is utilized, and the problems that a traditional wired monitoring system is complex in wiring and high in cost are effectively solved; meanwhile, the flexibility and expansibility of the system are improved, the real-time performance and accuracy of energy consumption monitoring are greatly improved through real-time data collection and wireless transmission in combination with an efficient data processing algorithm, and powerful technical support is provided for energy management of the smart park.

Description

Technical Field

[0001] The present invention relates to the technical field of energy consumption monitoring, and in particular to a smart park energy consumption monitoring system based on a wireless network. Background Art

[0002] With the acceleration of urbanization, smart parks, as an important part of urban development, are increasingly concerned about energy consumption. There are many buildings in the park, and the types of energy consumption are diverse, including electricity, water resources, and gas. Traditional energy consumption monitoring systems mostly use wired connections, which have problems such as complex wiring, high costs, and difficult system upgrades. In addition, traditional systems are insufficient in real-time, accuracy, and intelligence, and it is difficult to meet the needs of modern smart parks for energy consumption monitoring. Therefore, it is of great practical significance to develop a new type of energy consumption monitoring system to meet the development needs of smart parks.

[0003] Existing energy consumption monitoring technologies mostly rely on a single data collection and processing method, lacking efficient data analysis and anomaly detection capabilities. In terms of data collection, the communication protocols between different devices and systems are inconsistent, making data integration difficult. In terms of data processing, existing systems often lack the ability to process big data, making it difficult to achieve in-depth analysis and pattern recognition of energy consumption data. In addition, existing systems mostly use simple threshold judgments for anomaly detection, lack intelligent analysis and response mechanisms, and are unable to effectively identify and handle energy consumption anomalies. These problems limit the performance and application scope of energy consumption monitoring systems.

[0004] In order to solve the above defects, a technical solution is now provided. Summary of the invention

[0005] The purpose of the present invention is to solve the problem that the real-time collection, efficient processing, intelligent analysis and safe display of energy consumption data of existing smart parks need to be improved, and to propose a smart park energy consumption monitoring system based on a wireless network.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] The smart park energy consumption monitoring system based on wireless network includes:

[0008] Energy consumption collection module, used to collect water, electricity and gas energy consumption data of different users in the smart park;

[0009] A wireless data transmission module, used for transmitting energy consumption data to a data processing module via a wireless network;

[0010] The data processing module is used to receive, store and analyze energy consumption data, detect abnormal energy consumption and analyze the causes. The specific process is as follows:

[0011] Receive wirelessly transmitted energy consumption data in real time, verify its integrity and accuracy, exclude invalid or erroneous records, select a database to store data, perform cleaning, including removing noise and filling missing values, and unify data formats;

[0012] Integrate data from different sources into a unified view and use statistical and machine learning methods to analyze energy consumption patterns and trends;

[0013] Identify and analyze the causes of abnormal energy consumption through anomaly detection algorithms, including threshold-based, statistical or AI-based methods;

[0014] Update the model regularly and adjust the analysis method based on feedback to ensure the accuracy and adaptability of the model;

[0015] Design visualization tools to display analysis results, automatically generate reports containing energy consumption statistics and abnormal events, provide customized data analysis services, realize real-time monitoring, continuously analyze energy consumption data and detect anomalies;

[0016] Apply time series and forecasting model technology to predict energy consumption trends and provide optimization suggestions, integrate data processing modules into the energy consumption display platform to ensure data consistency, evaluate and optimize computing and storage performance, collect user feedback, build a knowledge base, accumulate experience, and support continuous improvement;

[0017] The energy consumption display module is used to display energy consumption data to users and provide prompts when an anomaly is detected.

[0018] Furthermore, the process of using statistical and machine learning methods to analyze energy consumption patterns and trends in the data processing module is as follows:

[0019] First, extract features from the raw data, perform descriptive statistical analysis, analyze the basic characteristics of the data, and use charts and graphs to visualize data distribution, trends, and relationships;

[0020] Determine which features are important enough to predict energy consumption patterns and trends, and divide the data into training, validation, and test sets to evaluate the performance of the model;

[0021] Select statistical methods or machine learning models based on data characteristics and business needs;

[0022] Use the training set data to train the model, adjust the model parameters to obtain the best performance, and use the validation set to evaluate the accuracy and generalization ability of the model;

[0023] Improve model performance by adjusting model parameters, using feature selection or ensemble learning methods, and implementing cross-validation to ensure model stability and reliability;

[0024] Identify and handle outliers that affect model performance, apply time series analysis to identify energy consumption trends and periodic patterns, use cluster analysis to identify energy consumption patterns, and group energy consumption behaviors that meet a certain standard of similarity;

[0025] Build predictive models to forecast future energy consumption data, interpret model results, determine their potential impact on business decisions, and deploy trained models into production environments for real-time or batch energy consumption data analysis;

[0026] Monitor how your model performs in real-world applications.

