Communication power supply control method for multi-energy power supply

Abstract

The invention relates to the field of multi-energy power supply control, in particular to a multi-energy power supply communication power supply control method. The method comprises the following steps: firstly, acquiring electricity consumption data of each time period every day in different periods and generating capacity data of different types of power generation facilities, and acquiring predicted meteorological data and actual meteorological data of different meteorological types every day; and predicting the power consumption of each time period of the next day, and predicting the power generation amount of each time period of the next day according to the power generation amount data of each power generation facility in the same time period in the current day and the difference between the predicted meteorological data and the actual meteorological data of the meteorological type on which each type of power generation facility depends. And extracting the insufficient power supply time period in the next day, and controlling the power supply mode of the insufficient power supply time period. According to the invention, the multi-energy power supply communication power supply can be effectively controlled, the power supply stability is ensured, and the final power supply control effect is improved.

Description

Technical Field

[0001] The present invention relates to the field of multi-energy power supply control, and in particular to a communication power supply control method for multi-energy power supply. Background Art

[0002] With the rapid development of communication technology, multi-energy powered communication power control has become the mainstream trend in the industry. This control method effectively integrates multiple power sources such as AC power, solar power generation, wind power generation and energy storage batteries. It can not only improve the stability and reliability of the communication power system, but also significantly improve energy utilization efficiency and reduce operating costs, providing a strong guarantee for the sustainable development of the communication industry.

[0003] In the related technologies, power supply services are mainly implemented through comprehensive dispatching and control of multiple energy sources such as municipal electricity, solar power generation, wind power generation, etc., and relying on energy storage batteries. However, since renewable energy power generation methods such as solar power generation and wind power generation are easily affected by related weather and meteorological conditions, the power supply stability is poor. At the same time, the frequent discharge of energy storage batteries can easily cause the attenuation of battery capacity and service life, which makes it impossible to effectively control the communication power supply powered by multiple energy sources through existing methods, thereby reducing the effect of the final power supply control. Summary of the invention

[0004] In order to solve the technical problem that the existing method cannot effectively control the communication power supply powered by multiple energy sources, thereby reducing the effect of the final power supply control, the purpose of the present invention is to provide a communication power supply control method powered by multiple energy sources, and the technical solution adopted is as follows: The present invention proposes a communication power supply control method for multi-energy power supply, the method comprising: Obtaining electricity consumption data for each period of each day in different cycles within a preset historical time period and power generation data for different types of power generation facilities, and obtaining forecast meteorological data and actual meteorological data for different meteorological types of each day within the preset historical time period, wherein each power generation facility relies on one meteorological type; The last cycle is taken as the current cycle, the cycles other than the current cycle are taken as historical cycles, the last day is taken as the current day, the days other than the current day are taken as historical days, and the fluctuation similarity of each historical cycle is obtained according to the difference in the distribution of all the power consumption data between each historical cycle and the current cycle; based on the fluctuation similarity, the matching historical cycle of the current cycle is screened out from all historical cycles; the degree of deviation of each historical day in the matching historical cycle is obtained according to the difference in the power consumption data of the same time period between each historical day and the current day in the matching historical cycle; based on the degree of deviation, the matching historical day of the current day is screened out from all historical days in the matching historical cycle; according to the change in the power consumption data of each time period in the next historical day of the matching historical day, the power consumption data of the last time period of the current day, and the degree of deviation of the matching historical day, the predicted power consumption of each time period of the next day of the current day is obtained; According to the difference between the predicted meteorological data and the actual meteorological data of each meteorological type on the same day within the preset historical time period, the meteorological deviation degree of each meteorological type is obtained; according to the power generation data of each power generation facility in the same time period of the current day, and the meteorological deviation degree of the meteorological type on which each type of power generation facility depends, the predicted power generation in each time period of the next day of the current day is obtained; According to the difference between the predicted power consumption and the predicted power generation in the same time period of the day after the current day, the power shortage time period of the day after the current day is obtained; according to the predicted power consumption of each time period in each power shortage time period and the number of all time periods, the power supply mode of each power shortage time period is controlled.

