Temporary electricity consumption identification, monitoring and management system based on the Internet of Things

Abstract

The present invention discloses a temporary electricity consumption identification, monitoring and management system based on the Internet of Things, and relates to the technical field of power monitoring and intelligent management. The system monitors and records the power consumption data of various types of power-consuming equipment in real time through Internet of Things sensors, extracts power demand characteristics and uses clustering algorithms to divide the equipment into primary equipment and secondary equipment. Load forecasting and analysis of primary equipment and secondary equipment are performed through a time series algorithm to determine peak load periods and stable power consumption periods. According to the power fluctuation characteristics and load fluctuation frequency characteristics, the power fluctuation adaptability index and stability interference index are calculated to evaluate the load adaptability and power consumption stability of the equipment. When the power fluctuation adaptability index of the primary equipment exceeds the set threshold, the power-off protection is automatically triggered, and when the stability interference index of the secondary equipment exceeds the threshold, the load is adjusted. Intelligent monitoring and dynamic adjustment of temporary power equipment are realized, and the safety and stability of the power system are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power monitoring and intelligent management, and in particular to a temporary power consumption identification, monitoring and management system based on the Internet of Things. Background Art

[0002] With the rapid development and application of Internet of Things technology, intelligent power management systems have become an important part of modern power networks. Especially in temporary power consumption scenarios, with the frequent development of social and economic activities, large-scale temporary power demand continues to increase. Traditional power management methods have been unable to meet the increasingly complex power demand and load scheduling, especially in scenarios such as construction, large-scale events, and temporary industrial projects. The uncertainty and volatility of power demand have brought great challenges to the power system. Therefore, the temporary power identification, monitoring and management system based on the Internet of Things came into being. By real-time monitoring of the status of power equipment and combining big data analysis technology, it can effectively classify, predict and monitor power equipment to ensure the stability, safety and efficiency of power consumption.

[0003] Existing temporary power management methods have some significant deficiencies. Existing temporary power management methods usually rely on static power demand or preset load to classify equipment, and fail to consider the dynamic changes of equipment load in different operation stages, resulting in inaccurate classification results, affecting subsequent power dispatch and resource allocation. Secondly, load forecasting methods mostly rely on historical data and cannot effectively cope with the frequently changing power demand in temporary power scenarios, and the accuracy of the forecast results is poor. The monitoring and intervention mechanism of the existing system is lagging and cannot respond to equipment load fluctuations in a timely manner, which may lead to overload or waste of power resources, especially during peak load periods. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a temporary electricity consumption identification, monitoring and management system based on the Internet of Things, which solves the problems of the above-mentioned background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a temporary electricity consumption identification, monitoring and management system based on the Internet of Things, including the following modules: an identification and classification module, a load prediction module, an abnormality monitoring module, and a safety management module; the identification and classification module is used to obtain scene electricity demand data, extract electricity demand characteristics, and divide the power-consuming equipment into primary equipment and secondary equipment through a clustering algorithm according to the electricity demand characteristics; the load prediction module is used to perform load prediction analysis on primary equipment and secondary equipment respectively through time series, and obtain the peak load period of primary equipment and the stable electricity consumption period of secondary equipment; the abnormality monitoring module is used to analyze the power consumption fluctuation characteristics and load fluctuation frequency characteristics according to the high load period data of the peak load period of the primary equipment, obtain the power fluctuation adaptability index, which is used to evaluate the load adaptability of the primary equipment, and perform abnormal interference analysis on the stability of power consumption according to the power consumption data of the stable power consumption period of the secondary equipment, and obtain the stability interference index, which is used to measure the power consumption stability of the secondary equipment; the safety management module is used to determine whether it is necessary to perform power-off protection on the primary equipment according to the power fluctuation adaptability index, and determine whether it is necessary to perform load adjustment on the secondary equipment according to the stability interference index.

[0006] Furthermore, the specific process of obtaining scene power demand data and extracting power demand characteristics is as follows: continuously collect real-time power data of each power-consuming device through the sensor equipment of the Internet of Things, record the power changes at time intervals, calculate the average and maximum power after removing abnormal values, and extract power demand characteristics; by analyzing the switching status of the power-consuming devices, calculate the cumulative operating time of each device in a specific time period, count the total working time of the equipment, and extract the working time characteristics; by collecting the switching frequency of the power-consuming devices, count the start and stop frequency of each device in a specific time period, and extract the working time characteristics; the power demand characteristics include power demand characteristics, working time characteristics and start and stop characteristics.

[0007] Furthermore, the specific process of dividing electrical equipment into primary equipment and secondary equipment through a clustering algorithm according to the characteristics of power demand is as follows: the power demand characteristics of each electrical equipment are constructed into a feature vector, and the feature vector is standardized; through the K-means clustering algorithm, two cluster numbers are set, namely the primary equipment clustering and the secondary equipment clustering; the standardized feature vector is input into the K-means clustering algorithm, the cluster center distribution value of each electrical equipment is calculated, and the equipment is divided into primary equipment and secondary equipment, where the primary equipment represents equipment with large power demand fluctuations, long working time and high switching frequency, and the secondary equipment represents equipment with stable power demand, short working time and low switching frequency.

[0008] Furthermore, the specific process of load forecasting and analyzing the primary equipment and the secondary equipment respectively through time series is as follows: the power consumption data of the primary equipment and the secondary equipment are monitored and recorded in real time through the Internet of Things sensor equipment, including the real-time power, switch status and working time of the equipment; according to the real-time data, the power consumption time series models of the primary equipment and the secondary equipment are constructed respectively through the long short-term memory network; the future load of the primary equipment and the secondary equipment is predicted through the constructed time series model, for the primary equipment, its peak load period is predicted; for the secondary equipment, its stable power consumption period is predicted; according to the load prediction results, the peak load period of the primary equipment and the stable power consumption period of the secondary equipment are determined.