[0027] Furthermore, the specific operation steps of the data processing module for monitoring the performance of the model in actual application are as follows:

[0028] A comprehensive analysis is performed by collecting the performance parameters of the model, including:

[0029] Accuracy, precision, recall, F1 score and mean square error;

[0030] Select the importance of each evaluation indicator, assign a weight to each indicator, and then normalize the obtained accuracy, precision, recall, F1 score and mean square error and enter them into the following formula: ZPZ = κ1*Accuracy+κ2*Precision+κ3*Recall+κ4*F1 Score+κ5*MSE to obtain the comprehensive value ZPZ, where Accuracy, Precision, Recall, F1 Score and MSE are accuracy, precision, recall, F1 score and mean square error respectively, and κ1, κ2, κ3, κ4, κ5 are the preset weight coefficients of accuracy, precision, recall, F1 score and mean square error respectively;

[0031] The obtained synergistic value is used as a standard to measure the performance of the model, and is compared with several preset synergistic value intervals. Different effect levels are set corresponding to the several synergistic value intervals, so as to determine the effect level of the current model performance;

[0032] At the same time, the obtained synergistic value ZPZ is compared with the preset synergistic threshold. When the synergistic value does not reach the preset synergistic threshold standard, it is judged that the effect does not meet the standard, and targeted model optimization is performed for different performance parameter data.

[0033] Furthermore, the specific operation steps of the data processing module for optimizing the model in a targeted manner according to different performance parameter data are as follows:

[0034] When the accuracy rate does not meet the standard, resample or collect more data, including misclassified samples, and use different feature selection methods to find features that represent the characteristics of the data;

[0035] When the precision and recall rates do not meet the standards, the classification threshold is adjusted to balance the two, and cost-sensitive learning is used to set different weights for the costs of misclassification.

[0036] When the F1 score does not meet the standard, optimize the model parameters or use a different model;

[0037] When the mean square error does not meet the standard, a new model with higher complexity than the existing model is selected or a nonlinear combination of features is added.

[0038] Furthermore, the specific operation steps of the data processing module to identify and analyze the causes of abnormal energy consumption through an abnormality detection algorithm are as follows:

[0039] Define the definition, type and characteristics of anomalies, analyze historical data to identify normal and abnormal energy consumption patterns, and select anomaly detection methods based on data characteristics: based on thresholds, statistical models or machine learning algorithms; use statistical metrics such as mean, median, and percentile to establish energy consumption baselines, determine thresholds to distinguish normal and abnormal energy consumption, and use statistical methods such as Z-scores and box plots for anomaly detection; select the corresponding algorithm and train the model;

[0040] Define scoring mechanisms for different detection methods, standardize scoring, assign weights based on the reliability of the methods, calculate comprehensive scores, set thresholds to judge anomalies, integrate the detection results of different methods, and determine the final anomaly detection results through a voting mechanism;

[0041] Sort anomalies based on comprehensive scores, manually review anomalies, compare detection results with actual conditions, collect feedback, and dynamically adjust thresholds and weights;

[0042] Interpret comprehensive test results, identify anomalous data points and their causes, and generate reports.

[0043] Furthermore, the energy consumption display module displays energy consumption data to the user and gives a prompt when an abnormality is detected. The specific operation steps are as follows:

[0044] First, an authentication mechanism is used to ensure that each user can only see his or her own energy consumption data to avoid data leakage;

[0045] Identify user needs for data presentation, including data types and interface preferences, design the user interface, determine the layout, colors, and fonts, and select data visualization tools, including D3.js, Echarts, or Highcharts;

[0046] Realize the display of charts and dashboards of real-time energy consumption data, provide functions that allow users to query and analyze historical energy consumption data, and allow users to customize data views according to specific needs;

[0047] When abnormal energy consumption is detected, the user is immediately prompted through the interface, an alarm mechanism is designed, and the user is notified via email, SMS or App push;

[0048] Providing tools to enable users to compare energy consumption in different time periods or user groups, displaying energy-saving suggestions based on data analysis, and assisting users in optimizing energy consumption;

[0049] Implement user login and permission control to ensure data security, ensure that the display module is compatible with PCs, tablets and smartphones, and develop interactive functions for data screening, exporting and printing;

[0050] Provide feedback channels, collect user opinions and suggestions, optimize loading speed and response time, and improve user experience.

