Optimization method for smart energy management platform

Abstract

The present invention relates to the technical field of intelligent energy management, and discloses an optimization method for a smart energy management platform, including: connecting various types of energy equipment to a unified smart energy management platform through the LoRaWAN protocol, and using the IoT gateway to transmit the real-time collected equipment operating parameters; after data preprocessing the equipment operating parameters, extracting key features to form a feature data set; inputting the feature data set into an analysis model established based on a random forest algorithm to analyze the energy consumption requirements of the equipment; inputting the analysis results into a control model established based on a fuzzy control algorithm, and the control model is deployed on the smart energy management platform to optimize system performance by dynamically adjusting the operating parameters of the equipment. The present invention solves the problems of data acquisition delay, low prediction accuracy and unintelligent control strategy in the prior art, and significantly improves the efficiency and effect of smart energy management.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent energy management, and in particular to an optimization method for a smart energy management platform. Background Art

[0002] With the increasing demand for energy management, smart energy management platforms have become an important development direction for the energy industry. Traditional energy management systems mostly rely on manual operations and basic automation technologies, which make it difficult to cope with complex and changing energy demands.

[0003] In recent years, the rapid development of Internet of Things (IoT) technology has provided new opportunities for smart energy management. IoT technology can realize intelligent interconnection and data sharing of energy equipment, thereby improving the efficiency and accuracy of energy management. As a low-power wide area network protocol, LoRaWAN protocol has gradually become a popular choice in the field of energy management due to its long distance, low power consumption and high transmission efficiency. It can effectively connect various energy devices to a unified management platform for real-time data collection and transmission. At the same time, the application of advanced technologies such as big data analysis, machine learning and fuzzy control enables smart energy management systems to more accurately predict energy consumption needs, optimize energy configuration and achieve more efficient energy utilization.

[0004] Although the current smart energy management system has made certain progress, it still has many shortcomings. First, the traditional system has delays and instability problems in data collection and transmission, making it difficult to achieve real-time monitoring and dynamic adjustment. Second, the existing energy consumption prediction models mostly use simple statistical methods, which make it difficult to accurately capture complex changes in energy demand and have low prediction accuracy. Third, the system's control strategies are mostly based on preset rules, lacking intelligence and dynamic adjustment capabilities, making it difficult to cope with the changing energy usage environment.

[0005] In addition, the existing system lacks effective technical means in data processing and feature extraction, making it difficult to fully utilize the large amount of collected data for in-depth analysis; therefore, how to use advanced Internet of Things technology, big data analysis methods and intelligent control algorithms to improve the performance of smart energy management systems has become a hot topic and difficulty in current research. Summary of the invention

[0006] The purpose of this section is to summarize some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the abstract of the specification and the title of the invention of this application to avoid blurring the purpose of this section, the abstract of the specification and the title of the invention, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0007] In view of the above existing problems, the present invention is proposed.

[0008] Therefore, the technical problem solved by the present invention is that the existing smart energy management technology has problems such as data collection delay, low prediction accuracy and unintelligent control strategy.

[0009] In order to solve the above technical problems, the present invention provides the following technical solutions: various energy devices are connected to a unified smart energy management platform through the LoRaWAN protocol, and the real-time collected device operating parameters are transmitted using the IoT gateway;

[0010] After data preprocessing of the equipment operation parameters, key features are extracted to form a feature data set;

[0011] The characteristic data set is input into an analysis model established based on a random forest algorithm to analyze the energy consumption requirements of the equipment;

[0012] The analysis results are input into a control model established based on a fuzzy control algorithm. The control model is deployed on the smart energy management platform to optimize system performance by dynamically adjusting the operating parameters of the equipment.

[0013] As a preferred solution of the optimization method for the smart energy management platform described in the present invention, the equipment operating parameters at least include current, voltage, power, energy consumption, temperature, humidity, operating status and fault status.