[0009] Furthermore, the specific process of analyzing the power consumption fluctuation characteristics and load fluctuation frequency characteristics is as follows: based on the high-load period data of the peak load period of the first-level equipment, the power data in the high-load period is extracted, and the power fluctuation amplitude of each period is calculated by counting the power value at each time point, and the power consumption fluctuation characteristics of the equipment in the high-load period are evaluated; the power data in the high-load period is subjected to time series analysis to identify the periodicity and frequency of load changes, and the number of power changes per unit time, that is, the number of times the power value exceeds the set fluctuation range per unit time, is counted to obtain the frequency of load fluctuations and evaluate the load change characteristics of the equipment.

[0010] Furthermore, the specific process of obtaining the power fluctuation adaptability index is as follows: obtain the power fluctuation amplitude and load fluctuation frequency of each high-load period, and standardize the power fluctuation amplitude and load fluctuation frequency; perform weighted average on the standardized power fluctuation amplitude and load fluctuation frequency to obtain the power fluctuation adaptability index, which is used to evaluate the load adaptability of the equipment during the high-load period.

[0011] Furthermore, based on the power consumption data of the secondary equipment during the stable power consumption period, the specific process of conducting abnormal interference analysis on the stability of power consumption is as follows: extract the power data of the secondary equipment during the stable power consumption period, count the power values ​​in each time period, calculate the power fluctuation amplitude during the stable power consumption period, and evaluate the stability of the power fluctuation; conduct time series analysis on the power data during the stable power consumption period, identify abnormal power fluctuations, set a power fluctuation threshold, and regard fluctuations exceeding the threshold as abnormal interference; count the number of times the power value exceeds the set fluctuation threshold per unit time, and evaluate the stability of power consumption.

[0012] Furthermore, the specific process of obtaining the stability interference index is as follows: obtain the power fluctuation amplitude and the number of abnormal interferences of the secondary equipment during the stable power consumption period, calculate the standard deviation of the power fluctuation as the fluctuation stability index, calculate the frequency of abnormal interference per unit time, which is defined as the ratio of the number of times the power fluctuation threshold is exceeded per unit time to the total time; perform weighted synthesis of the fluctuation standard deviation and the abnormal interference frequency to obtain the stability interference index.

[0013] Furthermore, based on the power fluctuation adaptability index, the specific process of judging whether power-off protection is needed for the first-level equipment is as follows: obtain the power fluctuation adaptability index of each first-level equipment, set the power fluctuation adaptability threshold, and when the power fluctuation adaptability index exceeds the set power fluctuation adaptability threshold, it indicates that the load fluctuation of the equipment is large and there is a risk of affecting the stability of the power system, which means that the equipment needs power-off protection.

[0014] Furthermore, based on the stability interference index, the specific process of determining whether load adjustment of the secondary device is required is as follows: obtaining the stability interference index of each secondary device, setting a stability interference index threshold, when the stability interference index exceeds the set stability interference index threshold, it indicates that the power consumption stability of the device is poor, there are large fluctuations or interferences, which indicates that the device needs load adjustment.

[0015] The present invention has the following beneficial effects:

[0016] (1) The temporary power consumption identification, monitoring and management system based on the Internet of Things, the identification and classification module obtains the scene power demand data and extracts the power demand characteristics, and uses the clustering algorithm to accurately divide the power consumption equipment into primary equipment and secondary equipment. In this way, high-load and low-load equipment can be accurately identified according to the power demand characteristics of the equipment, providing a reliable basis for subsequent load prediction and resource allocation. The load prediction module can identify the peak load period and stable power consumption period in advance by performing time series analysis on the primary equipment and the secondary equipment respectively. This not only helps to accurately predict the changing trend of the equipment load, but also can make reasonable scheduling in the actual power consumption process to avoid equipment overload or power waste, thereby improving the utilization efficiency of power resources and the stability of the system.

[0017] (2) The temporary power consumption identification, monitoring and management system based on the Internet of Things, the abnormal monitoring module can generate a power fluctuation adaptability index by analyzing the fluctuation characteristics and frequency characteristics of the power data of the first-level equipment during the peak load period, and effectively evaluate the load adaptability of the equipment during the high-load period. This process helps to identify potential power fluctuation risks in advance and ensure the safety of equipment operation. For the second-level equipment, the module will analyze its power consumption data during the stable power consumption period, identify and count abnormal interference, and obtain the stability interference index, thereby measuring the stability of the equipment's power consumption. This enables the system to monitor the operating status of the equipment in real time, detect abnormal fluctuations in time and intervene. The safety management module will power off the first-level equipment according to the power fluctuation adaptability index to avoid safety hazards caused by overload; at the same time, the load of the second-level equipment will be adjusted according to the stability interference index to ensure the overall stability and safety of the power system.

[0018] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 This is a flow chart of the temporary electricity consumption identification, monitoring and management system based on the Internet of Things of the present invention. DETAILED DESCRIPTION

[0020] The embodiment of the present application solves the problems of large load fluctuations, inefficient energy utilization and high risk of equipment overload during the use of temporary power equipment through a temporary power identification, monitoring and management system based on the Internet of Things. The system effectively optimizes the power dispatch of equipment by accurately identifying and classifying power equipment and combining time series analysis for load forecasting; at the same time, through abnormal monitoring and power fluctuation adaptability analysis, it timely detects abnormal conditions of equipment and provides safety management measures, thereby improving the stability and safety of the power system, reducing energy waste and reducing the risk of the power system.

[0021] The overall idea of ​​the solution in the embodiments of this application is as follows:

[0022] Obtain scene power demand data, extract power demand characteristics, and classify power-consuming devices into primary devices and secondary devices through clustering algorithms based on the power demand characteristics.