[0051] Furthermore, the energy consumption display module ensures that each user can only see his or her own energy consumption data information through an authentication mechanism. The specific operation steps are as follows:

[0052] Implement username and password, biometric or multi-factor authentication mechanisms to configure access rights based on user roles and identities to ensure data access restrictions;

[0053] Encrypt user data, including during storage and transmission, and generate and verify a unique identifier for each user session to ensure session security;

[0054] Record detailed user operation logs, including time, IP address, and operation details, and perform data isolation at the database level to ensure that users can only access their own data;

[0055] Follow the principle of least privilege, grant users only the permissions to complete corresponding tasks, customize the interface according to user permissions, only display authorized data and functions, and ensure that all data access APIs perform permission checks;

[0056] Monitor and alert on unusual access patterns, including unusual frequencies of failed logins or unusual data access;

[0057] Develop and maintain a data breach emergency plan to ensure rapid response.

[0058] Furthermore, the specific operation steps of the energy consumption collection module to collect water, electricity and gas energy consumption data of different users in the smart park are as follows:

[0059] Collect smart electricity meters, water meters, and gas meters from all buildings in the park, record the model, manufacturer, and communication interface, and confirm whether the communication protocol of the energy consumption monitoring equipment is compatible with the wireless network standard;

[0060] Select or develop adapters or gateways to convert communication protocols of different devices, design unified data collection logic, and ensure data format consistency;

[0061] Install an independent energy consumption monitoring device for each user and assign a unique identification code to link all energy consumption monitoring device identification codes of the same user;

[0062] Configure the data acquisition unit to communicate with the energy consumption monitoring equipment to achieve real-time data acquisition and preliminary processing, and configure the Wi-Fi or cellular network module to ensure compatibility with the data acquisition module;

[0063] Implement TLS / SSL data encryption technology to ensure data transmission security, test the data acquisition module in the actual environment to ensure data accuracy and real-time performance.

[0064] Furthermore, the specific operation steps of the wireless data transmission module transmitting the energy consumption data to the data processing module via the wireless network are as follows:

[0065] Clarify data transmission requirements, including data volume, frequency, and security, and select corresponding wireless communication technologies based on the scale and layout of the park;

[0066] Select communication protocols that match the Internet of Things, configure gateways for non-standard protocol devices, and design data encryption and authentication mechanisms to ensure transmission security;

[0067] Develop wireless data transmission modules to ensure seamless connection with data acquisition and processing modules, configure the IP address of energy consumption collection equipment or use DHCP to automatically allocate;

[0068] Test wireless network coverage, stability and speed to ensure that requirements are met, determine the data transmission format, and compress the data;

[0069] According to the network and data characteristics, optimize the data packet size and transmission interval, use error detection and automatic retransmission mechanisms to ensure data integrity, test the transmission speed, stability and security in a simulated environment, and perform regular maintenance and upgrades to adapt to new security and technical requirements.

[0070] Compared with the prior art, the present invention has the following beneficial effects:

[0071] (1) The present invention innovatively constructs a comprehensive smart park energy consumption monitoring system by integrating modules such as energy consumption collection, wireless data transmission, data processing and energy consumption display. It uses advanced wireless communication technology to effectively solve the problems of complex wiring and high cost of traditional wired monitoring systems, while improving the flexibility and scalability of the system. Through real-time data collection and wireless transmission, combined with efficient data processing algorithms, the present invention greatly improves the real-time and accuracy of energy consumption monitoring, providing strong technical support for energy management in smart parks.

[0072] (2) In the present invention, the data processing module uses statistical analysis and machine learning technology to conduct in-depth analysis of energy consumption data, identify energy consumption patterns and trends, and timely discover and analyze the causes of abnormal energy consumption through anomaly detection algorithms. The system can not only provide customized data analysis services, realize real-time monitoring and anomaly detection, but also apply time series and prediction model technology to predict energy consumption trends and provide users with energy consumption optimization and energy-saving suggestions. This intelligent analysis and optimization helps to improve energy utilization efficiency, reduce energy waste, and promote the sustainable development of the park;

[0073] (3) The energy consumption display module of the present invention provides users with an intuitive and easy-to-use energy consumption data display platform. The authentication mechanism ensures data security. Each user can only access his or her own energy consumption data, effectively avoiding the risk of data leakage. The user interface is customized according to user needs, supports multi-terminal access, and provides rich interactive functions such as data screening, exporting, and printing. The system also collects user feedback and continuously optimizes the user experience. Through these designs, the present invention not only improves the user's interactive experience, but also strengthens the security and privacy protection of data, ensuring the reliability and practicality of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;

[0075] Figure 1 This is the overall system block diagram of the present invention. DETAILED DESCRIPTION

[0076] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0077] It should be understood that the terms "include" and "comprising" used in the specification and claims of the present disclosure indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0078] It should also be understood that the terms used in this disclosure are only for the purpose of describing specific embodiments and are not intended to limit the disclosure. As used in this disclosure and claims, the singular forms of "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise. It should also be further understood that the term "and / or" used in this disclosure and claims refers to any combination of one or more of the associated listed items and all possible combinations, including these combinations.

