Smart park energy comprehensive management and control platform based on data analysis
By integrating data collection, analysis, and edge computing into the smart park energy comprehensive management and control platform, the problem of inaccurate renewable energy power generation forecasts has been solved, accurate forecasting and optimized scheduling of energy demand have been achieved, and the park's energy utilization rate and system reliability have been improved.
Patent Information
- Application Number
- CN202510759878.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-09
- Publication Date
- 2025-09-05
AI Technical Summary
The existing smart park energy integrated management and control platform is unable to accurately predict renewable energy generation, resulting in difficulties in balancing energy supply and demand in the park, especially when weather factors are highly uncertain.
Energy consumption and meteorological data are obtained in real time through the data acquisition module, energy demand is predicted using the LSTM algorithm, abnormal data is eliminated in combination with the isolation forest algorithm, the decision-making module is optimized for scheduling, multi-source data analysis and edge computing are used to reduce latency, and accurate prediction and optimized scheduling are achieved.
It has significantly improved the energy utilization rate of the park, reduced the overall energy consumption cost by 15%-20%, and enhanced the risk resistance and operational reliability of the park's energy system.
Smart Images
Figure CN120598720A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of smart energy management technology, and specifically to a smart park energy integrated management and control platform based on data analysis. Background Art
[0002] The Smart Park Integrated Energy Management and Control Platform is an intelligent management system that leverages technologies such as the Internet of Things, big data, and artificial intelligence to monitor, analyze, optimize, and control various energy systems within the park in real time. Through a data-driven approach, the platform achieves efficient energy utilization, cost savings, and reduced carbon emissions.
[0003] In smart parks, renewable energy sources such as solar, wind, and hydropower are widely used due to their environmentally friendly and sustainable nature. However, the power output of these renewable energy sources is significantly intermittent and volatile, and is significantly affected by natural factors such as weather and seasons. For example, solar power generation is directly related to the intensity of solar radiation. During periods of overcast, rainy days, and at night, solar radiation intensity is significantly reduced or even disappears, causing photovoltaic power generation to plummet or even reach zero. Research indicates that during periods of continuous overcast and rainy weather, photovoltaic power generation efficiency can drop by over 80%. Existing smart park energy management and control platforms based on data analytics primarily analyze and predict real-time and historical data. However, the uncertainty of weather factors makes accurate forecasting of renewable energy generation difficult, making it extremely difficult to maintain a balanced energy supply and demand in the park. Summary of the Invention
[0004] In response to the shortcomings of existing technologies, the present invention provides a smart park energy integrated management and control platform based on data analysis, which solves the problem that the uncertainty of weather factors makes it difficult to accurately predict renewable energy generation, which brings great difficulties to maintaining the balance of energy supply and demand in the park.
[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a smart park energy comprehensive management and control platform based on data analysis, including a data acquisition module, a data transmission module, a data storage module, a data processing module, an energy monitoring and analysis module, a visualization operation module and an optimization decision module. The data acquisition module is used to collect energy consumption data and equipment operation status in real time, and obtain meteorological data; the data transmission module is used for safe and real-time data transmission; the data storage module is used to store real-time data, historical data and user information; the data processing module is used to eliminate missing values and outliers and extract valid data; the energy monitoring and analysis module is used to monitor energy consumption and environmental parameters, support multi-dimensional comparison, and predict 1-24 hours of energy demand based on historical data; the visualization operation module is used for management personnel to manually adjust the optimization strategy; the optimization decision module is used to schedule according to energy demand.
[0006] Preferably, the data acquisition module includes deploying terminal devices such as smart electricity meters, water meters, gas meters, environmental sensors, cameras, etc. to collect energy consumption data and equipment operating status in real time, and uses RESTful API to connect to the Tianheng Program of the China Meteorological Administration to obtain minute-level hourly forecast data.
[0007] Preferably, the data transmission module performs preliminary filtering and protocol conversion on the original data through the edge node to reduce transmission delay and cloud pressure; adopts the MQTT networking protocol, and securely transmits the data processed by the edge node to the cloud platform through the edge algorithm.
[0008] Preferably, the data storage module uses the InfluxDB time series database to store real-time data and the MySQL relational database to store structured data such as device files and user information.
[0009] Preferably, the data processing module removes missing values and outliers through the isolation forest algorithm, extracts time features and derived indicators, and implements data aggregation, association analysis and machine learning modeling based on the Spark big data framework.
[0010] Preferably, the energy monitoring and analysis module includes energy monitoring and analysis and prediction. The energy monitoring performs multi-dimensional comparison by acquiring real-time energy consumption and environmental parameters, and identifies anomalies through threshold detection to trigger SMS and email alarms. The analysis and prediction module uses the LSTM algorithm to predict energy demand through the real-number energy consumption data characteristics.