[0014] As a preferred solution of the optimization method for the smart energy management platform described in the present invention, after data preprocessing of the equipment operation parameters, key features are extracted, including:

[0015] By performing data cleaning and standardization on the equipment operating parameters, the parameters are converted into unified numerical data;

[0016] Calculate the data characteristics at each time point through statistical analysis;

[0017] Through Fourier transform, the time domain data is converted to the frequency domain to extract the spectrum features;

[0018] Summarizing the data features and the spectrum features is the key feature;

[0019] The extracted key features are encoded using one-hot encoding to form a format that can be processed by subsequent calculations.

[0020] As a preferred solution of the optimization method for the smart energy management platform described in the present invention, the extracted key features are summarized into a feature matrix, that is, a feature data set is formed, wherein:

[0021] Each row represents the data of one collection period, and each column represents a feature.

[0022] As a preferred solution of the optimization method for the smart energy management platform described in the present invention, the analysis model performs an analysis process on the energy consumption demand of the equipment, which can be expressed by the following mathematical expression formula:

[0023]

[0024] Among them, E demand is the energy consumption requirement of the equipment, T is the upper limit of the time interval, I i (t) is the current of the ith device at time t, V i (t) is the voltage of the ith device at time t, P i (t) is the power of the i-th device at time t, α is the exponential parameter related to power, λ is the exponential attenuation coefficient of the effect of temperature on energy consumption, W i (t) is the temperature of the ith device at time t, κ is a smoothing parameter to avoid the denominator being zero, E j (t) is the energy consumption of the jth device at time t, μ is the smoothing parameter for normalization of energy consumption, σ is the normalization coefficient of the effect of humidity on energy consumption, T j (t) is the humidity of the jth device at time t, H j (t) is the operating status of the jth device at time t, F j (t) is the fault status of the jth device at time t, N is the number of devices considered, and M is the number of devices considered in the energy consumption calculation.

[0025] As a preferred solution of the optimization method for the smart energy management platform described in the present invention, the analysis result is E demand The output value, E demand The range of is non-negative real numbers, where:

[0026] When E demand When the value is 0, it means that the device has no energy consumption demand;

[0027] When E demand When the value is positive, it means that the energy demand of the device increases as the result value increases.

[0028] As a preferred solution of the optimization method for the smart energy management platform described in the present invention, the process of optimizing the control model by dynamically adjusting the operating parameters of the equipment can be expressed by the following mathematical expression formula:

[0029]

[0030] Among them, ΔP(t) is the dynamic adjustment value of the equipment power at time t, T is the upper limit of the time interval, and E demand (i,t) is the energy consumption requirement of the i-th device at time t, Ii (t) is the current of the ith device at time t, V i (t) is the voltage of the ith device at time t, P i (t) is the power of the ith device at time t, λ is the exponential attenuation coefficient of the effect of temperature on energy consumption demand, W i (t) is the temperature of the ith device at time t, κ is the smoothing parameter to avoid the denominator being zero, E j (t) is the energy consumption of the jth device at time t, μ is the smoothing parameter for normalization of energy consumption, σ1 is the normalization coefficient of the impact of operating status on energy consumption, H j (t) is the operating status of the jth device at time t, F j (t) is the fault status of the jth device at time t, N is the number of devices considered, and M is the number of devices considered in the energy consumption calculation.

[0031] As a preferred solution of the optimization method for the smart energy management platform described in the present invention, the dynamic adjustment is determined according to the numerical value of the dynamic adjustment value ΔP(t), and the value range of the dynamic adjustment value ΔP(t) is a real number set, representing the dynamic adjustment of the device power at time t, wherein:

[0032] When ΔP(t) is 0, it means that the equipment power does not need to be adjusted;

[0033] When ΔP(t) is a positive number, it means that the equipment needs to increase power;

[0034] When ΔP(t) is negative, it means the device needs to reduce power.