[0005] Furthermore, obtaining the fluctuation similarity of each historical period includes: The current cycle or any historical cycle is taken as the target cycle, and the average value of the power consumption data in all time periods on all days in the target cycle is taken as the overall power consumption of the target cycle; The standard deviation of the power consumption data in all time periods of all days in the target cycle is used as the power consumption dispersion of the target cycle; Based on the calculation formula of fluctuation similarity, the fluctuation similarity of each historical period is obtained. The calculation formula of fluctuation similarity is: , in, Indicates Similarity of fluctuations in historical cycles; Indicates The overall electricity consumption in the historical period; Indicates the overall power consumption of the current cycle; Indicates The dispersion of electricity consumption in a historical period; Indicates the power consumption dispersion of the current cycle; Represents the normalization function.

[0006] Furthermore, the filtering out the matching historical periods of the current period from all historical periods includes: The historical period corresponding to the maximum value of fluctuation similarity is taken as the matching historical period of the current period.

[0007] Furthermore, obtaining the deviation degree of each historical day in the matching historical period includes: Match any historical day in the historical period as the target historical day; The sequence formed by sorting the power consumption data of all time periods in the target historical day in chronological order is used as the first power consumption sequence of the target historical day, and the sequence formed by sorting the power consumption data of all time periods in the current day in chronological order is used as the second power consumption sequence of the current day; The mean square error between the first electricity consumption sequence and the second electricity consumption sequence is normalized and used as the degree of deviation of the target historical day.

[0008] Furthermore, the step of selecting the matching historical day of the current day from all the historical days in the matching historical period includes: The historical day corresponding to the maximum value of the deviation degree in the matching historical period is used as the matching historical day of the current day.

[0009] Further, obtaining the predicted power consumption for each time period of the next day of the current day includes: The next historical day of the matching historical day is used as a reference historical day, any time period in the reference historical day is used as a target time period, and the difference between the power consumption data of the target time period and the adjacent previous time period is used as the power consumption change of the target time period; Based on the calculation formula for predicted power consumption, the predicted power consumption for each period of the next day of the current day is obtained. The calculation formula for predicted power consumption is: , , in, Indicates the day after the current day. Forecasted electricity consumption for each period; Indicates the day after the current day. The initial power consumption of each period; Indicates the degree of deviation from matching historical days; Indicates the electricity consumption data for the last period of the current day; Indicates the reference historical day The change in electricity consumption during a period of time.

[0010] Further, obtaining the meteorological deviation degree of each meteorological type includes: Taking any meteorological type as the target meteorological type, taking the absolute value of the difference between the predicted meteorological data and the actual meteorological data of the target meteorological type on the same day within a preset historical time period as the initial deviation degree of the target meteorological type on each day; The average value of the initial deviations of the target meteorological type on all days is normalized to obtain the meteorological deviation of the target meteorological type.

[0011] Further, obtaining the predicted power generation for each time period of the next day of the current day includes: Based on the calculation formula for predicted power generation, the predicted power generation for each period of the next day of the current day is obtained. The calculation formula for predicted power generation is: , in, Indicates the day after the current day. Forecasted power generation for each period; Indicates the current day The first Electricity generation data for various types of power generation facilities; Indicates The degree of meteorological deviation of the meteorological type on which the type of power generation facility depends; The number representing the type of power generation facility.

[0012] Further, obtaining the power shortage time period of the next day of the current day includes: In the next day after the current day, the time period when the predicted power generation is less than the predicted power consumption is used as the time period to be analyzed, and the time period formed by the continuous time periods to be analyzed is used as the insufficient power supply time period.

[0013] Furthermore, the controlling of the power supply mode in each power shortage time period includes: Taking any power shortage time period in the next day after the current day as the target power shortage time period, taking the sum of the predicted power consumption of all time periods in the target power shortage time period as the numerator, taking the total power of the energy storage battery as the denominator, and taking the ratio as the power consumption proportion of the target power shortage time period; The power consumption proportion in the target power shortage time period and the number of all time periods in the target power shortage time period are integrated and normalized to obtain the power supply necessity of the energy storage battery in the target power shortage time period; When the power supply necessity of the energy storage battery during the target power supply shortage time period is greater than the preset necessity threshold, the power supply mode is switched from power supply by the power generation facility to power supply by the energy storage battery during the target power supply shortage time period; otherwise, the power supply mode is switched from power supply by the power generation facility to power supply by the mains during the target power supply shortage time period.