[0011] Preferably, the data acquisition module uses a RESTful API to connect to the Tianheng Program of the China Meteorological Administration to obtain minute-level hourly forecast data. The data processing module processes streaming meteorological data in real time through Apache Flink and updates the meteorological impact model on renewable energy through Apache Flink. The energy monitoring and analysis module plans energy scheduling by combining the impact of meteorology on renewable energy with energy demand in the next 24 hours.
[0012] Preferably, the optimization decision module optimizes the energy scheduling of the park through energy demand forecasting and the impact of weather on renewable energy, and issues control instructions to smart devices through an API interface.
[0013] Preferably, the visualization operation module provides dynamic charts and interactive dashboards through Grafana and ECharts, managers can manually adjust the optimization strategy, and the system automatically records and updates the model parameters.
[0014] Preferably, the edge algorithm pre-processes local meteorological data through Raspberry Pi and Node-RED to reduce the cloud load.
[0015] The present invention provides a smart park energy integrated management and control platform based on data analysis. It has the following beneficial effects: 1. The present invention integrates meteorological data through the platform to dynamically plan energy scheduling, adjusts equipment operation mode in extreme weather conditions, adjusts park energy scheduling, reduces the use of non-essential equipment in the park, deploys emergency response plans in advance, and significantly enhances the risk resistance and operational reliability of the park energy system.
[0016] 2. This invention utilizes a platform that collects and deeply analyzes multi-source data, integrating energy consumption, equipment status, and meteorological data. It then uses the LSTM algorithm to accurately predict 1-24 hour energy demand, incorporating an isolation forest algorithm to eliminate outliers and ensure prediction accuracy. Based on this, the optimization decision module can proactively schedule energy, such as pre-adjusting air conditioning loads before hot weather and adjusting energy storage charging and discharging strategies based on peak and valley electricity prices. This significantly improves the park's energy utilization, effectively reducing overall energy costs by 15%-20%, and achieving efficient resource allocation. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] Figure 1 This is a system block diagram of the present invention. DETAILED DESCRIPTION
[0018] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.
[0019] Example: Please see the attached Figure 1 The embodiment of the present invention provides a smart park energy comprehensive management and control platform based on data analysis, including a data acquisition module for real-time collection of energy consumption data and equipment operating status, and acquisition of meteorological data. By deploying terminal devices such as smart electricity meters, water meters, gas meters, environmental sensors, cameras, etc., energy consumption data and equipment operating status are collected in real time, and a RESTful API is used to connect to the Tianheng Program of the China Meteorological Administration to obtain minute-level hourly forecast data.
[0020] The data transmission module performs preliminary filtering and protocol conversion on the raw data through edge nodes to reduce transmission delays and cloud pressure; it uses the MQTT networking protocol to pre-process local meteorological data through Raspberry Pi and Node-RED to reduce cloud load, and securely transmits the data processed by the edge nodes to the cloud platform. It supports wired and wireless networks to ensure the stability and real-time performance of data transmission, and transmits the data to the data storage module and data processing module of the data processing center.
[0021] The data storage module uses the InfluxDB time series database to store real-time data and the MySQL relational database to store structured data such as device files and user information.
[0022] The data processing module uses the isolation forest algorithm to eliminate missing values and outliers, extract time features and derived indicators, and implement data aggregation, association analysis and machine learning modeling based on the Spark big data framework.
[0023] The energy monitoring and analysis module displays the energy consumption and environmental parameters of each building and equipment in real time, supports multi-dimensional comparison, and triggers SMS and email alerts through threshold detection, such as sudden increases in electricity consumption or anomalies identified by machine learning models such as the Isolation Forest. It also uses the LSTM algorithm to predict energy demand for 1-24 hours based on historical data and real-time energy consumption data. The data acquisition module uses a RESTful API to connect to the China Meteorological Administration's Tianheng Program to obtain minute-by-hour forecast data. The data processing module uses Apache Flink to process streaming meteorological data in real time and update the meteorological impact model on renewable energy through Apache Flink. The energy monitoring and analysis module combines the meteorological impact on renewable energy with energy demand within the next 24 hours to plan energy scheduling.
[0024] The optimization decision-making module optimizes the park's energy scheduling by forecasting energy demand and the impact of weather on renewable energy, and issues control instructions to smart devices through the API interface. The visualization operation module provides dynamic charts and interactive dashboards through Grafana and ECharts. Managers can manually adjust the optimization strategy, and the system automatically records and updates the model parameters.