[0079] like Figure 1 As shown, the energy consumption monitoring system of a smart park based on a wireless network includes an energy consumption collection module, a wireless data transmission module, a data processing module and an energy consumption display module;

[0080] The energy consumption collection module is used to collect water, electricity and gas energy consumption data of different users in the smart park;

[0081] First, investigate the energy consumption monitoring equipment of all buildings in the park, including smart electricity meters, water meters and gas meters, and record the model, manufacturer, and communication interface (such as Modbus, DNP3.0, MQTT, etc.) of the energy consumption monitoring equipment; analyze whether the communication protocol of the energy consumption monitoring equipment supports the existing wireless network standard, and determine whether an adapter or gateway is needed to convert the communication protocol;

[0082] Select or develop adapters / gateways to connect devices with different communication protocols, design data collection logic, ensure unified data format, and ensure unified management and data collection of all devices through integrated solutions; install independent smart electricity meters, water meters and gas meters for each individual user identified in the park, and ensure that all energy consumption monitoring devices of each individual user have unique identification codes, and associate the identification codes of different energy consumption monitoring devices of the same user;

[0083] Configure the data acquisition unit to communicate with each energy consumption monitoring device and integrate data processing logic to realize real-time data collection and preliminary processing; configure wireless network infrastructure, such as Wi-Fi access points or cellular network modules; ensure the compatibility of the data acquisition module with the wireless network; ensure that energy consumption data can be transmitted through the wireless network; implement data encryption technology, such as TLS / SSL, to ensure the security of the wireless network, prevent unauthorized access, and ensure the security of data during transmission; test the functions of the data acquisition module in an actual environment to verify the accuracy and real-time nature of the data.

[0084] The wireless data transmission module is used to transmit the energy consumption data to the data processing module via a wireless network;

[0085] Determine the needs for data transmission, including data volume, frequency, security requirements, etc., and select appropriate wireless communication technologies such as Wi-Fi, cellular networks (4G / 5G), LoRa, ZigBee, etc. according to the scale and layout of the smart park; determine the communication protocols used for data transmission, such as MQTT, CoAP, etc. These protocols are suitable for the IoT environment. If the energy consumption collection device uses a proprietary protocol, it is necessary to configure or develop a gateway device to convert the data into a format that can be used by the wireless network;

[0086] Design encryption and authentication mechanisms for data transmission to ensure data security during transmission. Develop or integrate wireless data transmission modules to ensure that they can be seamlessly connected to energy consumption collection modules and data processing modules. Configure IP addresses for each energy consumption collection device or use Dynamic Host Configuration Protocol (DHCP) to automatically assign addresses. Test the coverage, stability, and transmission rate of wireless networks in actual environments to ensure that data transmission requirements are met.

[0087] Determine the format of data transmission, such as JSON, XML, etc., to facilitate parsing by the data processing module, and compress the transmitted data to reduce transmission time and network bandwidth consumption; optimize the efficiency of data transmission according to network conditions and data characteristics, such as adjusting the packet size, transmission interval, etc., to implement error detection and automatic retransmission mechanisms to ensure data integrity and accuracy, and test the performance of the wireless data transmission module in a simulated environment, including transmission speed, stability and security; regularly maintain and upgrade the wireless data transmission module to adapt to new security requirements and technical standards.

[0088] The data processing module is used to receive, store and analyze energy consumption data, detect abnormal energy consumption and analyze the causes;

[0089] Design a data receiving interface to receive energy consumption data from the wireless data transmission module in real time, verify the integrity and accuracy of the data, and remove invalid or erroneous data records; store the received data in a database, select a suitable database system (such as SQL or NoSQL) to meet data storage requirements, and clean the stored data, including removing noise, filling missing values, and unifying the format. Filling missing values ​​is done by using historical averages, medians, modes, or interpolation methods (linear interpolation, polynomial interpolation); integrate energy consumption data from different sources and types to form a unified data view, and apply statistical analysis, machine learning, and other methods to conduct in-depth analysis of energy consumption data to identify energy consumption patterns and trends. The specific process is as follows:

