Power distribution method of machine room power supply system

Abstract

The invention relates to the technical field of power distribution, in particular to a power distribution method of a machine room power supply system, which comprises the following steps: acquiring a reference data set of parameter items of each acquisition moment in an operation data time sequence of bus connection equipment, the parameter items comprising current and / or voltage; calculating the tendency and prediction deviation of the parameter item at each acquisition moment, and normalizing the product of the prediction deviation of the parameter item, a preset error factor and the tendency to obtain an error factor of the parameter item; in the HTFE algorithm, the parameter item predicted values at the next acquisition moment are obtained by using the error factors, and the power required by the equipment at the next acquisition moment is obtained through the product of the parameter item predicted values, so that power distribution is realized, and the power distribution accuracy of the machine room power supply system is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power distribution, and more specifically, to a power distribution method for a computer room power supply system. Background Art

[0002] The computer room is the core place for data storage, processing and transmission, and usually contains related power supply equipment, environmental control equipment and safety equipment. Its energy consumption accounts for a large proportion of the total energy consumption of the enterprise. Therefore, improving energy utilization efficiency and achieving energy saving and efficiency improvement in the computer room is one of the important goals of computer room management.

[0003] An uninterruptible power supply (UPS) distribution cabinet is a special distribution cabinet for a computer room, which distributes power to various devices connected to the busbar of the distribution cabinet according to a predetermined distribution ratio. There are many studies on UPS power distribution in the prior art. For example, a patent application document with publication number CN107947337A discloses a power control device based on a UPS system. The application includes an uninterruptible power supply module, which can be switched to a shutdown state and immediately supply backup power when the power of an external power supply device is interrupted; a power distribution module, which supplies backup power to each power distribution area by pre-dividing the power distribution area of ​​the power system; and a power control module, which defines the emergency power supply level of the battery by detecting the charge level of the battery, and controls the supply of backup power to each power distribution area according to the priority order of the power distribution area set in advance and the emergency power supply level.

[0004] The above-mentioned prior art distributes power to various power distribution areas through UPS. However, in order to ensure power supply during peak hours or sudden high loads during the power distribution process, spare redundant power is usually reserved, resulting in the power supply of equipment during non-peak hours exceeding the current actual power demand, that is, there is a power surplus phenomenon, which increases energy consumption costs.

[0005] Based on this, how to accurately realize the power distribution of the power supply system of the computer room is a problem that needs to be solved urgently by technical personnel in this field. Summary of the invention

[0006] In order to solve the above technical problem of how to accurately realize the power distribution of the power supply system of the computer room, the present invention proposes a power distribution method of the power supply system of the computer room, which method comprises the following steps: Acquire a reference data set of parameter items at each acquisition moment in a time series of operation data of a bus connection device, wherein the parameter items include current and / or voltage; ; , , are the first The trend, fluctuation and value of each parameter. is the number of data in the reference dataset, , Respectively , The timestamp of the collection moment, For the The first collection time The value of the parameter item, is an exponential function with e as the base; the product of the predicted deviation of the parameter item, the preset error factor and the trend is normalized to obtain the error factor of the parameter item; the error factor is used in the HTFE algorithm to obtain the predicted value of the parameter item at the next collection moment, and the power required by the equipment at the next collection moment is obtained by multiplying the predicted values ​​of each parameter item to realize power distribution.

[0007] The present invention takes into account that the reserve power reserved in the power distribution process to ensure power supply during peak hours or sudden high loads will increase energy consumption costs, and the power demand in different time periods is different, which will cause resource waste. Based on this, the present invention predicts the power demand of the equipment through the HTFE algorithm, and adjusts the power of the equipment based on the predicted value, effectively improving the accuracy of power distribution and reducing resource waste. In this process, the present invention takes into account that the fixed error factor in the HTFE algorithm cannot adapt to the equipment operation data with various changing trends, resulting in low accuracy of the obtained prediction results; based on this, the present invention obtains the trend changes of recent data of the equipment parameter items at each collection time, and adjusts the error factor according to the trend changes, so as to accurately obtain the power demand prediction value of the equipment, effectively improving the accuracy of power distribution of the computer room power supply system.