[0035] Beneficial effects of the present invention: The present invention realizes device interconnection and real-time data collection by using the LoRaWAN protocol, improves data quality by data preprocessing and feature extraction, performs energy consumption demand analysis by a random forest algorithm, and realizes dynamic adjustment of device operating parameters by a fuzzy control algorithm, thereby solving the problems of data collection delay, low prediction accuracy and unintelligent control strategy in the prior art, and significantly improving the efficiency and effect of smart energy management. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0037] Figure 1 It is a flow chart of the optimization method for the smart energy management platform shown in the present invention;

[0038] Figure 2 It is a schematic diagram of some parameters of the feature data set shown in the present invention. DETAILED DESCRIPTION

[0039] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, but not all of the embodiments.

[0040] Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without making any creative work should fall within the scope of protection of the present invention.

[0041] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0042] According to an embodiment of the present invention, Figure 1 The flowchart shown is an optimization method for a smart energy management platform, which specifically includes the following steps:

[0043] S1. Connect various energy devices to a unified smart energy management platform through the LoRaWAN protocol, and use the IoT gateway to transmit real-time collected device operating parameters;

[0044] S2. After data preprocessing of the equipment operation parameters, key features are extracted to form a feature data set;

[0045] S3, the feature data set is input into the analysis model established based on the random forest algorithm to analyze the energy consumption requirements of the equipment;

[0046] S4. Input the analysis results into the control model based on the fuzzy control algorithm. The control model is deployed on the smart energy management platform to optimize the system performance by dynamically adjusting the operating parameters of the equipment.

[0047] The following describes in more detail the implementation process and / or effects of certain embodiments of the present invention in conjunction with some preferred or optional examples of the present invention.

[0048] It should be further explained in the embodiments of the present invention that high-precision sensors, smart meters and LoRa modules are installed in various types of energy equipment, and sensors and smart meters are configured to ensure that the equipment operating parameters can be accurately collected and transmitted; LoRa nodes are arranged around the equipment, and each node includes a LoRa module and related sensors, which are responsible for collecting and transmitting data; ensure that the layout of LoRa nodes covers all energy equipment that needs to be monitored, and ensure the stability and effectiveness of signal transmission.

[0049] Among them, each LoRa node collects the operating parameters of the energy equipment in real time and transmits the data to the LoRa gateway through the LoRaWAN protocol. The LoRa gateway is responsible for receiving data from each node and performing preliminary processing (such as data filtering and correction); the processed data is uploaded to the central smart energy management platform through the IoT gateway; the IoT gateway selects devices that support multi-protocol conversion to ensure the effective transmission of different types of data. The management platform receives and stores all collected data, and uses big data analysis technology for real-time monitoring and analysis.

[0050] As an example, the device operating parameters include at least current, voltage, power, energy consumption, temperature, humidity, operating status, and fault status.

[0051] In an optional implementation, after data preprocessing of the equipment operating parameters, key features are extracted, including:

[0052] By cleaning and standardizing the equipment operating parameters, they are converted into unified numerical data;

[0053] Calculate the data characteristics at each time point through statistical analysis;

[0054] Through Fourier transform, the time domain data is converted to the frequency domain to extract the spectrum features;

[0055] Summarizing data features and spectrum features is the key feature;

[0056] The extracted key features are encoded using one-hot encoding to form a format that can be processed by subsequent calculations.

[0057] Reference Figure 2 ,The extracted key features are summarized into a feature matrix, i.e., a feature data set is formed, where each row represents the data of an acquisition cycle and each column represents a feature.

[0058] Preferably, the embodiment of the present invention connects various types of energy equipment to a unified smart energy management platform through the LoRaWAN protocol, achieves low-power, long-distance communication, ensures stable connection of energy equipment over a large range, and can collect and transmit equipment operating parameters such as current, voltage, and power in real time; and then uses the IoT gateway to transmit real-time data, further improving the efficiency and reliability of data transmission, solving the problems of data transmission delay and instability in traditional energy management systems, improving the real-time and accuracy of data collection, and thus providing strong support for the optimization of the smart energy management platform.

[0059] Preferably, data availability and analysis accuracy are enhanced through data standardization and feature extraction, and complex raw data are converted into structured feature data sets, providing a high-quality data foundation for subsequent energy consumption demand analysis, thereby improving the accuracy and reliability of the analysis model.

