Abnormal early warning method and device for power supply system of communication base station

Abstract

The embodiment of the invention discloses an abnormal early warning method and device for a power supply system of a communication base station, and relates to the field of monitoring and early warning of the communication base station. The abnormity early warning method of the communication base station power supply system comprises the following steps: acquiring a current current time sequence of each power supply device in the communication base station power supply system; inputting the current time sequence of each power supply device into a current prediction model associated with each power supply device for future current prediction to obtain a future current time sequence of each power supply device; obtaining a future current sequential sequence set based on the future current sequential sequence of each power supply device; and under the condition that an abnormal current sequential sequence exists in the future current sequential sequence set, carrying out abnormity early warning.

Description

Technical Field

[0001] The present application relates to the field of monitoring and early warning of communication base stations, and in particular to an abnormal early warning method and device for a power supply system of a communication base station. Background Art

[0002] With the development of communication technology, communication base stations are widely deployed. Communication base stations are used to provide unlimited coverage for wireless terminals and realize wireless signal transmission between wireless terminals and wired communication networks. They are important equipment in mobile communication networks.

[0003] In the related art, a special power supply system is usually set up for the communication base station to provide power support for the communication base station. The abnormality of the power supply system will seriously affect the normal operation of the communication base station. How to give an abnormal warning to the power supply system of the communication base station to avoid affecting the normal operation of the communication base station is an urgent problem to be solved. Summary of the invention

[0004] An embodiment of the present application provides an abnormality warning method for a power supply system of a communication base station, which is used to provide an abnormality warning for the power supply system of the communication base station in advance to avoid affecting the normal operation of the communication base station.

[0005] In a first aspect, an embodiment of the present application provides an abnormal warning method for a power supply system of a communication base station, the method comprising: Obtain the current timing sequence of each power supply device in the communication base station power supply system; Inputting the current time series sequence of each power supply device into the current prediction model associated with each power supply device to perform future current prediction, thereby obtaining the future current time series sequence of each power supply device; Obtaining a future current time series set based on the future current time series of each power supply device; When there is an abnormal current time series sequence in the future current time series sequence set, an abnormality warning is performed.

[0006] In a second aspect, an embodiment of the present application provides an abnormal warning device for a power supply system of a communication base station, the device comprising: A current current acquisition module, used to acquire the current current timing sequence of each power supply device in the power supply system of the communication base station; A future current prediction model is used to input the current time series of each power supply device into the current prediction model associated with each power supply device to perform future current prediction, so as to obtain the future current time series of each power supply device; A sequence set acquisition module, used to obtain a future current timing sequence set based on the future current timing sequence of each power supply device; The early warning module is used to issue an abnormal early warning when there is an abnormal current time sequence in the future current time sequence set.

[0007] In an embodiment of the present application, the current current timing sequence of each power supply device in the power supply system of the communication base station is obtained; the current current timing sequence of each power supply device is input into the current prediction model associated with each power supply device to perform future current prediction, thereby obtaining the future current timing sequence of each power supply device; a future current timing sequence set is obtained based on the future current timing sequence of each power supply device; and an abnormal warning is performed when there is an abnormal current timing sequence in the future current timing sequence set. When it is predicted that there will be an abnormal current timing sequence in the future, an early warning can be performed, so that the monitoring personnel can conduct abnormality inspection before the current abnormality actually occurs, thereby ensuring the normal operation of the communication base station. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0009] Figure 1 A schematic diagram of a flow chart of an abnormal warning method for a communication base station power supply system provided in an embodiment of the present application; Figure 2 A schematic diagram of a training process of a current prediction model provided in an embodiment of the present application; Figure 3 An example of a warning message transmission process provided in an embodiment of the present application; Figure 4 A schematic diagram of a module of an abnormal warning device for a power supply system of a communication base station provided in an embodiment of the present application; Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0010] The embodiments of the present application provide a method and device for abnormal warning of a power supply system of a communication base station.

[0011] In order to enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this application.

[0012] The abnormal warning method and device for the power supply system of a communication base station provided in the embodiment of the present application can be applied to the monitoring and warning platform of the power supply system of a communication base station, and its application scenario includes the scenario where the monitoring and warning platform monitors and warns the power supply system of the communication base station. Based on the abnormal warning method and device for the power supply system of a communication base station provided in the embodiment of the present application, an abnormal warning can be performed in advance before the abnormality of the power supply equipment occurs in the power supply system, so as to avoid affecting the normal operation of the communication base station.

