Internet-based smart park power management system

Abstract

The invention provides a smart park power management system based on the Internet, and relates to the technical field of power management, and the system comprises a data collection module which is used for collecting the operation data of power related equipment in a park; the data management module is used for processing and storing the acquired operation data; the data analysis module is used for analyzing the operation data through a machine learning algorithm; the intelligent power dispatching module is used for intelligently adjusting power distribution according to the analysis result; according to the invention, through Internet connection, real-time monitoring of power equipment, environmental factors and power consumption of the park is realized, so that through cooperation of real-time monitoring and intelligent scheduling, unnecessary energy waste is avoided, the energy consumption of the park is reduced, the energy use efficiency is improved, the problem of blind scheduling in a traditional method is avoided, and the energy utilization rate of the park is improved. And the power distribution is more accurate and flexible.

Description

Technical Field

[0001] The present invention relates to the technical field of power management, and particularly to an Internet-based intelligent park power management system. Background Art

[0002] With the increasing attention to environmental protection, the application of intelligent power management systems in various buildings and parks has gradually become an important trend. Especially in the power management of intelligent parks, how to improve energy use efficiency and reduce energy consumption has become the core goal of promoting the development of intelligent parks. Traditional park power management systems usually rely on manual operation or simple timing control, and there are significant deficiencies in this management method, such as inflexible power scheduling, low equipment operation efficiency, and serious energy waste.

[0003] Existing power management systems usually adopt fixed power scheduling strategies, and perform power distribution and load management through schedules and preset rules. However, this method does not fully consider the real-time changes in power loads within the park and the operating status of equipment. For example, during some peak power demand periods or when the equipment load is too large, traditional power management systems often cannot adjust power supply in a timely manner, easily causing excessive waste or equipment overload, resulting in low overall system operation efficiency; for another example, existing power management systems often cannot monitor the energy efficiency of equipment in real time, resulting in inefficient equipment continuing to operate during inappropriate periods. Therefore, the present invention proposes an Internet-based intelligent park power management system to solve the problems existing in the prior art. Summary of the Invention

[0004] In view of the above problems, the object of the present invention is to propose an Internet-based intelligent park power management system, which has the advantages of reducing the energy consumption of the park and improving energy use efficiency, and can solve the problems in the prior art.

[0005] To achieve the object of the present invention, the present invention is realized through the following technical solutions: An Internet-based intelligent park power management system includes a data acquisition module for collecting the operation data of power-related equipment within the park;

[0006] A data management module for processing and storing the obtained operation data;

[0007] A data analysis module for analyzing the operation data through machine learning algorithms;

[0008] A power intelligent scheduling module for intelligently adjusting power distribution according to the analysis results.

[0009] A further improvement lies in that: the data acquisition module includes a device sensor sub-module for monitoring the operating status of power-related devices, an intelligent electricity meter sub-module for recording the electricity usage of power-related devices, and an environmental monitoring sub-module for recording the temperature, humidity, and wind speed within the park.

[0010] A further improvement lies in that: the data management module includes a cloud server sub-module for storing data using cloud computing and a data wireless transmission sub-module for wireless data transmission.

[0011] A further improvement lies in that: the specific steps for analyzing the operation data through machine learning algorithms are as follows:

[0012] S1. Construct a prediction analysis model based on the multi-task learning algorithm, with the input data being the operation data and the output data being power load prediction and equipment energy efficiency evaluation;

[0013] S2. Collect historical operation data, construct a data set, and train the prediction analysis model through the data set;

[0014] S3. Input the real-time collected operation data through the trained prediction analysis model to obtain the output result.

[0015] A further improvement lies in that: the power intelligent scheduling module includes an intelligent scheduling sub-module for intelligent adjustment, a backup power supply switching sub-module for automatically switching the backup power supply, and a green energy mobilization sub-module for accessing green energy.

