Internet of Things data platform based on big data and AI
By introducing an IoT data platform based on big data and AI into the energy management system, the problem of inefficiency of traditional energy management systems is solved, refined energy management and automated energy-saving operations are achieved, and energy consumption and operation costs are significantly reduced.
Patent Information
- Application Number
- CN202510320907.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-18
- Publication Date
- 2025-06-10
AI Technical Summary
Traditional energy management systems rely on manual monitoring and manual adjustments, which are inefficient and difficult to achieve refined management.
It adopts an IoT data platform based on big data and AI, including data acquisition module, data processing module, intelligent decision support module, user interaction interface and execution control module, and uses a variety of machine learning algorithms and wireless communication protocols to monitor and optimize energy use in real time.
It significantly improves the accuracy of energy consumption prediction, realizes automated energy-saving operations, reduces energy consumption and operation costs, and enhances the flexibility and adaptability of the system.
Smart Images
Figure CN120122540A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of data platforms, and more particularly, to an Internet of Things data platform based on big data and AI. Background Art
[0002] With the continuous growth of global energy demand and the increasing awareness of environmental protection, energy conservation and emission reduction have become an important issue of common concern for enterprises and individuals. Traditional energy management systems often rely on manual monitoring and manual adjustment, which is not only inefficient but also difficult to achieve refined management. In recent years, the development of Internet of Things (IoT) technology and artificial intelligence (AI) has provided new solutions for energy management.
[0003] Therefore, we have made improvements in this regard and proposed an Internet of Things data platform based on big data and AI. Summary of the Invention
[0004] The purpose of the present invention is to address the problem that traditional energy management systems often rely on manual monitoring and manual adjustment, which is not only inefficient but also difficult to achieve refined management.
[0005] To achieve the above object of the invention, the present invention provides an Internet of Things data platform based on big data and AI to improve the above problems.
[0006] Specifically, this application is as follows: It includes the following modules: Data Acquisition Module: This module includes various types of sensors and metering devices, including smart meters, temperature and humidity sensors, and light intensity sensors, for real-time monitoring of energy consumption and environmental parameters in buildings. It also includes a wireless communication unit that uses LoRaWAN and Zigbee protocols to transmit the collected data to the cloud server; Data Processing Module: Utilizes a cloud computing platform to store and process data from the data acquisition module, performs data cleaning, integration, and feature extraction through big data analysis tools to form a structured energy consumption dataset; Intelligent Decision Support Module: Trains historical energy consumption data using the following algorithms, combines the current energy consumption status and external factors (such as weather forecasts and electricity price information), predicts future energy consumption trends, and generates an optimized scheduling plan accordingly: Time Series Prediction Model: Adopts the ARIMA model, where is the number of autoregressive terms, is the number of differencing times, is the number of moving average terms, and the model expression is: Random Forest: Predictions are made by constructing multiple decision trees, each trained based on a subsample of the dataset and a subset of features; Neural Network: Adopts a feedforward neural network structure, including an input layer, hidden layers, and an output layer. The forward propagation formulas are as follows: Output of the hidden layer is: ; Output of the hidden layer after passing through the activation function is: ; Output of the output layer is: ; Final predicted output is: ; Adaptive Learning Mechanism: Updates the model parameters through gradient descent. The update rule is: ; User Interface: This interface is for web applications and mobile applications, allowing users to view detailed energy consumption reports, energy-saving suggestions, and personal preference settings. It also provides visual charts to display daily, weekly, and monthly power consumption trends and cost-saving estimates; Execution Control Module: Receives scheduling instructions from the intelligent decision support module and directly controls the controllable devices in the building. Sends commands to smart sockets and smart thermostat devices through the API interface to achieve automated energy-saving operations.
[0007] As a preferred technical solution of this application, the wireless communication unit in the data acquisition module further includes an encryption function to ensure the security of data during transmission.
[0008] As a preferred technical solution of this application, the data processing module further includes an anomaly detection sub-module, which can identify and mark abnormal energy consumption patterns and notify the administrator for inspection in a timely manner.
[0009] As a preferred technical solution of this application, the intelligent decision support module further includes an adaptive learning mechanism, which continuously adjusts and optimizes strategies according to user feedback to improve prediction accuracy and user satisfaction.
[0010] As a preferred technical solution of this application, the user interface also provides customized service options, allowing users to set personalized energy-saving goals according to their living habits and preferences.
[0011] As a preferred technical solution of this application, the execution control module further includes a manual intervention function, allowing users to temporarily modify the automatic control plan according to the actual situation.