[0023] Through time series, load forecasting analysis is performed on primary equipment and secondary equipment respectively to obtain the peak load period of primary equipment and the stable power consumption period of secondary equipment.

[0024] Based on the high-load period data of the primary equipment during the peak load period, the power consumption fluctuation characteristics and load fluctuation frequency characteristics are analyzed to obtain the power fluctuation adaptability index, which is used to evaluate the load adaptability of the primary equipment. Based on the power consumption data of the secondary equipment during the stable power consumption period, the stability of power consumption is analyzed for abnormal interference, and the stability interference index is obtained to measure the stability of power consumption of the secondary equipment.

[0025] Based on the power fluctuation adaptability index, determine whether the primary equipment needs to be powered off for protection, and based on the stability interference index, determine whether the secondary equipment needs to be load adjusted.

[0026] See also Figure 1 The embodiment of the present invention provides a technical solution for a temporary power consumption identification, monitoring and management system based on the Internet of Things, including the following modules: an identification and classification module, a load prediction module, an abnormality monitoring module, and a safety management module; the identification and classification module is used to obtain scene power demand data, extract power demand characteristics, and classify power-consuming devices into primary devices and secondary devices according to the power demand characteristics through a clustering algorithm; the load prediction module is used to perform load prediction analysis on primary devices and secondary devices respectively through time series, and obtain the peak load period of primary devices and the stable power consumption period of secondary devices; the abnormality monitoring module is used to analyze the power consumption fluctuation characteristics and the load fluctuation frequency characteristics according to the high load period data of the peak load period of the primary devices, obtain the power fluctuation adaptability index, which is used to evaluate the load adaptability of the primary devices, and perform abnormal interference analysis on the stability of power consumption according to the power consumption data of the stable power consumption period of the secondary devices, and obtain the stability interference index, which is used to measure the power consumption stability of the secondary devices; the safety management module is used to determine whether it is necessary to perform power-off protection on the primary devices according to the power fluctuation adaptability index, and determine whether it is necessary to perform load adjustment on the secondary devices according to the stability interference index.

[0027] In this implementation scheme, the identification and classification module: This module is responsible for obtaining the scene power demand data and extracting the power demand characteristics from it. Based on these characteristics, the module uses a clustering algorithm (such as K-means clustering) to divide the power-consuming equipment into primary equipment and secondary equipment. Clustering algorithm: It is an unsupervised learning algorithm that groups the similarity of data so that the devices in the same group are more similar in certain characteristics, thereby realizing automatic classification of equipment. Primary equipment: It is usually equipment with large power demand fluctuations and a greater impact on power distribution, such as industrial equipment, high-power machines, etc. Secondary equipment: Equipment with relatively stable power demand and less impact on power distribution, such as small household appliances. Load prediction module: Based on historical power consumption data, this module predicts the load of primary equipment and secondary equipment respectively through time series analysis, and obtains peak load periods (primary equipment) and stable power consumption periods (secondary equipment). Time series analysis: By modeling the time series of historical power consumption data of the equipment, the power load fluctuation in the future period is predicted. Peak load period: refers to the period when the power demand of the primary equipment reaches the highest. These periods are usually critical periods when the equipment load is large and prone to overload or increased pressure on the power system. Stable power consumption period: refers to the period when the power demand of the secondary equipment changes less and is more stable, which is usually not easy to cause system fluctuations. Abnormal monitoring module: This module evaluates the fluctuation characteristics of its power consumption and the load fluctuation frequency characteristics by analyzing the power data of the peak load period of the primary equipment and the stable power consumption period of the secondary equipment. Power consumption fluctuation characteristics: refers to the fluctuation amplitude of the power demand of the equipment in a certain period of time. Generally, equipment with large fluctuations may affect the stability of the system. Load fluctuation frequency characteristics: refers to the number of power changes per unit time. For example, frequent switching on and off of equipment in a short period of time or load fluctuations may cause unstable load in the power system. Power fluctuation adaptability index: Based on the power fluctuation data of the primary equipment, the load adaptability of the equipment is evaluated. The larger the index value, the stronger the ability of the equipment to adapt to large load fluctuations. Stability interference index: Based on the power fluctuation data of the secondary equipment, the stability of its power consumption is evaluated. A higher index value indicates that the power consumption of the equipment is relatively unstable and there may be abnormal interference. When power consumption anomalies are detected, the IoT sensor will immediately feed back the data to the system. Abnormal power consumption is fed back to AR glasses: When the sensor detects an abnormality in the device (power limit exceeded, wiring error, unstable load), the abnormal monitoring module will feed back the abnormal information to the AR glasses module. Based on the feedback information received, the AR glasses display the abnormality type, device location, and safety tips that need attention. Specific feedback information includes but is not limited to: Power consumption fluctuations: Real-time monitoring of whether the power fluctuation of the device exceeds the preset threshold. Incorrect or irregular wiring: Through visual recognition technology, AR glasses will directly display warnings of incorrect or irregular wiring locations. Abnormal load prompts: Display the power consumption status of the device, the time period when abnormal load occurs, and recommended safety measures.Functions of the safety management module: This module determines whether corresponding safety protection measures need to be taken based on the power fluctuation adaptability index and stability interference index obtained above. Power-off protection: Based on the power fluctuation adaptability index of the first-level equipment, determine whether the equipment has excessive load fluctuations. If it exceeds the set threshold, the power-off protection mechanism will be triggered to prevent equipment damage or power system failure. Load adjustment: Based on the stability interference index of the second-level equipment, determine whether the equipment has unstable load. If the index value is too high, the load of the equipment will be adjusted to reduce its interference with the power system and ensure a stable supply of electricity.