[0008] According to a power distribution method for a computer room power supply system provided by the present invention, the reference data set for obtaining parameter items at each collection moment in a timing sequence of operation data of a busbar-connected device also includes: collecting parameter data generated during the operation of each device connected to the UPS bus in the computer room, preprocessing the parameter data, and obtaining parameter items at each collection moment in the timing sequence of the operation data.

[0009] The present invention takes into account that there may be noise data or data missing in the originally collected parameter data, and therefore improves the overall quality of the data through preprocessing.

[0010] According to a power distribution method for a computer room power supply system provided by the present invention, the reference data set acquisition method of the parameter item includes: acquiring a historical data set of the parameter item; acquiring the number of data in the historical data set of the parameter item based on the size of a preset reference data set to construct a reference data set for the parameter item.

[0011] The present invention obtains historical data of parameter items as their recent reference data sets for analysis, thereby reducing data waiting time, so that trend changes of parameter items can be accurately obtained based on this.

[0012] According to a power distribution method for a computer room power supply system provided by the present invention, the method for obtaining the fluctuation degree of a parameter item includes: normalizing the square sum of the difference between the parameter item and each data in its reference data set to obtain the fluctuation degree of the parameter item.

[0013] The present invention can accurately obtain the fluctuation degree of the parameter item by obtaining the data difference between the parameter item and each parameter item in its reference data set. The larger the sum of squares of the differences, the greater the fluctuation degree.

[0014] According to a power distribution method for a computer room power supply system provided by the present invention, the method for obtaining the prediction deviation of the parameter item includes: obtaining an initial prediction value of the parameter item through a prediction algorithm; and recording the absolute value of the difference between the initial prediction value of the parameter item and the numerical value as the prediction deviation of the parameter item.

[0015] According to a power distribution method for a computer room power supply system provided by the present invention, the power required by the device at the next acquisition moment is obtained by multiplying the predicted values ​​of each parameter item to achieve power distribution, including: transmitting the power required by each device to the corresponding device through the corresponding bus.

[0016] According to a power distribution method for a computer room power supply system provided by the present invention, the power distribution is implemented, and then the method further includes: performing abnormal monitoring and early warning on parameter items of each device at each collection moment.

[0017] The present invention takes into account that there may be potential safety hazards when there are abnormalities in parameter data generated during the operation of the equipment. Therefore, through abnormal monitoring and early warning, the staff is promptly reminded to deal with the abnormal situation.

[0018] According to a power distribution method for a computer room power supply system provided by the present invention, the abnormal monitoring and early warning of the parameter items of each device at each collection moment also includes: associating and storing the values ​​of the parameter items of each device at each collection moment, the required power and the abnormal monitoring results.

[0019] The present invention has the following beneficial effects: When realizing the power distribution of the computer room power supply system, the present invention predicts the power demand of the equipment through the HTFE algorithm, and adjusts the power of the equipment based on the predicted value, which effectively improves the accuracy of power distribution and reduces resource waste. In this process, the present invention takes into account that the fixed error factor cannot adapt to the equipment operation data with various changing trends, resulting in low accuracy of the obtained prediction results; based on this, the present invention obtains the trend change of the recent data of the equipment parameter items at each collection time, and adjusts the error factor according to the trend change, so as to accurately obtain the power demand prediction value of the equipment, effectively improving the accuracy of power distribution of the computer room power supply system. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] 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: Figure 1 A schematic flow chart of a method for distributing power in a computer room power supply system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0021] 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.

[0022] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0023] The computer room is the core place for data storage, processing and transmission, and usually contains related power supply equipment, environmental control equipment and safety equipment. Its energy consumption accounts for a large proportion of the total energy consumption of the enterprise. Therefore, improving energy utilization efficiency and achieving energy saving and efficiency improvement in the computer room is one of the important goals of computer room management.