[0016] A further improvement lies in that: the specific method for intelligently adjusting power distribution is as follows:

[0017] Construct a demand response strategy, combine the power load prediction and energy efficiency evaluation results, and then introduce a reinforcement learning algorithm to optimize the power scheduling and make real-time adjustments. The demand response strategy is that when the power demand in a certain period is too high, give priority to ensuring the load of high-efficiency devices and reduce the operating load of low-efficiency devices.

[0018] A further improvement lies in that: it also includes a fault warning module, and the fault warning module includes a real-time fault monitoring sub-module for monitoring operation data and a warning notification sub-module for sending warning notifications.

[0019] A further improvement lies in that: it also includes a user interface and control module, and the user interface and control module includes a user operation interface sub-module for displaying the system status, an operation control sub-module for user remote control, and a data report sub-module for generating an energy usage report.

[0020] The beneficial effects of the present invention are:

[0021] (1) Through Internet connection, the present invention realizes real-time monitoring of power equipment, environmental factors and power consumption in the park. By combining real-time monitoring with intelligent scheduling, unnecessary energy waste is avoided, thereby reducing the energy consumption of the park and improving the energy utilization efficiency. Therefore, the problem of "blind scheduling" in the traditional method is avoided, and the power distribution becomes more accurate and flexible.

[0022] (2) The present invention introduces machine learning algorithms and data analysis. Based on the data collected in real time, it can automatically perform power load forecasting and equipment energy efficiency assessment. Through multi-task learning algorithms, the present invention can not only predict the future power demand of the park, but also analyze the energy efficiency performance of equipment, enabling the system to automatically optimize power load distribution and make dynamic adjustments according to the equipment operation status, avoiding overuse of inefficient equipment, and thus improving the energy efficiency of the overall system.

[0023] (3) Through dynamic scheduling and real-time adjustment, the present invention reduces the dependence on manual intervention and empirical judgment, making power management more efficient and flexible. At the same time, based on cloud computing and Internet of Things technologies, the system can process a large amount of equipment data and power usage information, support the intelligent management of large-scale parks, and through precise scheduling, reduce energy waste and lower the overall energy consumption of the park. Brief Description of the Drawings

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0025] Figure 1 It is a schematic diagram of the system flow of the present invention. Detailed Embodiments

[0026] To deepen the understanding of the present invention, the following will further elaborate on the present invention in combination with embodiments. These embodiments are only used to explain the present invention and do not constitute a limitation on the protection scope of the present invention.

[0027] According to Figure 1 As shown, this embodiment proposes an Internet-based intelligent park power management system, including:

[0028] A data acquisition module for collecting the operation data of power-related equipment in the park, which includes:

[0029] The device sensor sub-module for monitoring the operating status of power-related devices, the smart meter sub-module for recording the power consumption of power-related devices, and the environmental monitoring sub-module for recording the temperature, humidity, and wind speed within the park. Among them, the operating status of power-related devices (corresponding to operating data) includes voltage, current, power factor, and device operating time, while the power consumption of power-related devices corresponds to the power consumption data of the devices. Obtaining environmental parameters will affect the energy efficiency of the devices. For example, a high-temperature environment may lead to a decrease in the energy efficiency of the air conditioning system.

[0030] The data management module is used to process and store the obtained operating data, and it includes:

[0031] The cloud server sub-module for storing data using cloud computing and the data wireless transmission sub-module for wireless data transmission. In this embodiment, the present invention uses cloud computing to store a large amount of data to ensure the security, scalability, and high availability of the data. The data wireless transmission sub-module transmits data through wireless communication technologies (such as Wi-Fi) to ensure that the data of each device within the park can be transmitted to the cloud server sub-module in a timely manner;

[0032] The data analysis module is used to analyze the operating data through machine learning algorithms. Specifically, the specific steps for analyzing the operating data through machine learning algorithms are as follows:

[0033] S1. Construct a predictive analysis model based on the multi-task learning algorithm, with the input data being the operating data and the output data being the power load prediction and device energy efficiency evaluation;

[0034] S2. Collect historical operating data, construct a data set, and train the predictive analysis model through the data set;

[0035] S3. Input the real-time collected operating data through the trained predictive analysis model to obtain the output result.