[0028] Specifically, the specific process of obtaining scene power demand data and extracting power demand characteristics is as follows: continuously collect real-time power data of each power-consuming device through the sensor equipment of the Internet of Things, record the power changes at time intervals, calculate the average and maximum power after removing abnormal values, and extract power demand characteristics; by analyzing the switching status of the power-consuming equipment, calculate the cumulative operating time of each device in a specific time period, count the total working time of the equipment, and extract the working time characteristics; by collecting the switching frequency of the power-consuming equipment, count the start and stop frequency of each device in a specific time period, and extract the working time characteristics; power demand characteristics, including power demand characteristics, working time characteristics and start and stop characteristics.

[0029] In this implementation scheme, power demand characteristics are extracted: the sensor devices (power meters, current sensors) in the Internet of Things system continuously collect real-time power data for each power-consuming device. The sensor will record the power change data of the device at a certain time interval (such as every second, every minute), and these data represent the power consumption of the device at different time points. Abnormal value removal: The collected data may contain some abnormal values ​​caused by equipment failure, data transmission errors, etc., so it is necessary to remove these abnormal values ​​that do not conform to normal rules through data cleaning technology to ensure the accuracy of the data. Calculate the average and maximum value of power: After removing the data of abnormal values, further calculate the average and maximum value of power in each time period. The average power value can represent the overall power consumption level of the device over a period of time, while the maximum power value can reflect the high load period that may occur during the operation of the device. Through these data, an accurate basis can be provided for subsequent equipment load analysis. Extraction of working time characteristics: Equipment switch state analysis: This step mainly analyzes the switch state of the device. The switch state of the device can be collected in real time through sensors in the Internet of Things system (such as state sensors, switch sensors, etc.). When the device is in the on state, the sensor will record the state, otherwise it will be recorded as the off state. Cumulative running time: According to the on / off status of the device, the cumulative running time of each device in a specific time period is counted. For example, if the on / off status of the device in a certain time period is on, the running time of the device can be accumulated and calculated to reflect the activity level of the device. Extraction of start and stop frequency features: Start and stop frequency analysis: Monitor the start and stop frequency of the device through IoT sensors. Each time the device is switched on and off, it will be recorded as a start or stop event in the system. By counting the number of starts and stops of the device in a specific time period, the switching frequency of the device can be understood. This information helps to evaluate the operating mode of the device, especially whether the device is frequently switched on and off and the load fluctuates greatly. Frequency statistics: Count the number of times each device is started and stopped within a period of time. This statistical result can reflect the operating rules of the equipment and possible load fluctuations, especially when the equipment is frequently switched on and off, which may have an impact on the power system.

[0030] Specifically, the specific process of dividing electrical equipment into primary equipment and secondary equipment through a clustering algorithm according to power demand characteristics is as follows: the power demand characteristics of each electrical equipment are constructed into a feature vector, and the feature vector is standardized; through the K-means clustering algorithm, two cluster numbers are set, namely, primary equipment clustering and secondary equipment clustering; the standardized feature vector is input into the K-means clustering algorithm, and the cluster center distribution value of each electrical equipment is calculated, and the equipment is divided into primary equipment and secondary equipment, where the primary equipment represents equipment with large power demand fluctuations, long working time and high switching frequency, and the secondary equipment represents equipment with stable power demand, short working time and low switching frequency.

[0031] In this implementation, the process of classifying electrical equipment into primary equipment and secondary equipment by clustering algorithm based on power demand characteristics first uses K-means clustering algorithm to classify electrical equipment. The following is a detailed explanation of the process. Construction and standardization of feature vectors: The power demand characteristics of each electrical equipment (such as power demand, working hours, start and stop frequency, etc.) are first extracted and converted into a feature vector. The feature vector of each device is ,in: Indicates the device Power demand characteristics (such as maximum power value or average power); Indicates the device Working time characteristics (such as cumulative working hours); Indicates the device The start and stop frequency characteristics (such as the number of starts per unit time) of each device. Since these characteristics usually have different dimensions and ranges, the feature vector of each device needs to be standardized. The standardization process converts each feature into a form with a mean of zero and a standard deviation of one. The standardization formula is as follows: ;in, Yes Equipment No. eigenvalues, It is The mean of the features, It is The standard deviation of the feature, is the standardized feature value. K-means algorithm: K-means is an unsupervised learning algorithm used to divide the data set into Clusters, each of which is represented by a cluster center (i.e., the centroid of the cluster). The goal of the algorithm is to minimize the sum of the distances from the data points to the cluster centers to which they belong, thereby achieving effective data partitioning. Setting the number of clusters: According to the requirements, this system sets the number of clusters , that is, the electrical devices are divided into two categories: primary devices and secondary devices. Calculation of cluster center assignment value: Calculation of cluster center: First, randomly select two devices as the initial cluster centers and ,Then, according to the distance of the feature vector (usually Euclidean distance), other devices are assigned to the cluster center closest to them. Euclidean distance calculation: The feature vector of each power-consuming device The distance from each cluster center It can be calculated by the following formula: ;in: Yes Equipment To cluster center The Euclidean distance of Yes Equipment No. standardized eigenvalues; is the cluster center In the The value of the dimension; is the dimension of the feature vector (in this case, 3, corresponding to power demand, working time, and start-stop frequency, respectively). Cluster allocation: According to the distance between each device and the two cluster centers, the nearest cluster center is selected and the device is allocated to the corresponding cluster. At this time, the cluster center allocation value of the device is: ; That is, select the cluster center that minimizes the distance As a device Cluster center. Classification results: Level 1 equipment: After cluster analysis, the characteristics of level 1 equipment are large fluctuations in power demand, long working hours, and high switching frequency. These devices usually have high energy consumption and frequent start and stop requirements, so they are classified as level 1 equipment. Level 2 equipment: On the contrary, level 2 equipment is characterized by stable power demand, short working hours, and low switching frequency. This type of equipment is usually used to maintain the stable operation of the system and will not start and stop frequently, so it is classified as level 2 equipment.