[0024] Uninterruptible Power Supply (UPS) distribution cabinet is a special distribution cabinet for computer rooms, which distributes power to various devices connected to the distribution cabinet bus according to a predetermined distribution ratio. However, in order to ensure power supply during peak hours or sudden high loads, redundant power is usually reserved during the power distribution process, resulting in the power supply of equipment during non-peak hours exceeding the current actual power demand, that is, there is a phenomenon of excess power, which increases energy consumption costs.

[0025] Based on this, an embodiment of the present invention discloses a power distribution method for a computer room power supply system. The method analyzes the historical voltage and current data of the equipment to obtain the power demand prediction value of each device, and allocates power resources to each device based on the power demand prediction value. This can effectively improve the accuracy of power distribution and avoid waste of power resources.

[0026] See also Figure 1 As shown, Figure 1 A flow chart of a power distribution method for a computer room power supply system provided in an embodiment of the present invention, the method specifically includes the following steps.

[0027] S1: Obtain a reference data set of parameter items at each acquisition moment in the operation data timing sequence of the busbar connection device.

[0028] The parameter items include current and / or voltage.

[0029] It should be noted that in the power supply system of the computer room, the interface of the UPS distribution cabinet is usually used to connect with the corresponding equipment to maintain the stability of the power supply. The UPS distribution cabinet connects the corresponding equipment through different buses of each interface to achieve power transmission. Therefore, the wiring information of each interface in the UPS distribution cabinet can be obtained through the wiring record of the corresponding distribution cabinet in the computer room management system, including the different bus numbers of each interface and the numbers of all devices connected to each bus, and then the equipment parameter data can be collected by installing sensors on the equipment. The current and voltage changes of the equipment directly determine the power demand of the equipment.

[0030] By way of example, in an embodiment of the present invention, a reference data set of parameter items at each collection moment in a timing sequence of operating data of a busbar-connected device is obtained, which also includes: collecting parameter data generated during the operation of each device connected to the UPS bus in a computer room, preprocessing the parameter data, and obtaining parameter items at each collection moment in the timing sequence of operating data.

[0031] Among them, the preprocessing method can be data denoising, missing data interpolation, data format conversion, etc., which can be specifically set according to actual needs, and the embodiment of the present invention does not impose too many restrictions here.

[0032] Specifically, voltage data is collected by installing a voltage sensor on the equipment, and current data is collected by installing a current sensor; the collection frequency of the sensor can be set to once per second, which can be set according to actual needs. A voltage parameter value and a current parameter value are obtained at each collection moment, and the parameter values ​​are preprocessed to obtain parameter items in the operation data time series sequence. The parameter items at each collection moment in the operation data time series sequence correspond to each other one by one.

[0033] It needs to be further explained that in the 9th issue of Computer Age in 2023, there is an article entitled "Research on Time Series Prediction Method Based on Historical Trends and Forecast Errors". The adaptive prediction of time series based on historical trends and prediction errors (Historical Trends Forecast Errors, referred to as HTFE) algorithm recorded in it can analyze the trends in recent time series, and obtain the prediction deviation of the current moment by calculating the predicted value and the true value of the previous moment. The prediction error is obtained by multiplying the prediction deviation and the error factor; it is continuously adjusted according to the prediction error and the current value at the current moment, and finally the prediction value of the next moment of the current moment is obtained.

[0034] Therefore, the embodiment of the present invention can predict the required power of the device through the HTFE algorithm.

[0035] However, the conventional HTFE algorithm uses a fixed error factor during the adjustment process. In actual applications, the operating mode of the equipment in the computer room is significantly different during peak and non-peak periods, resulting in different trend changes in the monitored data. The fixed preset error factor is difficult to adapt to these changes. The larger error factor is highly sensitive to new data and can respond quickly to data changes, but it is easy to overfit and ignore long-term trends; the smaller error factor is less sensitive to new data and can better capture long-term trends, but it responds slowly to short-term fluctuations. Therefore, the choice of error factor affects the accuracy of equipment power prediction results and power distribution.