[0090] First, extract features that are helpful for analysis from the original data, perform descriptive statistical analysis, analyze the basic characteristics of the data, and use charts and graphs to visualize data distribution, trends, and relationships; determine which features are most important for predicting energy consumption patterns and trends, and divide the data into training sets, validation sets, and test sets to evaluate the performance of the model; select appropriate statistical methods or machine learning models such as linear regression, decision trees, random forests, support vector machines, neural networks, etc. based on data characteristics and business needs; use training set data to train the model, adjust model parameters to obtain optimal performance, and use validation sets to evaluate the accuracy and generalization ability of the model;

[0091] Improve model performance by adjusting model parameters, using feature selection or ensemble learning methods, and implement cross-validation to ensure model stability and reliability; identify and handle outliers that may affect model performance, apply time series analysis to identify energy consumption trends and periodic patterns, use cluster analysis to identify energy consumption patterns, and group similar energy consumption behaviors; build predictive models to predict future energy consumption data, interpret model results, determine their potential impact on business decisions, and deploy trained models to production environments for real-time or batch energy consumption data analysis;

[0092] Monitor the performance of the model in actual applications by collecting the performance parameters of the model for comprehensive analysis, including:

[0093] Accuracy: Precision: Recall: F1 Score: Mean Squared Error (MSE): Where I: the number of samples or observations; L: represents the sample index in the data set, from 1 to I; Y i : The actual value of the i-th observation; The predicted value of the i-th observation is used in regression problems to measure the difference between the model prediction and the actual value;

[0094] Select the importance of each evaluation indicator, assign a weight to each indicator, and then normalize the obtained accuracy, precision, recall, F1 score and mean square error and enter them into the following formula: ZPZ = κ1*Accuracy+κ2*Precision+κ3*Recall+κ4*F1 Score+κ5*MSE to obtain the comprehensive value ZPZ, where κ1, κ2, κ3, κ4, κ5 are the preset weight coefficients of accuracy, precision, recall, F1 score and mean square error respectively; use the obtained comprehensive value ZPZ as a standard to measure the performance of the model, and compare it with several preset comprehensive value intervals. Several comprehensive value intervals correspond to different effect levels, so as to determine the effect level of the current model performance;

[0095] At the same time, the obtained synergistic value ZPZ is compared with the preset synergistic threshold. When the synergistic value ZPZ does not reach the preset synergistic threshold standard, it is judged that the effect does not meet the standard, and targeted model optimization is performed for different performance parameter data, specifically:

[0096] When the accuracy rate does not meet the standard, consider resampling or collecting more data, especially those samples that are misclassified, and try different feature selection methods to find features that better represent the characteristics of the data; when the precision and recall rate do not meet the standard, balance the two by adjusting the classification threshold, adopt cost-sensitive learning, and set different weights for the cost of misclassification; when the F1 score does not meet the standard, optimize the model parameters or try different models; when the mean square error does not meet the standard, choose a more complex model or increase the nonlinear combination of features.

[0097] Regularly maintain and update, and continuously adjust and improve analysis methods based on model output and business feedback;

[0098] Develop anomaly detection algorithms, such as threshold-based, statistical model-based, or artificial intelligence-based methods, to identify anomalies in energy consumption data and analyze the causes of detected anomalies, which may include equipment failure, abnormal usage, or other external factors. The specific process is as follows:

[0099] Clarify what constitutes an "abnormality", including the definition, type and characteristics of anomalies, analyze historical data, and understand normal energy consumption patterns and potential abnormal patterns; select appropriate anomaly detection methods based on data characteristics and business needs, such as threshold-based, statistical models, machine learning or deep learning, determine the data characteristics of anomaly detection, and establish a baseline for normal energy consumption, which can be a statistical measure such as mean, median, percentile, etc.;

[0100] When using threshold-based methods, determine the threshold to distinguish between normal and abnormal energy consumption; when using statistical methods, include Z-scores, box plot analysis, or other statistical tests; when using machine learning, select an appropriate algorithm (such as Isolation Forest, One-Class SVM, Autoencoders, etc.) and use historical data to train the model;

[0101] A scoring mechanism is defined for the above three anomaly detection methods to quantify the severity of the anomaly and standardize the scores of different methods to the same range for easy comparison and integration; different weights are assigned to each method according to its reliability and applicability, and the comprehensive score of each method is calculated based on the assigned weights; a threshold for the comprehensive score is set, and energy consumption data exceeding this threshold is considered abnormal;

[0102] Integrate the analysis results based on thresholds, statistical methods, and machine learning to form a unified anomaly detection result set; implement a voting mechanism, where each method votes on whether a data point is an anomaly, and the final result is determined based on the majority principle. Detected anomalies are sorted based on the comprehensive score, with anomalies with higher scores being processed first. For anomalies with a comprehensive score close to the threshold, their authenticity is determined through manual review;

[0103] Compare the comprehensive detection results with the actual situation, collect feedback to optimize the accuracy and weight distribution of each method, and dynamically adjust the thresholds, weights and comprehensive strategies based on feedback and business development; interpret the comprehensive results, clearly indicate which data points are detected as anomalies and their reasons, generate a report containing the comprehensive anomaly detection results, and provide it to relevant personnel or systems for further analysis or decision-making.