[0060] As an example, the analysis model performs an analysis on the energy consumption requirements of the equipment, which can be expressed by the following mathematical expression formula:

[0061]

[0062] Among them, E demand is the energy consumption requirement of the equipment, T is the upper limit of the time interval, I i (t) is the current of the ith device at time t, V i (t) is the voltage of the ith device at time t, P i (t) is the power of the i-th device at time t, α is the exponential parameter related to power, λ is the exponential attenuation coefficient of the effect of temperature on energy consumption, W i (t) is the temperature of the ith device at time t, κ is a smoothing parameter to avoid the denominator being zero, E j (t) is the energy consumption of the jth device at time t, μ is the smoothing parameter for normalization of energy consumption, σ is the normalization coefficient of the effect of humidity on energy consumption, T j (t) is the humidity of the jth device at time t, H j (t) is the operating status of the jth device at time t, F j (t) is the fault status of the jth device at time t, N is the number of devices considered, and M is the number of devices considered in the energy consumption calculation.

[0063] It should be noted that the analysis result is E demand The output value, E demand The range of is non-negative real numbers, where:

[0064] When E demand When the value is 0, it means that the device has no energy consumption demand;

[0065] When E demand When the value is positive, it means that the energy demand of the device increases as the result value increases.

[0066] Preferably, the random forest algorithm uses multiple decision trees for ensemble learning, which improves the generalization ability and prediction accuracy of the model, can accurately predict the energy consumption requirements of the equipment at different time points, and identify the key factors affecting energy consumption.

[0067] Preferably, energy consumption forecasting is performed through a data-driven approach, which improves the scientific nature of energy consumption management and the accuracy of decision-making. Through this analysis, accurate energy consumption demand data can be provided for subsequent control models, thereby achieving optimization of energy management.

[0068] As an example, the process of optimizing the control model by dynamically adjusting the operating parameters of the equipment can be expressed by the following mathematical expression formula:

[0069]

[0070] Among them, ΔP(t) is the dynamic adjustment value of the equipment power at time t, T is the upper limit of the time interval, and E demand (i,t) is the energy consumption requirement of the i-th device at time t, I i (t) is the current of the ith device at time t, V i (t) is the voltage of the ith device at time t, P i (t) is the power of the ith device at time t, λ is the exponential attenuation coefficient of the effect of temperature on energy consumption demand, W i (t) is the temperature of the ith device at time t, κ is the smoothing parameter to avoid the denominator being zero, E j (t) is the energy consumption of the jth device at time t, μ is the smoothing parameter for normalization of energy consumption, σ1 is the normalization coefficient of the impact of operating status on energy consumption, H j (t) is the operating status of the jth device at time t, F j (t) is the fault status of the jth device at time t, N is the number of devices considered, and M is the number of devices considered in the energy consumption calculation.

[0071] It should also be noted that the embodiment of the present invention is that the dynamic adjustment is determined according to the numerical value of the dynamic adjustment value ΔP(t), and the value range of the dynamic adjustment value ΔP(t) is a real number set, representing the dynamic adjustment of the device power at time t, where:

[0072] When ΔP(t) is 0, it means that the equipment power does not need to be adjusted;

[0073] When ΔP(t) is a positive number, it means that the equipment needs to increase power;

[0074] When ΔP(t) is negative, it means the device needs to reduce power.

[0075] Preferably, the fuzzy control algorithm can handle complex uncertainty problems and realize flexible adjustment of the equipment operating status. The control model is deployed on the smart energy management platform and can adjust the equipment operating parameters such as current, voltage, power, etc. in real time, thereby optimizing system performance.

[0076] Preferably, through intelligent control of energy equipment, the response speed and optimization effect of the system are improved, and dynamic adjustment of the operating status of the energy equipment is achieved, thereby achieving the purpose of energy saving and improving system stability.

[0077] The aforementioned data preprocessing, feature extraction and model training methods can be performed using methods and means in the prior art and will not be described in detail in this example.