[0014] The present invention has the following beneficial effects: The present invention takes into account that the existing methods cannot effectively control the communication power supply powered by multiple energy sources, reducing the effect of the final power supply control. First, the power consumption data of each time period of each day in different cycles within a preset historical time period and the power generation data of different types of power generation facilities are obtained, and the predicted meteorological data and actual meteorological data of different meteorological types of each day are obtained. Since the present invention needs to predict future power consumption based on historical power consumption data, and predict future power generation based on historical power generation data, it is convenient to accurately predict the power supply shortage of power generation facilities in the subsequent period, and switch the power supply mode in time to ensure power supply stability. At the same time, considering that the user's power consumption is affected by various factors such as the environment and season, resulting in a certain similarity in power consumption in different cycles, multiple cycles are first divided into current cycles and historical cycles, and multiple days are divided into current days and historical days. The fluctuation similarity reflects the similarity of the fluctuation change of power consumption data in time series between each historical cycle and the current cycle, thereby screening out matching historical cycles with similar fluctuation change characteristics of power consumption data in the current cycle, and then through The degree of deviation reflects the difference in electricity consumption data for the same period between each day in the matching historical cycle and the current day in more detail, and selects the historical days that are consistent with the electricity consumption data for each period of the current day, and then obtains the predicted electricity consumption for each period of the next day, so as to achieve accurate prediction of electricity consumption for each period of the next day. When predicting the power generation of power generation facilities, the meteorological type on which each type of power generation facility depends can directly affect the power generation of the power generation facility. The greater the difference between the predicted meteorological data and the actual meteorological data of the meteorological type, the greater the interference to the power generation prediction of the power generation facility that depends on the meteorological type. Therefore, the deviation between the predicted meteorological data and the actual meteorological data of each meteorological type can be first reflected through the meteorological deviation degree, so as to obtain the predicted power generation for each period of the next day of the current day, and achieve accurate prediction of the power generation for each period of the next day, and then accurately extract the power supply shortage period in the next day, and realize timely switching control of the power supply mode in the power supply shortage period, so as to ensure stable power supply, reduce the frequent discharge of energy storage batteries, and improve the effect of final power supply control. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 A flow chart of a communication power supply control method for multi-energy power supply provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation method, structure, features and effects of a multi-energy power supply communication power control method proposed by the present invention in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0018] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0019] The specific scheme of the communication power supply control method with multi-energy power supply provided by the present invention is described in detail below with reference to the accompanying drawings.

[0020] See also Figure 1 , which shows a flow chart of a communication power supply control method for multi-energy power supply provided by an embodiment of the present invention, the method comprising: Step S1: Obtain the electricity consumption data for each time period of each day in different cycles within a preset historical time period and the power generation data of different types of power generation facilities, and at the same time obtain the predicted meteorological data and actual meteorological data of different meteorological types for each day within the preset historical time period, wherein each power generation facility depends on one meteorological type.

[0021] In a multi-energy power supply system, communication power is mainly composed of various types of renewable energy such as solar energy and wind energy, and relies on energy storage batteries and municipal power. The usual power supply strategy is to give priority to the use of renewable energy. If renewable energy cannot fully meet the power demand, energy storage batteries will be used instead, and finally municipal power will be considered as a supplement.

[0022] The embodiment of the present invention first uses power monitoring equipment such as smart meters in a multi-energy power supply system to collect the user's electricity consumption data for each time period of each day in different cycles within a preset historical time period, and collects the power generation data of different types of power generation facilities for each time period of each day in different cycles within the preset historical time period, wherein the preset historical time period is set to three months, the length of each cycle is set to one week, i.e., seven days, and the length of each time period is set to one hour, that is, a day is divided into 24 time periods, and the electricity consumption data and power generation data of each time period respectively represent the electric energy consumed and the electric energy generated in the time period, in kilowatt-hours.

[0023] The power generation facilities in the embodiments of the present invention specifically refer to power generation facilities using renewable energy. Different types of power generation facilities include, for example, wind turbine generators using wind energy to generate electricity and solar panels using solar energy to generate electricity.

[0024] At the same time, since the power generation of power generation facilities is directly affected by weather and meteorology, the embodiment of the present invention also needs to use the meteorological service API to obtain the predicted meteorological data and actual meteorological data of different meteorological types for each day in a preset historical time period, so that the weather and meteorological factors can be taken into account when subsequently predicting the power generation, thereby improving the accuracy of the power generation prediction. Among them, there is a certain deviation between the predicted meteorological data and the actual meteorological data of a certain meteorological type on a certain day. Different meteorological types include, for example, light radiation intensity and wind speed.