[0036] Based on this, the embodiment of the present invention analyzes the recent data of the current parameter item through the HTFE algorithm, calculates its trend performance, and adjusts the preset error factor based on the trend performance of the parameter item, so as to accurately obtain the predicted value of the parameter item at the next moment and realize the power prediction of the equipment.

[0037] For example, in an embodiment of the present invention, the method for obtaining a reference data set of a parameter item includes the following two possible implementations: In a possible implementation, a historical data set of the parameter item may be obtained, and the number of data in the historical data set of the parameter item is obtained based on the size of a preset reference data set to construct a reference data set of the parameter item.

[0038] The size of the reference data set may be 10, which may be set according to actual needs. The size of the reference data set is the number of parameter items contained in the reference data set, that is, the number of data. The reference data set of the current parameter item finally obtained does not include the current parameter item.

[0039] In this way, the embodiment of the present invention can accurately obtain the change trend from the historical data by acquiring the historical data as the recent data of the current parameter item, thereby accurately obtaining the prediction result.

[0040] In another possible implementation, an equal amount of data may be acquired on both sides of the parameter item based on the size of a preset reference data set to construct a reference data set for the parameter item.

[0041] In this way, the embodiment of the present invention can accurately obtain the data changes before and after the current parameter item by acquiring the parameter item data around the current parameter item as the recent data of the current parameter item, thereby accurately obtaining its historical and future change trends and realizing the prediction of the current parameter item.

[0042] Take the reference data set of a parameter item as an example: the parameter item is voltage, and the size of the reference data set of the current voltage is 10. You can obtain 10 voltage data from the historical data set of the current voltage to construct a reference data set for the current voltage; or you can obtain 5 voltage data on both sides of the current voltage to construct a reference data set for the current voltage.

[0043] After obtaining the reference data set of the parameter item at each acquisition moment based on the above steps, continue to perform the following steps to analyze the trend performance in its reference data set.

[0044] S2: Obtain the fluctuation degree of the parameter item, and calculate the trend of each parameter item at each collection time based on the fluctuation degree.

[0045] It should be noted that there are various devices in the computer room, and their operating models may have different peak periods, non-peak periods and stable periods. For example, the recent data changes of the server CPU in the computer room are relatively significant, which may indicate that the user usage or access volume has increased or decreased significantly, resulting in the server equipment experiencing rapid load fluctuations.

[0046] Based on this, the embodiment of the present invention can obtain the fluctuation degree of the device by acquiring the recent data changes at the current moment. If the recent data fluctuation degree of the parameter item at the current collection moment is large, it means that the operating status of the device at the current moment shows obvious load trend changes.

[0047] For example, in an embodiment of the present invention, a method for obtaining the degree of fluctuation of a parameter item includes: normalizing the sum of squares of differences between the parameter item and each data in a reference data set to obtain the degree of fluctuation of the parameter item.

[0048] It can be understood that if the sum of the squares of the differences between a parameter item at a collection moment and the data in its reference data set is larger, it means that the difference between the parameter item and the parameter items in its reference data set is larger, the degree of fluctuation is larger, and the corresponding fluctuation trend is more obvious.

[0049] It should be further explained that the greater the fluctuation of the parameter item at the current collection time, the more significant the data changes in the recent data, but it also means that the dispersion in the recent data is greater. If there are multiple trend changes in the recent data, it will also affect the dispersion and fluctuation. For example, a surge or sharp decrease in user access will cause a significant increase or decrease in the load of network equipment.

[0050] Based on this, in order to further determine whether the data fluctuations in recent data are fluctuations with consistent trends, the embodiment of the present invention obtains the estimated value of the current parameter item by weighting each parameter item in the reference data set of the current parameter item. According to the deviation between the estimated value of the current parameter item and the true value, it is determined whether there is a significant trend change in the recent data of the current parameter item. If the recent data shows a significant increasing or decreasing trend, the estimated value of the current parameter item is closer to the true value.