[0032] Specifically, the specific process of load forecasting and analysis for primary equipment and secondary equipment respectively through time series is as follows: use IoT sensor devices to monitor and record the power consumption data of primary equipment and secondary equipment in real time, including the real-time power, switch status and working time of the equipment; based on the real-time data, construct power consumption time series models of primary equipment and secondary equipment respectively through long short-term memory networks; predict the future load of primary equipment and secondary equipment through the constructed time series model, for primary equipment, predict its peak load period; for secondary equipment, predict its stable power consumption period; according to the load prediction results, determine the peak load period of primary equipment and the stable power consumption period of secondary equipment.

[0033] In this implementation scheme, real-time data collection: the power consumption data of the primary and secondary devices are monitored in real time through IoT sensor devices. These data include the real-time power of the device, the switch status (such as whether the device is turned on or off), and the working time of the device. This information provides basic data for subsequent load prediction. Constructing a time series model: Using the collected real-time data, a long short-term memory network (LSTM) is used to construct a time series model. LSTM is a special neural network that is particularly suitable for processing data with long-term dependencies, which enables it to capture long-term trends and periodic changes in device power consumption. For primary devices, the LSTM model will learn the change pattern of their power consumption, especially focusing on the high-load period of the device, that is, the period when the power demand of the device fluctuates greatly. For secondary devices, the LSTM model will analyze the stability of their power consumption, focusing on predicting the period when the power fluctuation of the device is small and relatively stable. Load prediction: Using the trained LSTM model, the system can predict the future power consumption of the device based on historical data. For primary devices, the model mainly predicts its peak load period in the future, that is, the period when the device may be overloaded or have large power fluctuations. For secondary devices, the model predicts its stable power consumption period, that is, the period when the power demand is relatively stable. In this way, the system can identify the high load and stable load periods of the equipment in advance during actual operation, so as to carry out targeted power dispatch and management. Application of results: Based on the load prediction results, the system can judge and optimize the allocation of power resources. For example, the peak load period of the first-level equipment can be warned in advance to avoid overload operation of the equipment or instability of the power system; while the stable load period of the second-level equipment can be used for equipment optimization management to ensure that the equipment operates smoothly without causing power fluctuations.

[0034] Specifically, the specific process of analyzing the power consumption fluctuation characteristics and load fluctuation frequency characteristics is as follows: based on the high-load period data of the peak load period of the first-level equipment, the power data in the high-load period is extracted, and the power fluctuation amplitude of each period is calculated by counting the power value at each time point, and the power consumption fluctuation characteristics of the equipment in the high-load period are evaluated; the power data in the high-load period is subjected to time series analysis to identify the periodicity and frequency of load changes, and the number of power changes per unit time is counted, that is, the number of times the power value exceeds the set fluctuation range per unit time, the frequency of load fluctuation is obtained, and the load change characteristics of the equipment are evaluated.

[0035] In this implementation scheme, the evaluation of the power fluctuation amplitude: Data extraction: First, analyze the high-load period data of the primary equipment during the peak load period. The high-load period refers to the period when the power consumption of the equipment is large, usually the highest load state when the equipment is running. From the data of these high-load periods, extract the power data in the corresponding period, which are usually the power consumption values ​​of the equipment at each time point. Calculate the power fluctuation amplitude: After extracting the power data of the high-load period, the system will count the power value at each time point. Common statistical methods include calculating the average power, maximum power, minimum power and other indicators of each period. By calculating the change amplitude of these power data, the power fluctuation amplitude can be obtained, that is, the maximum change in power value per unit time. The larger the fluctuation amplitude, the more drastic the fluctuation of the power consumption of the equipment. Evaluate the power consumption fluctuation characteristics: When evaluating the power consumption fluctuation characteristics of the equipment during the high-load period, focus on whether the fluctuation amplitude is within a reasonable range. If the fluctuation amplitude is too large, it may mean that the working state of the equipment is unstable and needs to be adjusted or inspected. Analysis of load fluctuation frequency: Timing analysis: Perform timing analysis on power data during high-load periods, that is, observe the pattern of power changes over time and analyze the periodicity and regularity of power changes. Timing analysis can help identify the trend of load changes and is the basis for identifying the frequency of load fluctuations. Statistical load fluctuation frequency: Load fluctuation frequency refers to the frequency of changes in the power value of the device per unit time. In order to calculate this frequency, the system sets a fluctuation range, that is, the range in which power changes are considered normal fluctuations. The system counts how many times the power value exceeds the set fluctuation range per unit time. This number can be used as the frequency of load fluctuations. For example, if the power value of the device frequently exceeds the set fluctuation range within a certain period of time, the load fluctuation frequency will be high, indicating that the load changes of the device are relatively frequent. Evaluate the characteristics of device load changes: The high or low frequency of load fluctuations can reflect the stability of the device load. If the frequency is high, it means that the load of the device fluctuates frequently during the high-load period, and there may be unstable factors. If the frequency is low, it means that the load changes of the device are relatively stable.

[0036] Specifically, the specific process of obtaining the power fluctuation adaptability index is as follows: obtain the power fluctuation amplitude and load fluctuation frequency of each high load period, and standardize the power fluctuation amplitude and load fluctuation frequency; perform weighted average on the standardized power fluctuation amplitude and load fluctuation frequency to obtain the power fluctuation adaptability index, which is used to evaluate the load adaptability of the equipment during the high load period.

