Malicious load identification method and system based on smart electric energy meter

Abstract

The present invention relates to the field of malicious load detection, and in particular to a method and system for identifying malicious loads based on a smart electric energy meter. The method comprises: collecting first data, the first data comprising line temperature data, weather data and power data of the current cycle; calculating the first power corresponding to the weather data of the current cycle according to historical weather data and its corresponding power data; calculating the first threshold according to the historical power data and the first power; and determining whether there is a malicious load in the circuit according to a preset rule. The present invention can effectively reduce the problem of misjudgment of malicious loads.

Description

Technical Field

[0001] The present invention relates to the field of malicious load detection, and more specifically, to a malicious load identification method and system based on a smart electric energy meter. Background Art

[0002] A malicious load generally refers to a high-power electrical appliance that converts a large amount of electrical energy into heat energy, which is prone to cause fire safety accidents and illegal use. A malicious load is approximately pure resistance. The characteristics are that the voltage and current waveforms are the same, the voltage and current phases are the same, and the power factor is close to 1.

[0003] With the development of society, the scale of electricity consumption in some densely populated residential places has continued to expand. Fire accidents caused by the illegal and intensive use of high-power microwave ovens, hot pots, induction cookers and other electrical appliances, as well as the charging of electric vehicles at home have occurred frequently. The efficiency and effectiveness of manual inspection of the access of such malicious load electrical appliances are low.

[0004] At present, the methods for detecting malicious loads include current detection method, power limitation method, temperature detection method, harmonic analysis method, instantaneous power increase method, etc. Each method can detect malicious loads, but all have shortcomings.

[0005] The patent application document with publication number "CN115765149A" and titled "A method for identifying malicious loads based on a big data cloud platform" discloses a method for performing total power detection, instantaneous power gain detection, harmonic analysis and power factor detection on malicious loads, and monitoring various aspects of malicious loads that affect safety, so as to detect malicious loads in a timely manner.

[0006] The above method does not take into account the impact that weather changes will have on the use of electrical appliances. For example, under high or low temperature conditions, the use of air conditioners or water heaters will increase, and relying on power detection may misjudge them as malicious loads. Summary of the invention

[0007] In order to solve the problem of reducing malicious load misjudgment, the present invention provides solutions in the following aspects.

[0008] In a first aspect, the present invention provides a method for identifying a malicious load based on a smart electric energy meter, comprising: collecting first data, the first data including line temperature data and weather data of a current cycle, and power averages of n cycles before the current cycle and weather data of the nth cycle before the current cycle; calculating first weather change data according to the weather data of the current cycle and the weather data of the nth cycle before the current cycle; calculating first power change data corresponding to the first weather change data according to historical weather change data and their corresponding power change data; calculating a first threshold γ according to the power averages of n cycles before the current cycle and the first power change data, ,in, is the first power change data, is the power average of the n cycles before the current cycle; if the line temperature data of the current cycle exceeds the second threshold and the power data exceeds the first threshold, it is determined that there is a malicious load in the circuit where the smart electric energy meter is located; if the line temperature data of the current cycle does not exceed the second threshold or the power data does not exceed the first threshold, the cycle size is adjusted and the first data is recollected; if the line temperature data of the current cycle does not exceed the second threshold and the power data does not exceed the first threshold, it is determined that there is no malicious load and no abnormality in the circuit where the smart electric energy meter is located.

[0009] Beneficial effects: The present invention introduces weather data, takes into account the impact of weather on power consumption, and combines power and temperature to more accurately determine whether there is a malicious load in the circuit. In addition, if the first identification is uncertain whether there is a malicious load in the circuit, a secondary identification can be performed by adjusting the cycle, thereby reducing the misjudgment of malicious loads.

[0010] In one embodiment, the line temperature data of the current cycle includes: a line temperature change value of the current cycle or a line temperature change rate of the current cycle.

[0011] Beneficial effect: A malicious load generally causes a sudden rise in line temperature. The line temperature change value or line temperature change rate can, to a certain extent, serve as evidence of the presence of a malicious load.