[0025] Through multi-source data collection and in-depth analysis, the platform integrates energy consumption, equipment status, and meteorological data. It uses the LSTM algorithm to accurately predict 1-24 hour energy demand, and combines it with the isolation forest algorithm to eliminate outliers to ensure forecast accuracy. Based on this, the optimized decision-making module can dispatch energy in advance. For example, it can pre-adjust air conditioning loads before high-temperature weather and adjust energy storage charging and discharging strategies using peak and valley electricity prices. This significantly improves the park's energy utilization rate, effectively reduces overall energy costs, and achieves efficient resource allocation. The platform also integrates meteorological data to dynamically plan energy scheduling, adjust equipment operating modes in extreme weather, adjust park energy scheduling, reduce the use of non-essential equipment in the park, and deploy emergency response plans in advance to avoid untimely and unreasonable energy scheduling due to sudden weather anomalies. This significantly enhances the risk resistance and operational reliability of the park's energy system.
[0026] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.
Claims
1. A smart park integrated energy management and control platform based on data analysis, including a data acquisition module, a data transmission module, a data storage module, a data processing module, an energy monitoring and analysis module, a visual operation module, and an optimization decision module, characterized by: The data acquisition module is used to collect energy consumption data and equipment operating status in real time, and obtain meteorological data; the data transmission module is used to transmit data securely in real time; the data storage module is used to store real-time data, historical data and user information; the data processing module is used to eliminate missing values and outliers and extract valid data; the energy monitoring and analysis module is used to monitor energy consumption and environmental parameters, support multi-dimensional comparison, and predict energy demand for 1-24 hours based on historical data; the visual operation module is used for managers to manually adjust optimization strategies; the optimization decision module is used to schedule according to energy demand.
2. The data analysis-based smart park energy integrated management and control platform according to claim 1 is characterized in that: The data collection module includes the deployment of smart electricity meters, water meters, gas meters, environmental sensors, cameras and other terminal devices to collect energy consumption data and equipment operating status in real time, and uses RESTful API to connect to the Tianheng Program of the China Meteorological Administration to obtain minute-by-minute forecast data.
3. The smart park energy integrated management and control platform based on data analysis according to claim 1 is characterized in that: The data transmission module performs preliminary filtering and protocol conversion on the original data through the edge node, reducing transmission delay and cloud pressure; Using the MQTT networking protocol, the data processed by the edge node is securely transmitted to the cloud platform through the edge algorithm.
4. The smart park energy integrated management and control platform based on data analysis according to claim 1 is characterized in that: The data storage module uses the InfluxDB time series database to store real-time data and the MySQL relational database to store structured data such as device files and user information.
5. The smart park energy integrated management and control platform based on data analysis according to claim 1 is characterized in that: The data processing module uses the isolation forest algorithm to eliminate missing values and outliers, extract time features and derived indicators, and implement data aggregation, association analysis and machine learning modeling based on the Spark big data framework.
6. The smart park energy integrated management and control platform based on data analysis according to claim 1 is characterized in that: The energy monitoring and analysis module includes energy monitoring and analysis and prediction. The energy monitoring performs multi-dimensional comparison by acquiring real-time energy consumption and environmental parameters, and identifies anomalies through threshold detection, triggering SMS and email alarms. The analysis and prediction module uses the LSTM algorithm to predict energy demand based on the real-number energy consumption data characteristics.
7. The smart park energy integrated management and control platform based on data analysis according to claim 1 is characterized in that: The data acquisition module uses a RESTful API to connect to the China Meteorological Administration's Tianheng Program to obtain minute-by-hour forecast data. The data processing module uses Apache Flink to process streaming meteorological data in real time and update the meteorological impact model on renewable energy through Apache Flink. The energy monitoring and analysis module plans energy scheduling by combining the meteorological impact on renewable energy with energy demand in the next 24 hours.
8. The data analysis-based smart park energy integrated management and control platform according to claim 1 is characterized in that: The optimization decision module optimizes the energy scheduling of the park by predicting energy demand and the impact of weather on renewable energy, and sends control instructions to smart devices through the API interface.
9. The smart park energy integrated management and control platform based on data analysis according to claim 1 is characterized in that: The visualization operation module provides dynamic charts and interactive dashboards through Grafana and ECharts. Managers can manually adjust the optimization strategy, and the system automatically records and updates the model parameters.
10. The smart park energy integrated management and control platform based on data analysis according to claim 3 is characterized in that: The edge algorithm pre-processes local meteorological data through Raspberry Pi and Node-RED to reduce the cloud load.