[0051] For example, in the embodiment of the present invention, the trend of each parameter item at each collection time is determined, and the specific relationship can be referred to as follows: ; is the first The trend of the parameter items, is the first The fluctuation degree of the parameter items, is the number of data in the reference dataset, For the The timestamp of the collection moment, For the The timestamp of the collection moment, For the The first collection time The value of the parameter item, is the first The value of the parameter item, is an exponential function with base e.

[0052] In the above formula, The difference between the timestamp of the collection time of each parameter item in the reference data set of parameter items and the timestamp of the collection time of the initial parameter item in the reference data set is its weight. The closer the parameter item in the reference data set is to the i-th collection time, the greater its weight.

[0053] represents the i-th acquisition time. The estimated value of the parameter term, if the If there is an obvious increasing or decreasing trend in the reference data set of the parameter item, then the value is The closer the values ​​of the parameters are, the closer the The greater the fluctuation of the parameter item, the greater the amplitude of the trend change, that is, the greater the fluctuation of the parameter item at the i-th acquisition time. The stronger the trend of the parameter item.

[0054] After obtaining the trend of each parameter item at each collection moment based on the above steps, continue to perform the following steps.

[0055] S3: Normalize the product of the predicted deviation, preset error factor and trend of the parameter item to obtain the error factor of the parameter item.

[0056] The preset error factor may be set to 0.5; the value of the preset error factor may be set in the range of 0 to 1 according to actual needs, and the embodiment of the present invention does not impose too many restrictions on this.

[0057] It should be noted that the operation mode of the equipment in the computer room is significantly different during peak and non-peak periods, resulting in different trend changes in the data, and fixed error factors are difficult to adapt to such changes. The embodiment of the present invention analyzes the recent data of the parameter items based on the above steps to obtain the trend of the parameter items, and adjusts the preset error factors according to the trend of the parameter items, so as to accurately obtain the error factors that meet the parameter items at the current moment.

[0058] By way of example, in an embodiment of the present invention, a method for obtaining a prediction deviation of a parameter item includes: obtaining an initial prediction value of the parameter item through a prediction algorithm; and recording the absolute value of the difference between the initial prediction value of the parameter item and the numerical value as the prediction deviation of the parameter item.

[0059] For example, when the initial prediction value of the parameter item at the next collection moment of the current collection moment is calculated by the HTFE algorithm, the prediction deviation of the current collection moment can be obtained by the difference between the initial prediction value and the true value of the parameter item at the previous collection moment of the current collection moment; the prediction error is obtained by multiplying the prediction deviation by a preset error factor; and the initial prediction value of the parameter item at the next collection moment of the current collection moment is finally obtained by continuously adjusting according to the prediction error and the value of the parameter item at the current collection moment.

[0060] The specific steps of calculating the initial predicted values ​​of the parameter items at each acquisition time by using the HTFE algorithm can be implemented by the existing technology, and the embodiments of the present invention will not be described in detail here.

[0061] It should be noted that the HTFE algorithm mainly realizes the prediction of the next collection moment of the time series by adjusting the prediction deviation of the previous collection moment. Therefore, when calculating the initial prediction value of the first parameter item in the historical data set of the current parameter item, there is no prediction error of the previous collection moment to adjust.

[0062] Based on this, when the initial prediction value of the first parameter item is obtained through the prediction algorithm, a prediction algorithm such as a moving average method and an exponential smoothing method can be used. The specific setting can be made according to actual needs, and the embodiment of the present invention does not make too many restrictions here; the prediction algorithm for calculating the initial prediction values ​​of subsequent other parameter items can use the HTFE algorithm.

[0063] Among them, the specific steps of obtaining the predicted value of the parameter item by the moving average method and the exponential smoothing method can be obtained through the existing technology, and the embodiment of the present invention will not be described in detail here.