[0037] In this implementation scheme, the calculation formula of the power fluctuation adaptability index is: ;Formula explanation: It is an index of adaptability to power fluctuations, used to evaluate the load adaptability of equipment during high-load periods. It is the value of the power fluctuation amplitude after normalization, indicating the fluctuation intensity of the device power. Normalization is performed by mapping the actual power fluctuation amplitude to the [0,1] interval. The formula is as follows: ;in, is the actual power fluctuation amplitude, and are the minimum and maximum values ​​of the power fluctuation amplitude respectively. It is the value after the load fluctuation frequency is standardized, indicating the number of times the power exceeds the set fluctuation range per unit time. The standardization process is the same as the power fluctuation amplitude: ;in, is the actual load fluctuation frequency, and are the minimum and maximum values ​​of the load fluctuation frequency respectively. is the weight of the impact of the power fluctuation amplitude on the adaptability index, indicating that the greater the power fluctuation, the higher the risk of poor device adaptability; is the impact weight of load fluctuation frequency. Frequent load fluctuations will increase the instability of the power system. They are the adjustment items for power fluctuation amplitude and load fluctuation frequency, which play the role of balancing and correcting the impact of small fluctuations. and load fluctuation frequency The relative impact on the power fluctuation adaptability index. The sum of the weighted coefficients is usually normalized to 1, that is, . Feature processing: For power fluctuation amplitude , we used a square treatment term , to emphasize the impact of larger fluctuations on the adaptability index. , using cubic processing terms , which makes the impact of devices with large frequency changes on the adaptability index more significant. At the same time, the logarithmic term is introduced ,This term has a mitigating effect on small fluctuations, preventing devices with smaller fluctuations from having too much impact on the index. In order to better handle the frequency term, the square root term is also used , which makes the impact of devices with lower load fluctuation frequency on the adaptability index smoother.

[0038] Specifically, based on the power consumption data of the secondary equipment during the stable power consumption period, the specific process of abnormal interference analysis on the stability of power consumption is as follows: extract the power data of the secondary equipment during the stable power consumption period, count the power values ​​in each time period, calculate the power fluctuation amplitude during the stable power consumption period, and evaluate the stability of power fluctuations; perform time series analysis on the power data during the stable power consumption period, identify abnormal power fluctuations, set a power fluctuation threshold, and regard fluctuations exceeding the threshold as abnormal interference; count the number of times the power value exceeds the set fluctuation threshold per unit time, and evaluate the stability of power consumption.

[0039] In this implementation scheme, power data is extracted: First, power data is extracted from the stable power consumption period of the secondary device. These data are real-time power consumption data of the device over a period of time, which are used for subsequent analysis. Statistical power value: The extracted power data is statistically analyzed to analyze its power changes in different time periods. This step mainly helps to evaluate the basic pattern of power consumption of the device by calculating the average power value and the maximum power value in different time periods. Calculate the power fluctuation amplitude: Next, calculate the amplitude of power fluctuation in the stable power consumption period. The power fluctuation amplitude refers to the range of change of the power consumption of the device in a specific time period, which can help to judge the stability of the device in normal operation. If the power fluctuation is large, it indicates that there is a large instability in the power consumption of the device. Timing analysis and abnormal fluctuation identification: Through the timing analysis of power data, the abnormal situation of power fluctuation is identified. In this process, the power change of the device is monitored moment by moment to identify whether there is abnormal fluctuation. Abnormal fluctuation refers to the fluctuation of the power value exceeding the normal working range, which may be caused by equipment failure, load change or other external factors. Set the fluctuation threshold: In order to determine which fluctuations belong to abnormal interference, a power fluctuation threshold needs to be set. When the power fluctuation exceeds this threshold, it is regarded as abnormal interference. These thresholds are usually set based on historical data or device performance standards. Count the number of times the threshold value is exceeded: Finally, count the number of times the power value exceeds the set fluctuation threshold value per unit time. This statistical value can be used to measure the stability of the device's power consumption. If the number of times the threshold value is exceeded is high, it means that the power consumption of the device fluctuates greatly during this period, and there is a risk of instability or abnormality.

[0040] Specifically, the specific process of obtaining the stability interference index is as follows: obtain the power fluctuation amplitude and the number of abnormal interferences of the secondary equipment during the stable power consumption period, calculate the standard deviation of the power fluctuation as the fluctuation stability index, and calculate the frequency of abnormal interference per unit time, which is defined as the ratio of the number of times the power fluctuation threshold is exceeded per unit time to the total time; perform weighted synthesis of the fluctuation standard deviation and the abnormal interference frequency to obtain the stability interference index.

[0041] In this implementation, the stability interference index formula is: ;Parameter explanation: The weighting coefficient of the power fluctuation standard deviation reflects the importance of power fluctuation in the final index. and The stability interference index indicates the stability of power consumption of secondary equipment during the stable power consumption period. The higher the value, the more unstable the power consumption of the equipment. . The weighting coefficient of abnormal interference frequency reflects the importance of abnormal interference frequency in the final index. and . During the stable power consumption period The power value at a certain moment, indicating the power consumption of the device at a certain point in time The average value of power values ​​during the stable power consumption period is used to calculate the standard deviation of power fluctuations. The number of data points during the stable power consumption period, that is, the number of time points at which the power values ​​were recorded. The number of times the power fluctuation threshold is exceeded within a unit time indicates the number of times abnormal interference occurs. Total time, that is, the total time period analyzed, is used to calculate the frequency of abnormal interference per unit time. Key points of the calculation process: Standard deviation of power fluctuation: reflects the difference between the power value and the average value. The larger the standard deviation, the more violent the fluctuation and the poorer the stability of the equipment. Abnormal interference frequency: measures the number of times the power fluctuation exceeds the threshold per unit time. Frequent abnormal interference means poor stability of the power consumption of the equipment. Weighting coefficient: through the weighting coefficient and The importance of the standard deviation of power fluctuation and abnormal interference frequency in the final stability interference index is controlled. According to the actual situation, these two coefficients will be adjusted to meet the stability requirements of different devices.