[0013] See also Figure 1 , is a flow chart of an abnormal warning method for a communication base station power supply system provided in an embodiment of the present application. Figure 1 As shown, the abnormal warning method includes the following steps: S102, obtaining a current time sequence of each power supply device in the power supply system of the communication base station.

[0014] In the embodiment of the present application, the current current timing sequence is a timing sequence composed of the current values ​​at each time point within a specified time length ending at the current time point.

[0015] For example, for power supply device 1, its current current timing sequence 1 is:

[0016] In one implementation, the current value of each power supply device may be collected at fixed time intervals, and the current values ​​of each power supply device at N time points before the current time point may be determined as the current current timing sequence of each power supply device.

[0017] S104, inputting the current time series sequence of each power supply device into the current prediction model associated with each power supply device to perform current prediction, and obtaining the future current time series sequence of each power supply device.

[0018] In the embodiment of the present application, the current prediction model is used to predict and output the future current time series based on the input current time series. The future current time series is a time series composed of the current at each time point within a specified time length starting from the next time point of the current time point.

[0019] For example, the current current timing sequence 1 of the power supply device 1 can be input into the current prediction model associated with the power supply device 1. After receiving the current current timing sequence 1, the current prediction model can perform future current prediction based on the current current timing sequence 1, generate and output the future current timing sequence 1. The future current timing sequence 1 is the future current timing sequence of the power supply device 1, which is, for example:

[0020] In the embodiment of the present application, the current prediction model associated with each power supply device is a current prediction model of the device type to which each power supply device belongs, which is obtained through supervised training based on a current sequence sample set corresponding to the device type to which the power supply device belongs.

[0021] The current sequence sample set includes: a sample current current time series sequence and a corresponding sample future current time series sequence, wherein the sample current current time series sequence is the input during supervised training, and the sample future current time series sequence is the output label during supervised training.

[0022] The power supply equipment may be of a type of AC equipment, a wind power equipment or a solar power equipment.

[0023] See also Figure 2 , is a schematic diagram of a training process of a current prediction model provided in an embodiment of the present application. In an embodiment of the present application, each device type such as a mains device type, a wind power device type, and a solar device type can be used as a target device type, and the following is performed: Figure 2 The following supervised training is shown to obtain a current prediction model for each device type: S202, obtaining a current sequence sample set corresponding to the target device type.

[0024] In the embodiment of the present application, the current sequence sample set of the target device type includes multiple current sequence samples, and each current sequence sample includes a sample current current timing sequence of the target device type and a corresponding sample future current timing sequence.

[0025] The sample current time series of the target device type and the corresponding sample future current time series can be obtained based on the historical current series of the power supply device of the target device type. The power supply device of the target device type includes all power supply devices of the target device type in the power supply system, which can be one or more.

[0026] For example, assuming that the target equipment type is a wind power equipment type, the sequence composed of current values ​​at N time points up to a specified time point in the historical current sequence of the power supply equipment 1 of the wind power equipment type can be determined as the sample current current time series, and the sequence composed of current values ​​at M time points starting from the next time point of the time point can be determined as the sample future current time series, thereby obtaining a current sequence sample of the wind power equipment type.

[0027] For example, in the historical current sequence of the power supply equipment 2 of the wind power equipment type, the sequence composed of the current values ​​of N time points up to the specified time point can be determined as the sample current current time series, and the sequence composed of the current values ​​of M time points starting from the next time point of the time point can be determined as the sample future current time series sequence, thereby obtaining another current sequence sample of the wind power equipment type.

[0028] S204, performing supervised training on the base model based on the current sequence sample set corresponding to the target device type to obtain a current prediction model corresponding to the target device type.

[0029] In an embodiment of the present application, the sample current time series sequence can be used as the input of the base model, and the sample future current time series sequence corresponding to the sample current current time series sequence can be used as the output label of the base model to perform supervised training on the base model to obtain a current prediction model.

[0030] The base model is a model to be trained, which can select an appropriate time series prediction model, such as an LSTM model, a Transformer model, an ARMA model, etc. For different device types, the selected base model can be different.

[0031] The embodiment of the present application obtains a current sequence sample set corresponding to the target device type based on the historical current sequences of all power supply devices belonging to the target device type, and trains a current prediction model of the target device type based on the current sequence samples, thereby improving the generalization of the current prediction model so that it can cope with various current timing sequences of the device type. Predicting the future current timing sequence of the power supply device belonging to the target device type based on the current prediction model of the target device type can improve the accuracy of the prediction.