[0012] In one embodiment, the weather data includes at least: temperature, humidity and rainfall.

[0013] Beneficial effects: Temperature, humidity, rainfall and snowfall generally affect the use of high-power electrical appliances, which are easily mistaken for malicious loads. Therefore, introducing these weather factors in the process of judging malicious loads can reduce the misjudgment of malicious loads.

[0014] In one embodiment, before collecting the first data, it also includes: collecting a circuit current signal; preprocessing the current signal; converting the preprocessed current signal into a frequency domain signal, and analyzing the harmonic components in the frequency domain signal; if there are malicious load harmonic components in the circuit, collecting the first data.

[0015] Beneficial effect: The current harmonic analysis method for judging malicious loads is relatively mature. By using the harmonic analysis method to analyze the malicious load components before collecting the first data, it can be preliminarily determined whether there is a malicious load in the circuit.

[0016] In one embodiment, if the line temperature data of the current cycle does not exceed the second threshold or the power data does not exceed the first threshold, the cycle size is adjusted, and after the first data is recollected, including: the line temperature data does not exceed the second threshold or the power data does not exceed the first threshold, the smart power meter issues an abnormal warning signal.

[0017] In one embodiment, it is determined that a malicious load exists in the circuit where the smart electric energy meter is located, and then the smart electric energy meter cuts off power to the circuit.

[0018] Beneficial effect: After identifying a malicious load, the smart energy meter directly cuts off the power to the circuit, which can timely reduce the impact of the malicious load on the entire circuit.

[0019] In one embodiment, the calculating the first power change data corresponding to the first weather change data based on the historical weather change data and the corresponding power change data includes: constructing a neural network prediction model based on the historical weather change data and the corresponding power change data; inputting the first weather change data into the neural network prediction model to predict the first power change data.

[0020] In a second aspect, the present invention further provides a malicious load identification system based on a smart power meter, comprising: a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above-mentioned malicious load identification method based on a smart power meter.

[0021] The beneficial effects of the present invention are as follows: the present invention takes into account the impact of weather on power consumption by introducing weather data, and combines power and temperature to more accurately determine whether there is a malicious load in the circuit, and the parameters in the first threshold calculation formula are related to the period. In the case of a first identification of whether there is a malicious load in the uncertain circuit, the first threshold can be adjusted by adjusting the period to perform a secondary identification, thereby also reducing the misjudgment of malicious loads. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0023] Figure 1 This is a flow chart of a method for identifying malicious loads based on a smart electric energy meter provided by an embodiment of the present invention;

[0024] Figure 2 The present invention provides a block diagram of a malicious load identification system based on a smart electric energy meter. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0026] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0027] Figure 1 The present invention is a flowchart of a method for identifying malicious loads based on a smart electric energy meter according to an embodiment of the present invention, comprising the following steps:

[0028] S101, collecting first data, where the first data includes line temperature data, weather data, and power data of a current period;

[0029] ‌‌Malicious loads‌ refer to electrical equipment that generates a lot of heat when working, which can easily lead to problems such as overheating of wires and internal short circuits of electrical appliances, thereby causing fires. After a malicious load is connected to a circuit, there will generally be a sudden increase in line temperature and a sudden increase in power. Therefore, the present invention needs to collect line temperature data and power data. At the same time, because weather data may cause some electrical appliances to be used more frequently, and these appliances are easily identified as malicious loads, introducing weather data of the current period into the identification method can reduce misjudgments.

[0030] S102, calculating a first power corresponding to the weather data of the current period according to the historical weather data and the corresponding power data;

[0031] In some embodiments, the weather data includes at least: temperature, humidity, and rainfall.

[0032] The specific calculation method of the first power can be as follows: preset a comfortable power threshold in advance, for example, the power consumption at a temperature of 26°C, a humidity of 30%, and no rainfall is set as a comfortable power threshold a, and the weather data of the current period is a temperature of 32°C, a humidity of 50%, and no rainfall. At this time, the power consumption is b, and the first power is ba. Generally speaking, a multiple linear regression method or a neural network model can also be used to calculate the first power corresponding to the weather data of the current period. It should be noted that the specific multiple linear regression method or neural network model is a well-known technology and will not be repeated here.