[0078] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An optimization method for a smart energy management platform, characterized in that: include: Connect various energy devices to a unified smart energy management platform through the LoRaWAN protocol, and use the IoT gateway to transmit real-time collected device operating parameters; After data preprocessing of the equipment operation parameters, key features are extracted to form a feature data set; The characteristic data set is input into an analysis model established based on a random forest algorithm to analyze the energy consumption requirements of the equipment; The analysis model performs an analysis process on the energy consumption requirements of the equipment, which is expressed by the following mathematical expression formula: Among them, E demand is the energy consumption requirement of the equipment, T is the upper limit of the time interval, I i (t) is the current of the ith device at time t, V i (t) is the voltage of the ith device at time t, P i (t) is the power of the i-th device at time t, α is the exponential parameter related to power, λ is the exponential attenuation coefficient of the effect of temperature on energy consumption, W i (t) is the temperature of the ith device at time t, κ is a smoothing parameter to avoid the denominator being zero, E j (t) is the energy consumption of the jth device at time t, μ is the smoothing parameter for normalization of energy consumption, σ is the normalization coefficient of the effect of humidity on energy consumption, T j (t) is the humidity of the jth device at time t, H j (t) is the operating status of the jth device at time t, F j (t) is the fault status of the jth device at time t, N is the number of devices considered, and M is the number of devices considered in the energy consumption calculation; Input the analysis results into a control model established based on a fuzzy control algorithm, and the control model is deployed on the smart energy management platform to optimize system performance by dynamically adjusting the operating parameters of the equipment; The analysis result is E demand The output value, E demand The range of is non-negative real numbers, where: When E demand When the value is 0, it means that the device has no energy consumption demand; When E demand When the value is positive, it means that the energy demand of the device increases as the result value increases; The control model is optimized by dynamically adjusting the operating parameters of the equipment, which is expressed by the following mathematical formula: Among them, ΔP(t) is the dynamic adjustment value of the equipment power at time t, T is the upper limit of the time interval, and E demand (i,t) is the energy consumption requirement of the i-th device at time t, I i (t) is the current of the ith device at time t, V i (t) is the voltage of the ith device at time t, P i (t) is the power of the ith device at time t, λ is the exponential attenuation coefficient of the effect of temperature on energy consumption demand, W i (t) is the temperature of the ith device at time t, κ is a smoothing parameter to avoid the denominator being zero, and E j (t) is the energy consumption of the jth device at time t, μ is the smoothing parameter for normalization of energy consumption, σ1 is the normalization coefficient of the impact of operating status on energy consumption, H j (t) is the operating status of the jth device at time t, F j (t) is the fault status of the jth device at time t, N is the number of devices considered, and M is the number of devices considered in the energy consumption calculation; The dynamic adjustment is determined according to the numerical value of the dynamic adjustment value ΔP(t), the value range of which is a real number set, representing the dynamic adjustment of the device power at time t, where: When ΔP(t) is 0, it means that the equipment power does not need to be adjusted; When ΔP(t) is a positive number, it means that the equipment needs to increase power; When ΔP(t) is negative, it means the device needs to reduce power.

2. The optimization method for the smart energy management platform according to claim 1, characterized in that: The equipment operating parameters at least include current, voltage, power, energy consumption, temperature, humidity, operating status and fault status.

3. The optimization method for the smart energy management platform according to claim 1 or 2, characterized in that: After data preprocessing of the equipment operating parameters, key features are extracted, including: By performing data cleaning and standardization on the equipment operating parameters, the parameters are converted into unified numerical data; Calculate the data characteristics at each time point through statistical analysis; Through Fourier transform, the time domain data is converted to the frequency domain to extract the spectrum features; Summarizing the data features and the spectrum features is the key feature; The extracted key features are encoded using one-hot encoding to form a format that can be processed by subsequent calculations.

4. The optimization method for the smart energy management platform according to claim 3, characterized in that: The extracted key features are summarized into a feature matrix, that is, a feature data set is formed, where: Each row represents the data of one collection period, and each column represents a feature.

Images