[0012] An energy management method, comprising the following steps: S100. Collect energy consumption data and environmental parameters at each key location within the building; S200. Upload the data to a cloud server for processing and analysis; S300. Analyze historical energy consumption patterns and current status using machine learning algorithms, and predict future electricity demand in combination with external data source information; S400. Develop an optimized scheduling plan based on the prediction results; As a preferred technical solution of this application, the following steps are further included: S100. Provide users with visual energy consumption reports and energy-saving suggestions; S100. Implement remote control of controllable devices to achieve immediate energy-saving effects; S100. Monitor the system operation status and give alarm prompts for abnormal situations; S100. Regularly update model parameters to adapt to new data patterns and user requirements.
[0013] A computer-readable medium, on which program instructions are stored, and when the program instructions are executed by a processor, the program instructions include: Data acquisition instructions for obtaining energy consumption and related environmental data from Internet of Things devices; Data processing instructions for cleaning and organizing data and forming a structured data set; Prediction and analysis instructions for predicting future energy consumption trends based on historical data; Scheduling and planning instructions for generating an optimized scheduling plan according to the prediction results; User interaction instructions for presenting energy consumption reports and energy-saving suggestions; As a preferred technical solution of this application, the program instructions further include: Control execution instructions for sending control signals to controllable devices to achieve energy-saving purposes; Abnormality detection instructions for identifying and marking abnormal energy consumption patterns; Adaptive learning instructions for adjusting and optimizing strategies according to user feedback; Manual intervention instructions allowing users to temporarily modify the automatic control scheme.
[0014] Compared with the prior art, the beneficial effects of the present invention: In the solution of this application: 1. Through the cloud computing platform and big data analysis tools, it is possible to quickly process a large amount of energy consumption data, generate a structured data set, and improve the data processing efficiency; 2. By adopting a variety of advanced machine learning algorithms and combining historical energy consumption data and external factors, the accuracy of energy consumption prediction has been significantly improved; 3. Provide a Web application or a mobile application that allows users to view detailed energy consumption reports and energy-saving suggestions, and at the same time support personalized setting options; 4. The system supports a manual intervention function that allows users to temporarily modify the automatic control scheme according to the actual situation, increasing the flexibility and adaptability of the system; 5. Through accurate energy consumption prediction and optimized scheduling, the system can significantly reduce the energy consumption of buildings, reduce operating costs, and at the same time promote sustainable development. Brief Description of the Drawings
[0015] Figure 1 It is a schematic diagram of the Internet of Things data platform based on big data and AI provided by this application; Detailed Embodiment In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a 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 those of ordinary skill in the art without creative work shall fall within the protection scope of the present invention.
[0016] As described in the background art, traditional energy management systems often rely on manual monitoring and manual adjustment. This method is not only inefficient but also difficult to achieve refined management.
[0017] To solve this technical problem, the present invention provides an Internet of Things data platform based on big data and AI, which is applied to the field of data platforms.
[0018] Specifically, please refer to Figure 1 , the Internet of Things data platform based on big data and AI specifically includes: Data acquisition module: This module includes various types of sensors and metering devices, including smart meters, temperature and humidity sensors, and light intensity sensors, which are used to monitor the energy consumption situation and environmental parameters in the building in real time. It also includes a wireless communication unit that uses the LoRaWAN and Zigbee protocols to transmit the collected data to the cloud server; Implementation steps: Install sensors and metering devices at key positions in the building, configure the wireless communication unit, and ensure the security of data transmission through a security protocol (such as AES encryption).
[0019] Data Processing Module: Utilize the cloud computing platform to store and process data from the data acquisition module, and perform data cleaning, integration, and feature extraction through big data analysis tools to form a structured energy consumption dataset; Implementation Steps: Establish cloud computing infrastructure, deploy data processing software, set data cleaning rules, and execute data preprocessing tasks such as removing noise, filling missing values, and standardizing data formats.
[0020] Intelligent Decision Support Module: Use the following algorithms to train historical energy consumption data, combine the current energy consumption status and external factors (such as weather forecasts, electricity price information), predict future energy consumption trends, and generate an optimized scheduling plan accordingly: Time Series Prediction Model: Adopt the ARIMA model, where is the number of autoregressive terms, is the number of differencing times, is the number of moving average terms, and the model expression is: Random Forest: Make predictions by constructing multiple decision trees, and each tree is trained based on a subsample of the dataset and a subset of features; Neural Network: Adopt a feedforward neural network structure, including an input layer, a hidden layer, and an output layer. The forward propagation formula is as follows: The output of the hidden layer is: ; The output of the hidden layer after passing through the activation function is: ; The output of the output layer is: ; The final predicted output is: ; Adaptive Learning Mechanism: Update the model parameters through the gradient descent method, and the update rule is: ; Implementation Steps: Select a suitable machine learning framework (such as TensorFlow or PyTorch), design and implement the above algorithms, train the model, and update it regularly to adapt to new data patterns.