[0042] Specifically, according to the power fluctuation adaptability index, the specific process of judging whether it is necessary to perform power-off protection on the first-level equipment is as follows: obtain the power fluctuation adaptability index of each first-level equipment, set the power fluctuation adaptability threshold, when the power fluctuation adaptability index exceeds the set power fluctuation adaptability threshold, it means that the load fluctuation of the equipment is large and there is a risk of affecting the stability of the power system, which means that the equipment needs to be powered off for protection.

[0043] In this implementation scheme, the power fluctuation adaptability index is obtained: data is extracted from the power fluctuation adaptability index of each primary device to reflect the load fluctuation characteristics of the device during high-load periods. The higher the index, the greater the load fluctuation of the device, which may pose a threat to the stability of the power system. Set the power fluctuation adaptability threshold: In order to determine whether power off protection is needed, it is necessary to set a "threshold" value, that is, a standard fluctuation adaptability indicator. Compare with the threshold: When the power fluctuation adaptability index of a primary device exceeds this threshold, it means that the load fluctuation of the device is too large and may have a negative impact on the stability of the power system. Power off protection decision: If the power fluctuation adaptability index exceeds the threshold, it means that the device needs power off protection to prevent the device.

[0044] Specifically, based on the stability interference index, the specific process of judging whether it is necessary to perform load adjustment on the secondary device is as follows: obtain the stability interference index of each secondary device, set the stability interference index threshold, and when the stability interference index exceeds the set stability interference index threshold, it indicates that the power consumption stability of the device is poor, and there are large fluctuations or interferences, which means that the device needs to perform load adjustment.

[0045] In this implementation scheme, the stability interference index is obtained: First, the system extracts the stability interference index from each secondary device, which reflects the power fluctuation of the device during the stable power consumption period and its abnormal interference frequency. The higher the index, the more unstable the power consumption of the device is, and the greater the possibility of fluctuation and interference. Set the stability interference index threshold: In order to solve the situation of unstable power consumption of the device, this is a standard indicator used to distinguish between normal and abnormal stability. The threshold is determined by analyzing the stability requirements of the device. Comparison with the threshold: When the stability interference index of a secondary device exceeds the set threshold, it indicates that the power consumption stability of the device is poor, and there may be large fluctuations or abnormal interference. At this time, the unstable power consumption of the device may affect the normal operation of other devices and even cause system-level problems. Load adjustment decision: If the stability interference index exceeds the set threshold, the system will determine that the device needs to be load adjusted to balance its power consumption fluctuations and reduce the risks caused by interference and fluctuations, thereby ensuring the stability of the device and the system. Load adjustment can be achieved by reducing load, optimizing load distribution, or other means.

[0046] In summary, this application has at least the following effects:

[0047] The temporary power identification, monitoring and management system based on the Internet of Things can obtain and monitor the power demand and load of various types of power-consuming equipment in real time through the system based on the Internet of Things, realize the automatic identification and classification of power-consuming equipment, so as to manage temporary power demand more accurately and improve the intelligent use of power resources. Through time series analysis, the load of primary and secondary equipment can be accurately predicted, helping the system to effectively identify the peak load period and stable power consumption period of the equipment, thereby providing a scientific basis for load management and scheduling. Through in-depth analysis of the power consumption fluctuation characteristics and load fluctuation frequency, it can timely identify abnormal conditions in the operation of the equipment, quantify its fluctuation adaptability and stability, and prevent safety hazards caused by excessive equipment fluctuations or unstable power consumption. Through the power fluctuation adaptability index and stability interference index, the system can intelligently judge whether there are potential risks in the equipment and take necessary safety measures, such as power-off protection for primary equipment or load adjustment for secondary equipment, so as to ensure the safety and stability of equipment operation and ensure the overall stable operation of the power system. The temporary power identification, monitoring and management system based on the Internet of Things, through these intelligent monitoring and management mechanisms, can optimize the power consumption of equipment, reduce unnecessary energy waste, and improve the efficiency and reliability of the power system under the premise of ensuring safety.

[0048] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0049] The present invention is described with reference to flowcharts and / or block diagrams of systems, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0050] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0051] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0052] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0053] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. The temporary electricity consumption identification, monitoring and management system based on the Internet of Things is characterized by: It includes the following modules: identification and classification module, load prediction module, abnormality monitoring module, and safety management module; The identification and classification module is used to obtain scene power demand data, extract power demand characteristics, and classify power-consuming devices into primary devices and secondary devices through a clustering algorithm according to the power demand characteristics; The load prediction module is used to perform load prediction analysis on the primary equipment and the secondary equipment respectively through time series to obtain the peak load period of the primary equipment and the stable power consumption period of the secondary equipment; The abnormal monitoring module is used to analyze the power consumption fluctuation characteristics and load fluctuation frequency characteristics according to the high load period data of the primary equipment during the peak load period, and obtain the power fluctuation adaptability index, which is used to evaluate the load adaptability of the primary equipment, and to analyze the stability of power consumption according to the power consumption data of the secondary equipment during the stable power consumption period, and obtain the stability interference index, which is used to measure the stability of power consumption of the secondary equipment; The safety management module is used to determine whether it is necessary to perform power-off protection on the primary equipment according to the power fluctuation adaptability index, and to determine whether it is necessary to perform load adjustment on the secondary equipment according to the stability interference index; The specific process of obtaining the power fluctuation adaptability index is as follows: Obtain the power fluctuation amplitude and load fluctuation frequency during each high-load period, and perform standardization on the power fluctuation amplitude and load fluctuation frequency; The power fluctuation amplitude and load fluctuation frequency after normalization are weighted averaged to obtain the power fluctuation adaptability index, which is used to evaluate the load adaptability of the equipment during high-load periods. The specific process of obtaining the stability interference index is as follows: Obtain the power fluctuation amplitude and abnormal interference frequency of the secondary equipment during the stable power consumption period, calculate the standard deviation of the power fluctuation as the fluctuation stability index, and calculate the frequency of abnormal interference per unit time, which is defined as the ratio of the number of times the power fluctuation threshold is exceeded per unit time to the total time; The fluctuation standard deviation and abnormal interference frequency are weighted and integrated to obtain the stability interference index; The stability interference index formula is as follows: Parameter explanation: w p : Weighting coefficient of power fluctuation standard deviation, w p ∈[0,1], SI: Stability interference index, which indicates the stability of power consumption of secondary equipment during the stable power consumption period. The higher the value, the more unstable the power consumption of the equipment. p +w e =1,w e : Weighting coefficient of abnormal interference frequency, w e ∈[0,1],P b : The power value at time b during the stable power consumption period, The average value of the power value during the stable power consumption period, m: the number of data points during the stable power consumption period, that is, the number of time points of the recorded power value, N e : The number of times the power fluctuation threshold is exceeded within a unit time, T total : Total time, that is, the total time period of analysis, is used to calculate the frequency of abnormal interference per unit time.