[0032] S106: Obtain a future current time series set based on the future current time series of each power supply device.

[0033] In the embodiment of the present application, the future current timing sequence set is a set composed of the future current timing sequence of each power supply device.

[0034] For example, assuming that there are three power supply devices in the power supply system, namely, power supply device 1, power supply device 2, and power supply device 3, the future current timing sequence set may be:

[0035] Each row in the above set corresponds to a power supply device, and each column corresponds to a time point.

[0036] S108, when there is an abnormal current time series sequence in the future current time series sequence set, an abnormality warning is issued.

[0037] In the embodiment of the present application, when there is an abnormal current timing sequence in the future current timing sequence set, an abnormal warning is issued, thereby enabling the staff to eliminate the abnormality of the power supply system in advance to avoid affecting the normal operation of the communication base station when the abnormality of the power supply equipment actually occurs.

[0038] In the embodiment of the present application, before step S108, an abnormal current time series sequence in the future current time series sequence set may be determined. The abnormal current time series sequence is a future current time series sequence with abnormal current variation law, which may be determined in an appropriate manner.

[0039] In one implementation, the future current timing sequence of each power supply device in the future current timing sequence set can be compared for similarity with the historical abnormal current timing sequence in the historical abnormal current database associated with each power supply device; and the future current timing sequence whose similarity to the historical abnormal current timing sequence is greater than a threshold is determined as an abnormal current timing sequence.

[0040] The historical abnormal current database associated with the power supply equipment is the historical abnormal current database of the equipment type to which the power supply equipment belongs, which contains the historical abnormal current time series of all power supply equipment under the equipment type. The historical abnormal current time series is the current time series of abnormalities that occurred in the history of the power supply equipment, which has the same length as the above-mentioned future current time series.

[0041] For example, for the power supply device 1, it belongs to the wind power equipment type, and its associated historical abnormal current database is the historical abnormal current database of the wind power supply device. The historical abnormal current database of the wind power equipment type stores the historical abnormal current time series of each power supply device of the wind power equipment type.

[0042] The embodiment of the present application establishes a historical abnormal current database corresponding to the equipment type, compares the future current timing sequence of the power supply equipment with the historical abnormal current timing sequence in the historical abnormal current database of the equipment type to which the power supply equipment belongs for similarity, and can use the historical abnormal current timing sequences of different power supply equipment belonging to the same equipment type to screen abnormal current timing sequences, thereby improving the accuracy of abnormal current timing sequence screening.

[0043] In the embodiment of the present application, the similarity between the future current time series sequence and the historical abnormal current time series sequence can be determined in an appropriate manner.

[0044] In one implementation, a current time curve may be generated for a future current time series sequence; an abnormal current time curve may be generated for a historical abnormal current time series sequence; and a similarity between the current time curve and the abnormal current time curve may be calculated.

[0045] The method for calculating the similarity between the current time curve and the abnormal current time curve specifically includes the following steps: Dividing the current time curve to obtain a plurality of first current short-term sub-segments of equal length and interval; dividing the abnormal current time curve to obtain a plurality of second current short-term sub-segments of equal length and interval, one first current short-term sub-segment corresponds to one second current short-term sub-segment; Setting a weight of each first current short-term sub-segment and a weight of each second current short-term sub-segment; respectively obtaining the distance between every two corresponding first current short-term sub-segments and every second current short-term sub-segment; The similarity of the current time curve and the abnormal current time curve is calculated according to the distances between the corresponding first current short-term sub-segments and each second current short-term sub-segment and the corresponding weights.

[0046] In the embodiment of the present application, in step S108, the abnormal warning level can be determined according to the number of abnormal current time series in the future current time series set, and a warning message can be generated based on the abnormal warning level; an abnormal warning is performed based on the warning message, wherein the abnormal warning level is used to indicate the degree of power supply abnormality. Thus, it is convenient for monitoring personnel to take corresponding response measures according to the warning level, thereby improving the efficiency and accuracy of the response.

[0047] For example, when the number of abnormal current timing sequences in the future current timing set is within the first number range, the abnormal warning level can be determined to be the first level, and the first level abnormal warning can be performed. When the number of abnormal current timing sequences in the future current timing set is within the second number range, the abnormal warning level can be determined to be the second level, and the second level abnormal warning can be performed. When the number of abnormal current timing sequences in the future current timing set is within the third number range, the abnormal warning level can be determined to be the third level, and the third level abnormal warning can be performed.