[0036] Furthermore, the predictive analysis model includes an input layer, a fully connected neural network layer, and an output layer. The input layer includes time information, environmental data, historical power load data, and operating data. Then, the fully connected neural network layer is used to extract shared features from the input data and learn the common information between different tasks. Finally, a specific result is output through the output layer.

[0037] Then, during the model training process, a data set is constructed through historical electricity consumption data, factors affecting power demand (such as weather, holidays, etc.), and data such as the power consumption, load, and efficiency of each device, and it is divided into a training set, a validation set, and a test set. Then, the data is normalized, and then the weights of the predictive analysis model are initialized, and the Adam optimizer is used as the optimization algorithm for iterative training. Finally, the model performance is evaluated on the validation set.

[0038] Subsequently, the trained predictive analysis model is utilized to input the collected operation data, and two results, namely power load prediction and equipment energy efficiency evaluation, are obtained.

[0039] The power intelligent scheduling module is used to intelligently adjust power distribution according to the analysis results. Specifically, it includes an intelligent scheduling sub-module for intelligent adjustment, a backup power supply switching sub-module for automatically switching the backup power supply, and a green energy mobilization sub-module for connecting green energy. For the intelligent mobilization sub-module, the specific distribution method is as follows:

[0040] A demand response strategy is constructed. Combining the power load prediction and energy efficiency evaluation results, and then introducing a reinforcement learning algorithm to optimize power scheduling and make real-time adjustments. The demand response strategy is that when the power demand in a certain time period is too high, the load of high-efficiency equipment is given priority to ensure, and the operation load of low-efficiency equipment is reduced.

[0041] Furthermore, for power scheduling optimization, its goal is to maximize the operation efficiency of the system (while ensuring stable power supply, minimizing unnecessary power consumption as much as possible. Through the energy efficiency evaluation of equipment, the load of equipment can be reasonably scheduled to avoid overusing low-efficiency equipment), reduce energy consumption (according to the results of load prediction, high-energy-consuming equipment can be selected to operate during periods with lower power prices (such as late at night), and avoid excessive consumption during peak power price periods), and ensure sufficient power supply in the park (by real-time monitoring of load distribution, preventing the power demand of any equipment or area from exceeding its capacity, thus avoiding power overload and equipment failures). The scheduling algorithm is calculated through a dynamic programming algorithm, using the dynamic programming algorithm to solve the optimal power distribution plan to ensure that power demand can be optimally scheduled at different time periods and maximize the operation efficiency of the system.

[0042] It is assumed that the smart park is divided into three main areas, namely the production area, the office area, and the leisure area. Then, through machine learning algorithms to analyze the operation data, the following power load predictions are obtained:

[0043] In the production area, the predicted power demand in the next 24 hours is 500 kWh;

[0044] In the office area, the predicted power demand in the next 24 hours is 150 kWh;

[0045] In the leisure area, the predicted power demand in the next 24 hours is 100 kWh.

[0046] The energy efficiency evaluation results are as follows:

[0047] In the production area, the equipment energy efficiency score is relatively high, and the equipment load is relatively uniform;

[0048] Office area, with medium equipment energy efficiency rating, and some old equipment needs to be optimized;

[0049] Leisure area, with relatively low equipment energy efficiency, but the power consumption priority in this area is low.

[0050] Correspondingly, the scheduling plan is as follows:

[0051] During peak hours (daytime), priority is given to ensuring power supply in the production area and office area. While during off-peak hours (nighttime), the equipment load in the leisure area is reduced, and non-critical equipment (such as air conditioners and lighting) will be reduced or suspended to reduce power consumption. When the load in the production area approaches the upper limit, backup power and green energy are activated to ensure stable power supply.

[0052] Specifically, in combination with power load forecasting and equipment energy efficiency assessment, the system can adjust power distribution according to the following principles during peak demand hours:

[0053] According to the energy efficiency assessment results, the load of high-efficiency equipment will be given priority, while the operation of low-efficiency equipment (such as old equipment) will be restricted or suspended.