2. According to the temporary electricity consumption identification, monitoring and management system based on the Internet of Things according to claim 1, it is characterized by: The specific process of obtaining scene power demand data and extracting power demand characteristics is as follows: The real-time power data of each electrical device is continuously collected through the sensor devices of the Internet of Things, the power changes are recorded at time intervals, the average and maximum power values ​​are calculated after removing the abnormal values, and the power demand characteristics are extracted; By analyzing the switch status of electrical equipment, the cumulative operating time of each device in a specific time period is calculated, the total working time of the equipment is counted, and the working time characteristics are extracted; By collecting the switching frequency of electrical equipment, counting the start and stop frequency of each device in a specific time period, and extracting working time characteristics; The electricity demand characteristics include power demand characteristics, working time characteristics, and start and stop characteristics.

3. According to the temporary electricity consumption identification, monitoring and management system based on the Internet of Things as claimed in claim 2, it is characterized by: The specific process of classifying power-consuming equipment into primary equipment and secondary equipment through clustering algorithm according to power demand characteristics is as follows: The power demand characteristics of each power-consuming device are formed into a feature vector, and the feature vector is standardized; Through the K-means clustering algorithm, two cluster numbers are set, namely the first-level equipment clustering and the second-level equipment clustering; The standardized feature vector is input into the K-means clustering algorithm to calculate the cluster center distribution value of each electrical device, which is divided into primary equipment and secondary equipment. The primary equipment represents equipment with large power demand fluctuations, long working hours and high switching frequency, and the secondary equipment represents equipment with stable power demand, short working hours and low switching frequency.

4. According to the temporary electricity consumption identification, monitoring and management system based on the Internet of Things as claimed in claim 3, it is characterized by: The specific process of load forecasting analysis for primary equipment and secondary equipment through time series is as follows: Use IoT sensor devices to monitor and record the power consumption data of primary and secondary devices in real time, including the real-time power, switch status, and working hours of the devices; According to the real-time data, the power consumption time series models of the primary equipment and the secondary equipment are constructed respectively through the long short-term memory network; The future load of the primary and secondary equipment is predicted through the constructed time series model. For the primary equipment, its peak load period is predicted; for the secondary equipment, its stable power consumption period is predicted; Based on the load forecast results, determine the peak load period of the primary equipment and the stable power consumption period of the secondary equipment.

5. According to the temporary electricity consumption identification, monitoring and management system based on the Internet of Things as claimed in claim 4, it is characterized by: The specific process of analyzing the power consumption fluctuation characteristics and load fluctuation frequency characteristics is as follows: Based on the high-load period data of the first-level equipment during the peak load period, extract the power data during the high-load period, calculate the power fluctuation amplitude of each period by counting the power value at each time point, and evaluate the power consumption fluctuation characteristics of the equipment during the high-load period; Perform time series analysis on power data during high-load periods to identify the periodicity and frequency of load changes, count the number of power changes per unit time, that is, the number of times the power value exceeds the set fluctuation range per unit time, derive the frequency of load fluctuations, and evaluate the load change characteristics of the equipment.

6. The temporary electricity consumption identification, monitoring and management system based on the Internet of Things according to claim 5 is characterized by: Based on the power consumption data of the secondary equipment during the stable power consumption period, the specific process of abnormal interference analysis on the stability of power consumption is as follows: Extract the power data of secondary equipment during the stable power consumption period, count the power values ​​in each time period, calculate the power fluctuation amplitude during the stable power consumption period, and evaluate the stability of power fluctuation; Perform time series analysis on power data during stable power consumption periods, identify abnormal power fluctuations, set power fluctuation thresholds, and consider fluctuations exceeding the thresholds as abnormal interference; Count the number of times the power value exceeds the set fluctuation threshold per unit time to evaluate the stability of power consumption.

7. The temporary electricity consumption identification, monitoring and management system based on the Internet of Things according to claim 6 is characterized by: The specific process of judging whether power-off protection is required for primary equipment according to the power fluctuation adaptability index is as follows: Obtain the power fluctuation adaptability index of each first-level device and set the power fluctuation adaptability threshold. When the power fluctuation adaptability index exceeds the set power fluctuation adaptability threshold, it means that the load fluctuation of the device is large and there is a risk of affecting the stability of the power system, which means that the device needs to be powered off for protection.

8. The temporary electricity consumption identification, monitoring and management system based on the Internet of Things according to claim 7 is characterized by: The specific process of judging whether load adjustment is required for the secondary equipment according to the stability interference index is as follows: Obtain the stability interference index of each secondary device and set a stability interference index threshold. When the stability interference index exceeds the set stability interference index threshold, it means that the power consumption stability of the device is poor, there are large fluctuations or interferences, which means that the device needs to adjust the load.

Images