[0048] In the embodiment of the present application, in addition to the abnormal warning level information, the warning message may further include the warning information and response strategy corresponding to each abnormal current time series. In step S108, the warning message may be generated based on the abnormal warning level and the warning information and response strategy corresponding to each abnormal current time series.

[0049] The warning information includes: when the abnormal current timing sequence occurs, the status information of each device, such as temperature information, current information, voltage information, smoke information, etc. This information allows monitoring personnel to understand the status of each device. The response strategy includes: the response measures taken when the abnormal current timing sequence occurs.

[0050] In one implementation, the warning information and the coping strategy corresponding to the abnormal current time series sequence may be obtained based on the historical warning information and the historical coping strategy corresponding to the historical abnormal current sequence corresponding to the abnormal current time series sequence.

[0051] For example, assuming that the future current timing sequence 1 of the power supply device 1 is an abnormal current timing sequence, which is similar to the historical abnormal current timing sequence 2 in the abnormal current database associated with the power supply device 1, the historical warning information and historical response strategy corresponding to the abnormal current timing sequence 2 can be determined as the warning information and response strategy corresponding to the future current timing sequence 1.

[0052] In the embodiment of the present application, the warning message can be conveyed to the monitoring personnel in an appropriate manner.

[0053] In one implementation, the current indoor image of the monitoring room can be acquired from an indoor camera device; it can be identified whether there is a monitored person in the current indoor image; and when there is a monitored person in the current indoor image, an early warning message can be displayed on the central control display screen of the monitoring room.

[0054] The communication base station of the present application is provided with a monitoring room, and one or more indoor camera devices are provided at a designated position of the monitoring room, and the indoor camera device is used to collect real-time indoor images of the monitoring room. In the case of needing to make an abnormal warning, the current indoor image of the monitoring room can be obtained from the indoor camera device of the monitoring room to determine whether there is a monitoring person in the monitoring room based on the current indoor image, and in the case of a monitoring person in the monitoring room, the warning message is effectively conveyed to the indoor monitoring person.

[0055] In one implementation, further, when there is no monitored person in the current indoor image, the current outdoor image can be acquired from the outdoor camera device; it is identified whether there is a monitored person in the current outdoor image; and when there is a monitored person in the current outdoor image, the warning message is broadcast through an external loudspeaker.

[0056] The communication base station of the embodiment of the present application is, for example, a tower-type communication base station, and the outdoor camera device can be set on the tower to collect environmental information outside the monitoring room in real time. The external loudspeaker can also be set on the tower to cover a larger amplification range. When there is no monitoring person in the current indoor image, the current outdoor image can be obtained from the outdoor camera device to determine whether there is a monitoring person outside the monitoring room based on the current outdoor image. If there is a monitoring person outside the monitoring room, the early warning message is effectively conveyed to the outdoor monitoring person.

[0057] In one implementation, further, when there is no monitored person in the current outdoor image, a telephone number set of the monitored person is obtained; the telephone numbers in the telephone number set are dialed in sequence until the call is connected; and a voice call is made with the connected terminal based on the early warning message.

[0058] In the embodiment of the present application, the monitoring personnel telephone number set stores the telephone numbers of multiple monitoring personnel in sequence according to the convenience of the monitoring personnel in handling the warning. By calling the telephone numbers in the telephone number set in sequence, the warning message can be effectively conveyed to the monitoring personnel who is most convenient to handle the warning.

[0059] Among them, conducting a voice call with the connected terminal based on the warning message may specifically include the following processing: Sending a warning notification voice to the connected terminal based on the warning message; Recognizing the feedback voice returned by the terminal; Perform semantic recognition on the feedback voice to determine whether the connected monitoring personnel can currently handle the warning; In the case that the connected monitoring personnel cannot currently handle the early warning, the next telephone number in the telephone number set is dialed.

[0060] Through the above-mentioned warning message transmission process, the warning message can be effectively transmitted to the monitoring personnel who are most convenient to handle the warning through various contact channels, ensuring that the monitoring personnel can receive the warning message and handle the warning as soon as possible. Figure 3 shown.

[0061] The abnormal warning method for the power supply system of a communication base station provided in the embodiment of the present application obtains the current current timing sequence of each power supply device in the power supply system of the communication base station; inputs the current current timing sequence of each power supply device into the current prediction model associated with each power supply device to perform future current prediction, thereby obtaining the future current timing sequence of each power supply device; obtains a future current timing sequence set based on the future current timing sequence of each power supply device; and performs abnormal warning when there is an abnormal current timing sequence in the future current timing sequence set. When it is predicted that there will be an abnormal current timing sequence in the future, a warning can be issued, thereby facilitating monitoring personnel to conduct abnormality inspection before the current abnormality actually occurs, thereby ensuring the normal operation of the communication base station.