[0033] S103, calculating a first threshold γ according to historical power data and the first power, ,in, is the first power, is the power mean of the first n cycles;

[0034] For example, when the temperature is high, the use of air conditioners will increase. When the temperature is low, the use of air conditioners, water heaters, and electric blankets will increase. When the humidity is high or there is a lot of rainfall, the use of dryers will increase. These electrical appliances are all high-power electrical appliances. If the previous power identification method is used, it is easy to think that there is a malicious load in the circuit. Therefore, the first threshold is introduced. ,in, It is the first power, which is related to weather data and can reflect the impact of weather on circuit power. It is the power average of the previous n cycles, which can reflect the overall situation of the circuit power in the recent period.

[0035] In some embodiments, the first power corresponding to the weather data of the current period is calculated based on the historical weather data and the corresponding power data, including: calculating the historical weather change data and the corresponding power change data based on the historical weather data and the corresponding power data; constructing a neural network prediction model based on the historical weather change data and the corresponding power change data; calculating the first weather change data based on the weather data of the current period and the weather data of the nth period before the current period; inputting the first weather change data into the neural network prediction model, and predicting the power change data, i.e., the first power.

[0036] S104. If the line temperature data of the current cycle exceeds the second threshold and the power data exceeds the first threshold, it is determined that there is a malicious load in the circuit where the smart electric energy meter is located; if the line temperature data of the current cycle does not exceed the second threshold or the power data does not exceed the first threshold, the cycle size is adjusted and the first data is recollected; if the line temperature data of the current cycle does not exceed the second threshold and the power data does not exceed the first threshold, it is determined that there is no malicious load in the circuit where the smart electric energy meter is located and there is no abnormality.

[0037] In some embodiments, the line temperature data of the current cycle includes: a line temperature change value of the current cycle or a line temperature change rate of the current cycle.

[0038] For example, if the line temperature change value of the current cycle is 4°C, the preset second threshold is 3°C, the power data of the current cycle is 12 kilowatts, and the first threshold calculated by step S103 is 13 kilowatts, it is obvious that the line temperature data of the current cycle exceeds the second threshold and the power data exceeds the first threshold, then it is determined that there is a malicious load in the circuit. In some embodiments, the smart energy meter will power off the circuit at this time; if the line temperature change value of the current cycle is 4°C, the preset second threshold is 3°C, the power data of the current cycle is 12 kilowatts, and the first threshold calculated by step S103 is 11 kilowatts, it is obvious that the line temperature data of the current cycle does not exceed the second threshold or the power data does not exceed the first threshold. At this time, it is necessary to adjust the cycle size and re-collect the first data for calculation. Generally speaking, the adjusted cycle is smaller than the cycle before adjustment. For example, the preset cycle before adjustment is 60 seconds, and the adjusted cycle is 30 seconds. Generally, line power and temperature are directly proportional. If the line temperature is too high and the power is low, the temperature sensor or power measurement device may be faulty. If the line temperature is low and the power is too high, there may be poor contact in the line. Therefore, in some embodiments, if the cycle size is adjusted and the first data is re-collected, if it is still detected that the line temperature data does not exceed the second threshold or the power data does not exceed the first threshold, it can be determined that there is an abnormality in the line, and the smart power meter will issue an abnormal warning signal.

[0039] In some embodiments, before collecting the first data, the method further includes: collecting the circuit current signal; preprocessing the current signal; converting the preprocessed current signal into a frequency domain signal, and analyzing the harmonic components in the frequency domain signal; if there are malignant load harmonic components in the circuit, the first data is collected. Before collecting the first data, the malignant load components are analyzed using a harmonic analysis method, which can preliminarily determine whether there are malignant loads in the circuit and reduce the amount of subsequent calculations. It should be noted that the specific harmonic analysis method for analyzing malignant load harmonic components is a well-known technology and will not be described in detail here.