[0064] After obtaining the prediction deviation of each parameter item based on the above steps, the error factor of the parameter item can be obtained by the following formula.

[0065] For example, the error factor of the parameter item is determined by normalizing the product of the prediction deviation of the parameter item, the preset error factor and the trend, and the specifics can be seen in the following relationship: ; is the i-th collection time The error factor of the parameter term, is the preset error factor, is the i-th collection time The initial predicted values ​​of the parameters, is the i-th collection time The value of the parameter item, is the i-th collection time The trend of the parameter items, is the normalization function.

[0066] In the above formula, Indicates the i-th collection time The prediction deviation of the parameter term.

[0067] It represents the correction weight of the preset error factor. The greater the deviation between the predicted value of the current parameter item and the actual value, the more the preset error factor is not adapted to the data changes of the parameter item at the current collection moment, resulting in lower prediction accuracy. At this time, if the trend of the parameter item is greater, it is necessary to increase the preset error factor to improve the sensitivity of the prediction algorithm to new data.

[0068] After the error factors of the parameter items at the acquisition time are obtained based on the above steps, the predicted values ​​of the parameter items at the next time can be obtained based on the error factors of the parameter items at the acquisition time in the HTFE algorithm.

[0069] S4: The error factor is used in the HTFE algorithm to obtain the predicted value of the parameter item at the next collection moment, and the power required by the device at the next collection moment is obtained by multiplying the predicted values ​​of each parameter item to achieve power distribution.

[0070] Among them, the specific steps of using the error factor in the HTFE algorithm to obtain the predicted value of the parameter item at the next acquisition moment are similar to the steps of calculating the initial predicted value of the parameter item through the HTFE algorithm mentioned above, and the specific implementation method is recorded in the prior art, so the embodiment of the present invention will not be described in detail here.

[0071] It should be noted that the busbar of the power distribution cabinet may have multiple devices connected to it, so it is necessary to analyze the prediction results of the electrical parameter data of all devices on each busbar, so as to predict in real time the required power of each device on the busbar at the next acquisition time. Based on the prediction results of the total power required for each busbar, the power transmission power of different busbars of the interface is adjusted to achieve the effect of optimizing power distribution and ensure that the equipment can reduce unnecessary energy consumption during peak and non-peak hours.

[0072] For example, in an embodiment of the present invention, the power required by the device at the next acquisition moment is obtained by multiplying the predicted values ​​of each parameter item to achieve power distribution, including: transmitting the power required by each device to the corresponding device through the corresponding bus.

[0073] It can be understood that the parameter items are current and voltage, and the predicted power of the device can be obtained by multiplying the predicted current value and the predicted voltage value, and the allocation of power resources can be achieved based on the predicted power of the device.

[0074] It needs to be further explained that the power supply of the computer room is one of the core components for the normal operation of an enterprise. If there is an abnormality in the power supply of the computer room, there may be a major safety hazard.

[0075] Based on this, in the embodiment of the present invention, after realizing power distribution, it also includes: performing abnormal monitoring and early warning on the parameter items of each device at each collection moment.

[0076] Specifically, the abnormality monitoring result of the equipment can be obtained by setting a corresponding abnormality threshold for each parameter item and comparing the value of the parameter item with the abnormality threshold.

[0077] The abnormal threshold may be specifically set according to parameters of the device, and the embodiment of the present invention does not impose too many limitations on this.

[0078] For example, in an embodiment of the present invention, abnormal monitoring and early warning are performed on the parameter items of each device at each collection moment, and then the method further includes: associating and storing the values ​​of the parameter items of each device at each collection moment, the required power and the abnormal monitoring results.

[0079] After the power distribution and abnormality monitoring of the equipment are implemented based on the above-mentioned embodiments, the relevant data can be associated and stored to facilitate data analysis by the staff.