[0104] Design data visualization tools to present analysis results in the form of charts, dashboards, etc. for easy understanding and interpretation, and automatically generate energy consumption reports, including energy consumption statistics, abnormal events, analysis conclusions, etc.; provide customized data analysis and reporting services according to user needs, realize real-time monitoring functions, and conduct continuous analysis and anomaly detection of energy consumption data streams; apply time series analysis, forecasting models and other technologies to predict future energy consumption trends, and provide energy consumption optimization and energy-saving suggestions based on analysis results;

[0105] Integrate the data processing module with other energy consumption display modules to ensure the consistency of data flow and information flow, and regularly evaluate and optimize the performance of the data processing module, including computing efficiency, storage optimization, etc.; collect user feedback on data processing results, continuously adjust and improve analysis methods, build a knowledge base, accumulate historical data and analysis experience, and provide support for continuous improvement.

[0106] The energy consumption display module is used to display energy consumption data to users and provide prompts when an abnormality is detected;

[0107] First, an authentication mechanism is used to ensure that each user can only see his or her own energy consumption data to avoid data leakage. The specific process is as follows:

[0108] Utilize preset user authentication mechanisms, such as username and password, biometrics or multi-factor authentication, to set different access rights according to the user's role and identity, ensuring that users can only access authorized data; encrypt the storage and transmission of users' energy consumption data to ensure that even if the data is intercepted, it cannot be read by unauthorized persons; generate a unique session identifier for each user session and verify it on the server side to ensure the security of the session; record all user operations and access logs, including access time, IP address and operation content, for security audits, and implement data isolation at the database level to ensure that each user can only query and operate their own data records;

[0109] Follow the principle of least privilege and grant users only the access rights necessary to complete the required tasks. Customize the user interface based on user permissions and only display data and functions that users are authorized to view. Ensure that all data access APIs are subject to strict permission verification to prevent unauthorized access. Monitor abnormal access patterns, such as frequent failed login attempts or unusual data access behavior, and develop a data breach emergency plan to respond quickly when a data breach occurs.

[0110] Then determine user needs, including the type of data to be displayed, user interface preferences, etc., and design an intuitive and easy-to-use user interface, including layout, color scheme, fonts, etc.; select appropriate data visualization tools and libraries, such as D3.js, Echarts, Highcharts, etc., to achieve real-time energy consumption data display, and use charts, dashboards and other elements to dynamically display energy consumption data;

[0111] Provide historical energy consumption data query function, allowing users to view energy consumption records in the past time period, and allow users to customize their own data views according to their needs, such as choosing to focus on specific energy consumption types or time periods. When the data processing module detects abnormal energy consumption, the energy consumption display module should immediately prompt the user; design an alarm and notification mechanism to notify users through email, SMS or App push, and provide data comparison tools so that users can compare energy consumption in different time periods or different user groups;

[0112] Display energy-saving suggestions based on data analysis to help users optimize energy consumption, implement user login and permission control, and ensure that users can only access their own energy consumption data; ensure that the energy consumption display module can adapt to a variety of terminals, including PCs, tablets and smart phones, and develop interactive functions such as data filtering, exporting, and printing; provide user feedback channels, collect user opinions and suggestions on the energy consumption display module, and test the energy consumption display module in different scenarios and user groups to ensure its stability and usability;

[0113] Optimize the loading speed and response time of the energy consumption display module, improve user experience, and ensure that data security and privacy protection standards are followed during the display of energy consumption data; provide help documents and user guides to help users understand how to use the energy consumption display module, and train users to ensure that they can fully utilize the functions of the energy consumption display module.