[0021] User Interface: This interface is a web application and a mobile application that allows users to view detailed energy consumption reports, energy-saving suggestions, and personal preference settings, and at the same time provides visual charts to display the daily, weekly, and monthly electricity consumption trends and cost savings estimates; Implementation steps: Develop the front-end interface, integrate a data visualization library (such as D3.js or ECharts), implement a user login authentication system, and provide personalized setting options.
[0022] Execution control module: Receive scheduling instructions from the intelligent decision support module and directly control the controllable devices in the building. Send commands to smart sockets and smart thermostat devices through the API interface to achieve automated energy-saving operations.
[0023] Implementation steps: Develop a device control interface, write API documentation, implement docking with various smart devices, and ensure the accuracy and timeliness of control commands.
[0024] To enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings.
[0025] It should be noted that, without conflict, the embodiments in the present invention and the features and technical solutions in the embodiments can be combined with each other.
[0026] It should be noted that: Similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.
[0027] Example 1, please refer to Figure 1 , An IoT data platform based on big data and AI, the wireless communication unit in the data acquisition module further includes an encryption function to ensure the security of data during transmission; Implementation steps: Integrate an encryption algorithm (such as AES-256) in the wireless communication unit, set a key management strategy to ensure that data is not stolen or tampered with during transmission.
[0028] The data processing module further includes an anomaly detection sub-module, which can identify and mark abnormal energy consumption patterns and notify the administrator for inspection in a timely manner; Implementation steps: Design an anomaly detection algorithm (such as Isolation Forest or One-Class SVM), integrate it into the data processing module, and configure an alarm system to automatically send notifications when anomalies are detected.
[0029] The intelligent decision support module further includes an adaptive learning mechanism, which continuously adjusts and optimizes strategies according to user feedback to improve prediction accuracy and user satisfaction; Implementation steps: Design a user feedback system, collect user feedback data, regularly evaluate the model performance, adjust the model parameters according to the feedback, and continuously optimize the prediction effect.
[0030] The user interface also provides customization service options, allowing users to set personalized energy-saving goals according to their living habits and preferences. Implementation steps: Add a personalized setting function to the user interface, allowing users to set energy-saving goals and adjust the system's optimization strategy according to the user settings.
[0031] The execution control module also includes a manual intervention function, allowing users to temporarily modify the automatic control scheme according to the actual situation.
[0032] Implementation steps: Provide manual control options on the user interface, allowing users to temporarily override automatic control commands and record the user's intervention behavior for subsequent system optimization.
[0033] An energy management method includes the following steps: S100. Collect energy consumption data and environmental parameters at key locations within the building. S200. Upload the data to a cloud server for processing and analysis. S300. Use machine learning algorithms to analyze historical energy consumption patterns and the current state, and combine external data source information to predict future electricity demand. S400. Develop an optimized scheduling plan based on the prediction results. It also includes the following steps: S100. Provide users with visual energy consumption reports and energy-saving suggestions. S100. Implement remote control of controllable devices to achieve immediate energy-saving effects. S100. Monitor the system operation status and give alarm prompts for abnormal situations. S100. Regularly update the model parameters to adapt to new data patterns and user requirements.
[0034] A computer-readable medium stores program instructions that, when executed by a processor, cause the processor to execute the energy management method according to claim 7, where the program instructions include: Data acquisition instructions for obtaining energy consumption and related environmental data from Internet of Things devices. Data processing instructions for cleaning and organizing the data to form a structured data set. Prediction and analysis instructions for predicting future energy consumption trends based on historical data. Scheduling and planning instructions for generating an optimized scheduling plan according to the prediction results. User interaction instructions for presenting energy consumption reports and energy-saving suggestions. The program instructions further include: Control execution instructions for sending control signals to controllable devices to achieve energy-saving purposes. Anomaly detection instruction for identifying and marking abnormal energy consumption patterns; Adaptive learning instruction for adjusting and optimizing strategies according to user feedback; Manual intervention instruction allowing users to temporarily modify the automatic control scheme.
[0035] In the present invention, unless otherwise clearly defined and limited, terms such as "installed", "connected", "joined", "fixed", etc. shall be construed in a broad sense. For example, it may be a fixed connection, a detachable connection, or integrated; it may be a mechanical connection, an electrical connection, or communicable with each other; it may be directly connected, or indirectly connected through an intermediate medium, and may be the internal connection of two components or the interaction relationship between two components, unless otherwise clearly defined. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.