[0080] It can be seen that in the embodiment of the present invention, when implementing power distribution of the power supply system of the computer room, a reference data set of parameter items at each acquisition moment in the time series of the operation data of the bus connection device can be obtained, and the parameter items include current and voltage; ; , , are the i-th collection time and the The trend, fluctuation and value of each parameter. is the number of data items in the reference dataset, , Respectively , The timestamp of the collection moment, For the The collection time The value of the parameter item, is an exponential function with e as the base; the product of the predicted deviation of the parameter item, the preset error factor and the trend is normalized to obtain the error factor of the parameter item; the error factor is used in the HTFE algorithm to obtain the predicted value of the parameter item at the next collection moment, and the power required by the equipment at the next collection moment is obtained by multiplying the predicted values ​​of each parameter item to realize power distribution.

[0081] In this way, the embodiment of the present invention predicts the power demand of the equipment through the HTFE algorithm, and adjusts the power of the equipment based on the predicted value, which effectively improves the accuracy of power distribution and reduces resource waste. In this process, the embodiment of the present invention takes into account that the fixed error factor cannot adapt to the equipment operation data with various changing trends, resulting in low accuracy of the obtained prediction results; based on this, the embodiment of the present invention obtains the trend changes of the recent data of the equipment parameter items at each collection time, and adjusts the error factor according to the trend changes, so as to accurately obtain the power demand prediction value of the equipment, effectively improving the accuracy of power distribution of the power supply system in the computer room. The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for distributing power in a computer room power supply system, characterized in that: include: Acquire a reference data set of parameter items at each acquisition moment in a time series of operation data of a bus connection device, wherein the parameter items include current and / or voltage; ； , , are the first The trend, fluctuation and value of each parameter. is the number of data in the reference dataset, , Respectively , The timestamp of the collection moment, For the The first collection time The value of the parameter item, is an exponential function with base e; The product of the predicted deviation, the preset error factor and the trend of the parameter item is normalized to obtain the error factor of the parameter item; In the HTFE algorithm, the error factor is used to obtain the predicted value of the parameter item at the next collection moment, and the power required by the device at the next collection moment is obtained by multiplying the predicted values ​​of each parameter item to achieve power distribution.

2. The power distribution method of a computer room power supply system according to claim 1, characterized in that: The step of obtaining a reference data set of parameter items at each acquisition moment in the time series of the operation data of the bus connection device also includes: Collect parameter data generated during the operation of each device connected to the UPS bus in the computer room, pre-process the parameter data, and obtain parameter items at each collection moment in the operating data time series.

3. The power distribution method of a computer room power supply system according to claim 1, characterized in that: The method for obtaining the reference data set of the parameter item includes: Get the historical data set of parameter items; The number of data is obtained in the historical data set of the parameter item based on the size of the preset reference data set to construct a reference data set for the parameter item.

4. The power distribution method of a computer room power supply system according to claim 1, characterized in that: The method for obtaining the fluctuation degree of the parameter item includes: The sum of squares of the differences between the parameter item and each data in its reference data set is normalized to obtain the degree of fluctuation of the parameter item.

5. The power distribution method of a computer room power supply system according to claim 1, characterized in that: The method for obtaining the prediction deviation of the parameter item includes: The initial predicted value of the parameter item is obtained through the prediction algorithm; the absolute value of the difference between the initial predicted value of the parameter item and the numerical value is recorded as the prediction deviation of the parameter item.

6. The power distribution method of a computer room power supply system according to claim 1, characterized in that: The method of obtaining the power required by the device at the next acquisition moment by multiplying the predicted values ​​of each parameter item to achieve power distribution includes: The power required by each device is transmitted to the corresponding device through the corresponding bus.

7. The power distribution method of a computer room power supply system according to claim 1, characterized in that: The power distribution is achieved, and then further comprises: Abnormal monitoring and early warning are carried out on the parameter items of each device at each collection moment.

8. The power distribution method of a computer room power supply system according to claim 7, characterized in that: The abnormal monitoring and early warning of the parameter items of each device at each collection moment also includes: The values ​​of the parameter items of each device at each collection moment, the required power and the abnormal monitoring results are associated and stored.

Images