[0114] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. The energy consumption monitoring system of smart park based on wireless network is characterized by: include: Energy consumption collection module, used to collect water, electricity and gas energy consumption data of different users in the smart park; A wireless data transmission module, used for transmitting energy consumption data to a data processing module via a wireless network; The data processing module is used to receive, store and analyze energy consumption data, detect abnormal energy consumption and analyze the causes. The specific process is as follows: Receive wirelessly transmitted energy consumption data in real time, verify its integrity and accuracy, exclude invalid or erroneous records, select a database to store data, perform cleaning, including removing noise and filling missing values, and unify data formats; Integrate data from different sources into a unified view and use statistical and machine learning methods to analyze energy consumption patterns and trends; Identify and analyze the causes of abnormal energy consumption through anomaly detection algorithms, including threshold-based, statistical or AI-based methods; Update the model regularly and adjust the analysis method based on feedback to ensure the accuracy and adaptability of the model; Design visualization tools to display analysis results, automatically generate reports containing energy consumption statistics and abnormal events, provide customized data analysis services, realize real-time monitoring, continuously analyze energy consumption data and detect anomalies; Apply time series and forecasting model technology to predict energy consumption trends and provide optimization suggestions, integrate data processing modules into the energy consumption display platform to ensure data consistency, evaluate and optimize computing and storage performance, collect user feedback, build a knowledge base, accumulate experience, and support continuous improvement; The energy consumption display module is used to display energy consumption data to users and provide prompts when an anomaly is detected.

2. The wireless network-based smart park energy consumption monitoring system according to claim 1 is characterized in that: The process of using statistical and machine learning methods to analyze energy consumption patterns and trends in the data processing module is as follows: First, extract features from the raw data, perform descriptive statistical analysis, analyze the basic characteristics of the data, and use charts and graphs to visualize data distribution, trends, and relationships; Determine which features are important enough to predict energy consumption patterns and trends, and divide the data into training, validation, and test sets to evaluate the performance of the model; Select statistical methods or machine learning models based on data characteristics and business needs; Use the training set data to train the model, adjust the model parameters to obtain the best performance, and use the validation set to evaluate the accuracy and generalization ability of the model; Improve model performance by adjusting model parameters, using feature selection or ensemble learning methods, and implementing cross-validation to ensure model stability and reliability; Identify and handle outliers that affect model performance, apply time series analysis to identify energy consumption trends and periodic patterns, use cluster analysis to identify energy consumption patterns, and group energy consumption behaviors that meet a certain standard of similarity; Build predictive models to forecast future energy consumption data, interpret model results, determine their potential impact on business decisions, and deploy trained models into production environments for real-time or batch energy consumption data analysis; Monitor how your model performs in real-world applications.

3. The wireless network-based smart park energy consumption monitoring system according to claim 2 is characterized in that: The specific operation steps of monitoring the performance of the model in actual application in the data processing module are as follows: A comprehensive analysis is performed by collecting the performance parameters of the model, including: Accuracy, precision, recall, F1 score and mean square error; Select the importance of each evaluation indicator, assign a weight to each indicator, and then normalize the obtained accuracy, precision, recall, F1 score and mean square error and enter them into the following formula: ZPZ = κ1*Accuracy+κ2*Precision+κ3*Recall+κ4*F1 Score+κ5*MSE to obtain the comprehensive value ZPZ, where Accuracy, Precision, Recall, F1 Score and MSE are accuracy, precision, recall, F1 score and mean square error respectively, and κ1, κ2, κ3, κ4, κ5 are the preset weight coefficients of accuracy, precision, recall, F1 score and mean square error respectively; The obtained synergistic value is used as a standard to measure the performance of the model, and is compared with several preset synergistic value intervals. Different effect levels are set corresponding to the several synergistic value intervals, so as to determine the effect level of the current model performance; At the same time, the obtained synergistic value ZPZ is compared with the preset synergistic threshold. When the synergistic value does not reach the preset synergistic threshold standard, it is judged that the effect does not meet the standard, and targeted model optimization is performed for different performance parameter data.

4. The wireless network-based smart park energy consumption monitoring system according to claim 3 is characterized in that: The specific operation steps of the data processing module for optimizing the model in a targeted manner according to different performance parameter data are as follows: When the accuracy rate does not meet the standard, resample or collect more data, including misclassified samples, and use different feature selection methods to find features that represent the characteristics of the data; When the precision and recall rates do not meet the standards, the classification threshold is adjusted to balance the two, and cost-sensitive learning is used to set different weights for the costs of misclassification. When the F1 score does not meet the standard, optimize the model parameters or use a different model; When the mean square error does not meet the standard, a new model with higher complexity than the existing model is selected or a nonlinear combination of features is added.