[0036] Obviously, the above-described embodiments are only a part of the embodiments of the present invention, rather than all embodiments. The drawings show preferred embodiments of the present invention, but do not limit the patent scope of the present invention. The present invention can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosed content of the present invention more thorough and comprehensive. Although the present invention has been described in detail with reference to the foregoing embodiments, for those skilled in the art, they can still modify the technical solutions described in the foregoing specific embodiments, or perform equivalent replacements for some of the technical features. Any equivalent structure directly or indirectly using the content of the specification and drawings of the present invention in other related technical fields is equally within the scope of the patent protection of the present invention.
Claims
1. An Internet of Things data platform based on big data and AI, characterized in that: Includes the following modules: Data acquisition module: This module contains various types of sensors and metering devices, including smart meters, temperature and humidity sensors, and light intensity sensors, which are used to monitor energy consumption and environmental parameters in the building in real time. It also includes a wireless communication unit that uses LoRaWAN and Zigbee protocols to transmit the collected data to the cloud server; Data processing module: uses the cloud computing platform to store and process data from the data acquisition module, and uses big data analysis tools to clean, integrate and extract features of the data to form a structured energy consumption data set; Intelligent decision support module: Use the following algorithms to train historical energy consumption data, combine current energy consumption status and external factors, predict future energy consumption trends, and generate optimized scheduling plans accordingly: Time Series Forecasting Model: Using ARIMA Model, where is the number of autoregressive terms, is the number of differences, is the number of sliding average items, and the model expression is: Random Forest: Make predictions by building multiple decision trees, each trained on a subsample of the dataset and a subset of features; Neural network: A feedforward neural network structure is used, including an input layer, a hidden layer, and an output layer. The forward propagation formula is as follows: Output of hidden layer for: ; The hidden layer output after the activation function for: ; Output of the output layer for: ; Final prediction output for: ; Adaptive learning mechanism: Update model parameters through gradient descent method, and the update rule is: ； User Interface: This interface is a web application and mobile application that allows users to view detailed energy consumption reports, energy saving suggestions and personal preferences, and provides visual charts to show daily, weekly and monthly power consumption trends and cost savings estimates; Execution control module: Receives dispatch instructions from the intelligent decision support module and directly controls the controllable devices in the building. It sends commands to smart sockets and smart thermostats through the API interface to achieve automated energy-saving operations.
2. According to claim 1, an Internet of Things data platform based on big data and AI is characterized in that: The wireless communication unit in the data acquisition module also includes an encryption function to ensure the security of data during transmission.
3. According to claim 2, an Internet of Things data platform based on big data and AI is characterized in that: The data processing module also includes an anomaly detection submodule that can identify and mark abnormal energy consumption patterns and promptly notify administrators to conduct inspections.
4. The IoT data platform based on big data and AI according to claim 3, characterized in that: The intelligent decision support module also includes an adaptive learning mechanism to continuously adjust the optimization strategy based on user feedback to improve prediction accuracy and user satisfaction.
5. The IoT data platform based on big data and AI according to claim 4, characterized in that: The user interaction interface also provides customized service options, and users can set personalized energy-saving goals according to their own living habits and preferences.
6. The IoT data platform based on big data and AI according to claim 5, characterized in that: The execution control module also includes a manual intervention function, allowing the user to temporarily modify the automatic control scheme according to actual conditions.
7. An energy management method, using the Internet of Things data platform described in any one of claims 1 to 6, characterized in that: The following steps are involved: S100, collect energy consumption data and environmental parameters at key locations in the building; S200, uploading the data to a cloud server for processing and analysis; S300, using machine learning algorithms to analyze historical energy consumption patterns and current status, and combining external data source information to predict future electricity demand; S400. Formulate an optimized scheduling plan based on the prediction results.
8. An energy management method according to claim 7, characterized in that: The following steps are also included: S100, provide users with visual energy consumption reports and energy-saving suggestions; S100, remotely control controllable equipment to achieve immediate energy saving effect; S100, monitor the system operation status and issue an alarm for abnormal situations; S100. Regularly update model parameters to adapt to new data patterns and user needs.
9. A computer-readable medium having program instructions stored thereon, which, when executed by a processor, causes the processor to execute the energy management method according to claim 7, characterized in that: The program instructions include: Data collection instructions, used to obtain energy consumption and related environmental data from IoT devices; Data processing instructions, used to clean and organize data and form structured data sets; Predictive analysis instructions for predicting future energy consumption trends based on historical data; Scheduling planning instructions, used to generate optimized scheduling plans based on forecast results; User interaction commands for presenting energy consumption reports and energy saving suggestions.
10. A computer-readable medium according to claim 9, characterized in that: The program instructions also include: Control execution instructions, used to send control signals to controllable devices to achieve energy saving; Anomaly detection instructions to identify and flag unusual energy consumption patterns; Adaptive learning instructions for adjusting optimization strategies based on user feedback; Manual intervention commands allow the user to temporarily modify the automatic control scheme.