[0025] It should be noted that the meteorological type analyzed in the embodiment of the present invention is directly related to the power generation facilities, that is, each type of power generation facility depends on a meteorological type. For example, a wind turbine generator that uses wind energy to generate electricity depends on wind speed, while a solar panel that uses solar energy to generate electricity depends on light radiation intensity.

[0026] Step S2: take the last cycle as the current cycle, take the other cycles except the current cycle as the historical cycles, take the last day as the current day, take the other days except the current day as the historical days, and obtain the fluctuation similarity of each historical cycle based on the difference in the distribution of all electricity consumption data between each historical cycle and the current cycle; based on the fluctuation similarity, filter out the matching historical cycle of the current cycle from all historical cycles; based on the difference in electricity consumption data in the same time period between each historical day and the current day in the matching historical cycle, obtain the degree of deviation of each historical day in the matching historical cycle; based on the degree of deviation, filter out the matching historical day of the current day from all historical days in the matching historical cycle; based on the change in electricity consumption data in each time period in the next historical day of the matching historical day, the electricity consumption data in the last time period of the current day, and the degree of deviation of the matching historical day, obtain the predicted electricity consumption in each time period of the next day of the current day.

[0027] Since the present invention needs to predict future power consumption based on historical power consumption data, and predict future power generation based on historical power generation data, it is convenient to accurately predict the power supply shortage of power generation facilities in the future, so as to switch the power supply mode in time to ensure power supply stability. At the same time, considering that the power consumption of users is affected by various factors such as environment and season, the power consumption in different cycles has a certain similarity. Therefore, in order to accurately predict future power consumption in the future, the embodiment of the present invention first takes the last cycle as the current cycle, takes other cycles except the current cycle as historical cycles, takes the last day as the current day, and takes other days except the current day as historical days. Then, it is necessary to preliminarily select historical cycles with similar fluctuation characteristics of power consumption data in the current cycle from all historical cycles, so as to accurately predict power consumption in the future. Therefore, the difference in the distribution of all power consumption data between each historical cycle and the current cycle can be analyzed first, and the similarity of the fluctuation change of power consumption data in time series between each historical cycle and the current cycle can be reflected by the obtained fluctuation similarity. Subsequently, based on the fluctuation similarity, the historical cycle with the most similar fluctuation characteristics of power consumption data in the current cycle can be accurately selected.

[0028] Preferably, in one embodiment of the present invention, the method for obtaining the fluctuation similarity of each historical period specifically includes: The current cycle or any historical cycle is taken as the target cycle, and the average of the electricity consumption data of all time periods of all days in the target cycle is taken as the overall electricity consumption of the target cycle. The overall electricity consumption reflects the overall level of electricity consumption data of all time periods of all days in the target cycle.

[0029] The standard deviation of the electricity consumption data in all time periods of all days in the target cycle is taken as the electricity consumption dispersion of the target cycle, and the electricity consumption dispersion reflects the degree of dispersion of the electricity consumption data in all time periods of all days in the target cycle.

[0030] The same method as above can be used to obtain the overall power consumption and power consumption dispersion of the current cycle and any historical cycle. Then, based on the calculation formula of fluctuation similarity, the fluctuation similarity of each historical cycle can be obtained. The calculation formula of fluctuation similarity is: , in, Indicates Similarity of fluctuations in historical cycles; Indicates The overall electricity consumption in the historical period; Indicates the overall power consumption of the current cycle; Indicates The dispersion of electricity consumption in a historical period; Indicates the power consumption dispersion of the current cycle; Represents the normalization function.

[0031] in, To reflect the The difference in overall electricity consumption between the historical cycle and the current cycle, The smaller the The closer the overall distribution level of electricity consumption data between the historical cycle and the current cycle is, the more similar the fluctuation characteristics of the two are. To reflect the The difference in power consumption dispersion between the historical cycle and the current cycle, The smaller the The discrete characteristics of electricity consumption data between the historical cycle and the current cycle are relatively similar, which means that the more similar the fluctuation characteristics of the two are, the more likely it is that the Perform negative correlation normalization and limit the calculation results to within the range.