[0040] The above-mentioned malicious load identification method based on the smart electric energy meter provided in an embodiment of the present invention introduces weather data, takes into account the impact of weather on electric power consumption, and combines power and temperature to more accurately determine whether there is a malicious load in the circuit. Moreover, the parameters in the first threshold calculation formula are related to the period. When a first identification is uncertain whether there is a malicious load in the circuit, the first threshold can be adjusted by adjusting the period to perform a secondary identification, thereby reducing the misjudgment of malicious loads.

[0041] The present invention also provides a malicious load identification system based on a smart electric energy meter. Figure 2As shown, the system includes a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a malicious load identification method based on a smart electric energy meter described in the present invention is implemented.

[0042] The system also includes other components familiar to those skilled in the art, such as a communication bus and a communication interface, whose configuration and functions are known in the art and thus will not be described in detail here.

[0043] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of a device or accessible or connectable to a device. Any application or module described in the present invention may be implemented using computer-readable / executable instructions that may be stored or otherwise maintained by such a computer-readable medium.

[0044] In the description of this specification, "plurality" or "several" means at least two, such as two, three or more, etc., unless otherwise clearly and specifically defined.

[0045] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

Claims

1. A method for identifying malicious loads based on a smart electric energy meter, characterized in that: include: Collecting first data, the first data including line temperature data and weather data of a current cycle, power averages of n cycles before the current cycle, and weather data of the nth cycle before the current cycle; Calculate the first weather change data according to the weather data of the current period and the weather data of the nth period before the current period; Calculating first power change data corresponding to the first weather change data according to historical weather change data and corresponding power change data; Calculate a first threshold γ according to the power average of n cycles before the current cycle and the first power change data, ,in, is the first power change data, is the power average of n cycles before the current cycle; If the line temperature data of the current cycle exceeds the second threshold and the power data exceeds the first threshold, it is determined that there is a malicious load in the circuit where the smart electric energy meter is located; if the line temperature data of the current cycle does not exceed the second threshold or the power data does not exceed the first threshold, the cycle size is adjusted and the first data is recollected; if the line temperature data of the current cycle does not exceed the second threshold and the power data does not exceed the first threshold, it is determined that there is no malicious load and no abnormality in the circuit where the smart electric energy meter is located.

2. The method for identifying malicious loads based on a smart electric energy meter according to claim 1, characterized in that: The line temperature data of the current cycle includes: the average line temperature of the current cycle or the line temperature change rate of the current cycle.

3. The method for identifying malicious loads based on a smart electric energy meter according to claim 1, characterized in that: The weather data includes: temperature, humidity and rainfall.

4. The method for identifying malicious loads based on a smart electric energy meter according to claim 1, characterized in that: Before collecting the first data, the method further includes: Collect circuit current signal; Preprocessing the current signal; Converting the preprocessed current signal into a frequency domain signal, and analyzing the harmonic components in the frequency domain signal; If there are malignant load harmonic components in the circuit, the first data is collected.

5. The method for identifying malicious loads based on a smart electric energy meter according to claim 1, characterized in that: If the line temperature data of the current cycle does not exceed the second threshold or the power data does not exceed the first threshold, the cycle size is adjusted, and the first data is collected again, including: If the line temperature data does not exceed the second threshold or the power data does not exceed the first threshold, the smart energy meter will issue an abnormal warning signal.

6. The method for identifying malicious loads based on a smart electric energy meter according to claim 1, characterized in that: Determining that a malicious load exists in the circuit where the smart electric energy meter is located, and then comprising: The smart energy meter cuts off the power to the circuit.

7. The method for identifying malicious loads based on a smart electric energy meter according to claim 1, characterized in that: The calculating, according to the historical weather change data and the corresponding power change data, the first power change data corresponding to the first weather change data comprises: Constructing a neural network prediction model based on the historical weather change data and its corresponding power change data; The first weather change data is input into the neural network prediction model to predict the first power change data.

8. A malicious load identification system based on smart electric energy meter, characterized in that: include: A memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the malicious load identification method based on the smart electric energy meter as claimed in any one of claims 1 to 7.

Images