[0054] For low-priority areas (such as the leisure area), during peak power demand, the equipment load is reduced, and non-critical equipment such as air conditioners and lighting can be reduced or suspended.

[0055] When the load approaches the upper limit, the system will automatically activate backup power (such as energy storage systems or generators) to ensure stable power supply.

[0056] Meanwhile, when the load demand is high, the system preferentially connects to green energy (solar energy) to reduce the consumption of traditional energy and lower carbon emissions.

[0057] It also includes a fault warning module, which includes a real-time fault monitoring sub-module for monitoring operation data and a warning notification sub-module for sending warning notifications. By monitoring the real-time operation status of each device in the power system, abnormal situations (such as overload, short circuit, voltage fluctuation, etc.) are detected. Once a device fault or abnormality is found, the warning notification sub-module sends a warning notification to notify the user to conduct inspections and maintenance.

[0058] It also includes a user interface and control module, which includes a user operation interface sub-module for displaying the system status, an operation control sub-module for user remote control, and a data report sub-module for generating energy usage reports. Correspondingly, through the user operation interface sub-module, the operation status of the system, the energy efficiency rating of equipment, power demand forecasting, load scheduling, etc. are displayed, facilitating real-time viewing by administrators. The operation control sub-module allows users to perform remote control, adjust the power scheduling plan, activate backup power, etc.

[0059] The foregoing has shown and described the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments, and what is described in the above embodiments and the specification is only to illustrate the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of the present invention claimed is defined by the appended claims and their equivalents.

Claims

1. An Internet-based intelligent park power management system, characterized in that: It includes a data acquisition module for acquiring the operation data of power-related equipment in the park; A data management module for processing and storing the acquired operation data; A data analysis module for analyzing the operation data through machine learning algorithms; A power intelligent scheduling module for intelligently adjusting power distribution according to the analysis results.

2. The intelligent park power management system based on the Internet according to claim 1, characterized in that: The data acquisition module includes a device sensor sub-module for monitoring the operation status of power-related equipment, an intelligent electricity meter sub-module for recording the power usage of power-related equipment, and an environmental monitoring sub-module for recording the temperature, humidity and wind speed in the park.

3. An Internet-based intelligent park power management system according to claim 1, characterized in that: The data management module includes a cloud server sub-module for storing data using cloud computing and a data wireless transmission sub-module for wireless data transmission.

4. An Internet-based intelligent park power management system according to claim 1, characterized in that: The specific steps for analyzing the operation data through machine learning algorithms are as follows: S1. Build a predictive analysis model based on a multi-task learning algorithm, with the input data being the operation data and the output data being power load prediction and equipment energy efficiency evaluation; S2. Collect historical operation data, build a data set, and train the predictive analysis model through the data set; S3. Input the operation data collected in real time through the trained predictive analysis model to obtain the output result.

5. The power management system for an intelligent park based on the Internet according to claim 1, characterized in that: The power intelligent scheduling module includes an intelligent scheduling sub-module for intelligent adjustment, a backup power supply switching sub-module for automatically switching the backup power supply, and a green energy mobilization sub-module for connecting green energy.

6. The intelligent park power management system based on the Internet according to claim 4, characterized in that: The specific method for intelligently adjusting power distribution is as follows: Build a demand response strategy, combine the power load prediction and energy efficiency evaluation results, then introduce a reinforcement learning algorithm to optimize power scheduling and make real-time adjustments. The demand response strategy is that when the power demand in a certain period is too high, give priority to ensuring the load of high-efficiency equipment and reduce the operation load of low-efficiency equipment.

7. The intelligent park power management system based on the Internet according to claim 1, characterized in that: It also includes a fault warning module, which includes a real-time fault monitoring sub-module for monitoring operation data and a warning notification sub-module for sending warning notifications.

8. An Internet-based intelligent park power management system according to claim 1, characterized in that: It also includes a user interface and control module, which includes a user operation interface sub-module for displaying the system status, an operation control sub-module for user remote control, and a data report sub-module for generating an energy usage report.

Images