[0062] The above is an abnormal warning method for a communication base station power supply system provided by an embodiment of the present application. Based on the same idea, an abnormal warning device for a communication base station power supply system is also provided by an embodiment of the present application. Figure 4 As shown, the abnormal warning device 400 of the communication base station power supply system includes the following modules: The current current acquisition module 401 is used to acquire the current current timing sequence of each power supply device in the power supply system of the communication base station; A future current prediction model 402 is used to input the current time series of each power supply device into the current prediction model associated with each power supply device to perform future current prediction, so as to obtain the future current time series of each power supply device; A future current set acquisition module 403, configured to obtain a future current time series set based on the future current time series of each power supply device; The early warning module 404 is used to issue an abnormal early warning when there is an abnormal current time series sequence in the future current time series sequence set.

[0063] Among them, the current prediction model associated with each power supply device is obtained through supervised training based on the current sequence sample set corresponding to the device type to which each power supply device belongs; the current sequence sample set includes: a sample current current timing sequence and a corresponding sample future current timing sequence, the sample current current timing sequence is the input during supervised training, and the sample future current timing sequence is the output label during supervised training.

[0064] In one implementation, the device 400 further includes: The abnormal current determination module is used to calculate the similarity between the future current timing sequence of each power supply device in the future current timing sequence set and the historical abnormal current timing sequence in the historical abnormal current database associated with each power supply device; and determine the future current timing sequence whose similarity with the historical abnormal current timing sequence is greater than a threshold as an abnormal current timing sequence.

[0065] In one implementation manner, the early warning module 404 is specifically configured to: Determining an abnormal warning level based on the number of abnormal current time series sequences in the future current time series sequence set; generating a warning message based on the abnormal warning level; An abnormality warning is performed based on the warning message.

[0066] In one implementation manner, the early warning module 404 is specifically configured to: Based on the abnormal warning level and the warning information and response strategy corresponding to each abnormal current time series, a warning message is generated.

[0067] In one implementation manner, the early warning module 404 is specifically configured to: Acquire the current indoor image of the monitoring room from the indoor camera device; Identify whether there is a surveillance person in the current indoor image; When there is a monitored person in the current indoor image, an early warning message is displayed on the central control display screen in the monitoring room.

[0068] In one implementation manner, the early warning module 404 is further configured to: When there is no monitored person in the current indoor image, obtaining the current outdoor image from the outdoor camera device; Identify whether there is a surveillance person in the current outdoor image; In the case where there is a monitoring person in the current outdoor image, the warning message is broadcasted through an external loudspeaker.

[0069] In one implementation manner, the early warning module 404 is further configured to: When there is no monitoring person in the current outdoor image, obtaining a telephone number set of the monitoring person; dialing the telephone numbers in the telephone number set in sequence until the call is connected; A voice call is made with the connected terminal based on the early warning message.

[0070] In one implementation manner, the early warning module 404 is specifically configured to: Sending a warning notification voice to the connected terminal based on the warning message; Recognizing the feedback voice returned by the terminal; Perform semantic recognition on the feedback voice to determine whether the connected monitoring personnel can currently handle the warning; In the case that the connected monitoring personnel cannot currently handle the early warning, the next telephone number in the telephone number set is dialed.

[0071] The abnormal warning device of the communication base station power supply system provided in the embodiment of the present application obtains the current current timing sequence of each power supply device in the communication base station power supply system; inputs the current current timing sequence of each power supply device into the current prediction model associated with each power supply device to predict the future current, and obtains the future current timing sequence of each power supply device; obtains a future current timing sequence set based on the future current timing sequence of each power supply device; and performs an abnormal warning when there is an abnormal current timing sequence in the future current timing sequence set. When it is predicted that there will be an abnormal current timing sequence in the future, a warning can be issued, which is convenient for monitoring personnel to conduct abnormality inspection before the current abnormality actually occurs, so as to ensure the normal operation of the communication base station.