5. The wireless network-based smart park energy consumption monitoring system according to claim 1 is characterized in that: The specific operation steps of the data processing module to identify and analyze the causes of abnormal energy consumption through an abnormality detection algorithm are as follows: Define the definition, type and characteristics of anomalies, analyze historical data to identify normal and abnormal energy consumption patterns, and select anomaly detection methods based on data characteristics: based on thresholds, statistical models or machine learning algorithms; use statistical metrics such as mean, median, and percentile to establish energy consumption baselines, determine thresholds to distinguish normal and abnormal energy consumption, and use statistical methods such as Z-scores and box plots for anomaly detection; select the corresponding algorithm and train the model; Define scoring mechanisms for different detection methods, standardize scoring, assign weights based on the reliability of the methods, calculate comprehensive scores, set thresholds to judge anomalies, integrate the detection results of different methods, and determine the final anomaly detection results through a voting mechanism; Sort anomalies based on comprehensive scores, manually review anomalies, compare detection results with actual conditions, collect feedback, and dynamically adjust thresholds and weights; Interpret comprehensive test results, identify anomalous data points and their causes, and generate reports.

6. The wireless network-based smart park energy consumption monitoring system according to claim 1 is characterized in that: The specific operation steps of the energy consumption display module to display energy consumption data to the user and to prompt when an abnormality is detected are as follows: First, an authentication mechanism is used to ensure that each user can only see his or her own energy consumption data to avoid data leakage; Identify user needs for data presentation, including data types and interface preferences, design the user interface, determine the layout, colors, and fonts, and select data visualization tools, including D3.js, Echarts, or Highcharts; Realize the display of charts and dashboards of real-time energy consumption data, provide functions that allow users to query and analyze historical energy consumption data, and allow users to customize data views according to specific needs; When abnormal energy consumption is detected, the user is immediately prompted through the interface, an alarm mechanism is designed, and the user is notified via email, SMS or App push; Providing tools to enable users to compare energy consumption in different time periods or user groups, displaying energy-saving suggestions based on data analysis, and assisting users in optimizing energy consumption; Implement user login and permission control to ensure data security, ensure that the display module is compatible with PCs, tablets and smartphones, and develop interactive functions for data screening, exporting and printing; Provide feedback channels, collect user opinions and suggestions, optimize loading speed and response time, and improve user experience.

7. The wireless network-based smart park energy consumption monitoring system according to claim 6 is characterized in that: The energy consumption display module ensures that each user can only see his or her own energy consumption data information through the authentication mechanism. The specific operation steps are as follows: Implement username and password, biometric or multi-factor authentication mechanisms to configure access rights based on user roles and identities to ensure data access restrictions; Encrypt user data, including during storage and transmission, and generate and verify a unique identifier for each user session to ensure session security; Record detailed user operation logs, including time, IP address, and operation details, and perform data isolation at the database level to ensure that users can only access their own data; Follow the principle of least privilege, grant users only the permissions to complete corresponding tasks, customize the interface according to user permissions, only display authorized data and functions, and ensure that all data access APIs perform permission checks; Monitor and alert on unusual access patterns, including unusual frequencies of failed logins or unusual data access; Develop and maintain a data breach emergency plan to ensure rapid response.

8. The wireless network-based smart park energy consumption monitoring system according to claim 1 is characterized in that: The specific operation steps of the energy consumption collection module to collect water, electricity and gas energy consumption data of different users in the smart park are as follows: Collect smart electricity meters, water meters, and gas meters from all buildings in the park, record the model, manufacturer, and communication interface, and confirm whether the communication protocol of the energy consumption monitoring equipment is compatible with the wireless network standard; Select or develop adapters or gateways to convert communication protocols of different devices, design unified data collection logic, and ensure data format consistency; Install an independent energy consumption monitoring device for each user and assign a unique identification code to link all energy consumption monitoring device identification codes of the same user; Configure the data acquisition unit to communicate with the energy consumption monitoring equipment to achieve real-time data acquisition and preliminary processing, and configure the Wi-Fi or cellular network module to ensure compatibility with the data acquisition module; Implement TLS / SSL data encryption technology to ensure data transmission security, test the data acquisition module in the actual environment to ensure data accuracy and real-time performance.

9. The wireless network-based smart park energy consumption monitoring system according to claim 1 is characterized in that: The specific operation steps of the wireless data transmission module transmitting the energy consumption data to the data processing module via the wireless network are as follows: Clarify data transmission requirements, including data volume, frequency, and security, and select corresponding wireless communication technologies based on the scale and layout of the park; Select communication protocols that match the Internet of Things, configure gateways for non-standard protocol devices, and design data encryption and authentication mechanisms to ensure transmission security; Develop wireless data transmission modules to ensure seamless connection with data acquisition and processing modules, configure the IP address of energy consumption collection equipment or use DHCP to automatically allocate; Test wireless network coverage, stability and speed to ensure that requirements are met, determine the data transmission format, and compress the data; According to the network and data characteristics, optimize the data packet size and transmission interval, use error detection and automatic retransmission mechanisms to ensure data integrity, test the transmission speed, stability and security in a simulated environment, and perform regular maintenance and upgrades to adapt to new security and technical requirements.

Images