[0072] The above methods and devices provided in the embodiments of the present application can be applied to electronic devices such as monitoring and early warning platforms of communication base stations. Figure 5 Schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 5As shown, the electronic device includes a processor 501 and a memory 502. The memory 502 stores a computer program that can be run on the processor 501. When the computer program is executed by the processor 501, the various processes of the above-mentioned communication base station power supply system abnormal warning method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0073] The embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, each process of the above-mentioned abnormal warning method embodiment of the power supply system of the communication base station is implemented, and the same technical effect can be achieved. To avoid repetition, it is not repeated here. Among them, the computer-readable storage medium is such as a read-only memory (Read-Only Memory, referred to as ROM), a random access memory (Random Access Memory, referred to as RAM), a disk or an optical disk, etc.

[0074] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt 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 codes.

[0075] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes 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 generate 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.

[0076] 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.

[0077] 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.

[0078] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0079] Memory may include non-permanent storage in a computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0080] Computer-readable media include permanent and non-permanent, removable and non-removable media that can be used to store information by any method or technology. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. According to the definition in this article, computer-readable media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0081] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0082] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for abnormal warning of a power supply system of a communication base station, characterized in that: The method comprises: Obtain the current timing sequence of each power supply device in the communication base station power supply system; Inputting the current time series of each power supply device into the current prediction model associated with each power supply device to perform future current prediction, thereby obtaining the future current time series of each power supply device; Obtaining a future current time series set based on the future current time series of each power supply device; When there is an abnormal current time series sequence in the future current time series sequence set, an abnormality warning is performed.

2. The abnormal warning method according to claim 1, characterized in that: The current prediction model associated with each power supply device is obtained through supervised training based on a current sequence sample set corresponding to the device type to which each power supply device belongs; The current sequence sample set includes: a sample current current time series sequence and a corresponding sample future current time series sequence, wherein the sample current current time series sequence is the input during supervised training, and the sample future current time series sequence is the output label during supervised training.

3. The abnormal warning method according to claim 1, characterized in that: Before performing the abnormal warning, the method further includes: Calculate the similarity between the future current time series sequence of each power supply device in the future current time series set and the historical abnormal current time series sequence in the historical abnormal current database associated with each power supply device; A future current time series sequence whose similarity to a historical abnormal current time series sequence is greater than a threshold is determined as an abnormal current time series sequence.

4. The abnormal warning method according to claim 1, characterized in that: The abnormal warning includes: Determining an abnormal warning level based on the number of abnormal current time series sequences in the future current time series sequence set; generating a warning message based on the abnormal warning level; An abnormality warning is performed based on the warning message.

5. The abnormal warning method according to claim 4, characterized in that: The generating of the warning message based on the abnormal warning level includes: Based on the abnormal warning level and the warning information and response strategy corresponding to each abnormal current time series, a warning message is generated.

6. The abnormal warning method according to claim 4, characterized in that: The abnormal warning based on the warning message includes: Acquire the current indoor image of the monitoring room from the indoor camera device; Identify whether there is a surveillance person in the current indoor image; When there is a monitored person in the current indoor image, an early warning message is displayed on the central control display screen in the monitoring room.

7. The abnormal warning method according to claim 6, characterized in that: The abnormal warning based on the warning message also includes: When there is no monitored person in the current indoor image, obtaining the current outdoor image from the outdoor camera device; Identify whether there is a surveillance person in the current outdoor image; In the case where there is a monitoring person in the current outdoor image, the warning message is broadcasted through an external loudspeaker.

8. The abnormality early warning method according to claim 7, characterized in that: The abnormal warning based on the warning message also includes: When there is no monitoring person in the current outdoor image, obtaining a telephone number set of the monitoring person; dialing the telephone numbers in the telephone number set in sequence until the call is connected; A voice call is made with the connected terminal based on the early warning message.

9. The abnormal warning method according to claim 8, characterized in that: The performing a voice call with the connected terminal based on the warning message includes: Sending a warning notification voice to the connected terminal based on the warning message; Recognizing the feedback voice returned by the terminal; Perform semantic recognition on the feedback voice to determine whether the connected monitoring personnel can currently handle the warning; In the case that the connected monitoring personnel cannot currently handle the early warning, the next telephone number in the telephone number set is dialed.

10. An abnormal warning device for a power supply system of a communication base station, characterized in that: The device comprises: A current current acquisition module, used to acquire the current current timing sequence of each power supply device in the power supply system of the communication base station; A future current prediction model is used to input the current time series of each power supply device into the current prediction model associated with each power supply device to perform future current prediction, so as to obtain the future current time series of each power supply device; A sequence set acquisition module, used to obtain a future current timing sequence set based on the future current timing sequence of each power supply device; The early warning module is used to issue an abnormal early warning when there is an abnormal current time sequence in the future current time sequence set.

Images