[0032] In one embodiment of the present invention, the normalization processing can be specifically, for example, maximum and minimum value normalization processing, and the normalization in subsequent steps can all adopt maximum and minimum value normalization processing. In other embodiments of the present invention, other normalization methods can be selected according to the specific range of numerical values, which will not be described in detail.

[0033] The greater the fluctuation similarity of each historical period, the more similar the fluctuation change characteristics of the electricity consumption data of the historical period and the electricity consumption data of the current period are. Therefore, based on the fluctuation similarity, the historical period with the most similar fluctuation change characteristics to the electricity consumption data of the current period can be preliminarily screened out from all historical periods, that is, the matching historical period of the current period. This facilitates the subsequent screening of historical days with consistent electricity consumption data in each time period of the current day from all historical days in the matching historical period, thereby improving the accuracy of subsequent electricity consumption predictions for each time period of the future day, and thereby improving the control effect of communication power supply for multi-energy power supply.

[0034] Preferably, in one embodiment of the present invention, the historical period corresponding to the maximum value of the fluctuation similarity is used as the matching historical period of the current period.

[0035] In the subsequent steps of the embodiment of the present invention, it is necessary to predict the electricity consumption for the day after the current day based on the electricity consumption data of the next day of the historical day that is most consistent with the electricity consumption data of the current day in the matching historical period, so as to improve the accuracy of the electricity consumption prediction. The smaller the difference in electricity consumption data for the same time period between a historical day and the current day in the matching historical period, the more consistent the electricity consumption data between the historical day and the current day in time series. Therefore, the difference in electricity consumption data for the same time period between each historical day and the current day in the matching historical period can be first analyzed, and the difference in electricity consumption data for the same time period between each day in the matching historical period and the current day can be reflected in more detail by obtaining the degree of deviation. Subsequently, based on the degree of deviation, the historical days that are most consistent with the electricity consumption data for each time period of the current day can be accurately screened out from all historical days in the matching historical period, so as to improve the accuracy of the electricity consumption prediction for each time period of the day after the current day.

[0036] Preferably, in one embodiment of the present invention, the method for obtaining the degree of deviation of each historical day in the matching historical period specifically includes: Any historical day in the matching historical cycle is taken as the target historical day, and the sequence formed by sorting the electricity consumption data of all time periods in the target historical day in chronological order is taken as the first electricity consumption sequence of the target historical day, and the sequence formed by sorting the electricity consumption data of all time periods in the current day in chronological order is taken as the second electricity consumption sequence of the current day.

[0037] The mean square error between the first electricity consumption sequence and the second electricity consumption sequence is normalized and used as the degree of deviation of the target historical day.

[0038] As an example, in one embodiment of the present invention, the expression of the deviation degree of the target historical day may be specifically, for example, as follows: , in, Indicates the degree of deviation from the target historical day; Represents the first electricity consumption sequence of the target historical day; Indicates the second electricity consumption sequence of the current day; represents the mean square error between the first power consumption sequence and the second power consumption sequence; Represents the normalization function.

[0039] in, The larger the value is, the greater the difference in electricity consumption data between the target historical day and the current day in the same period is, which further indicates that the electricity consumption data of each period of the target historical day deviates more from the electricity consumption data of each period of the current day, and Normalize the calculation results to within the range.

[0040] The same method as above can be used to obtain the degree of deviation of each historical day in the matching historical cycle. The smaller the deviation of a historical day in the matching historical cycle, the more consistent the electricity consumption data of the historical day is with the electricity consumption data of the current day in time series. Therefore, based on the degree of deviation, the historical day that is most consistent with the electricity consumption data of each time period on the current day can be screened out from all historical days in the matching historical cycle, that is, the matching historical day of the current day. Subsequently, based on the electricity consumption data of each time period on the next day of the matching historical day, the electricity consumption of each time period on the next day of the current day can be accurately predicted.

[0041] Preferably, in one embodiment of the present invention, the historical day corresponding to the maximum value of the deviation degree in the matching historical period is used as the matching historical day of the current day.

[0042] Since the fluctuation characteristics of the electricity consumption data between the matching historical day and the current day are most similar, and the electricity consumption data will not change significantly in a short period of time, the change characteristics of the electricity consumption data between the next day of the matching historical day and the next day of the current day are also similar. Based on the changes in the electricity consumption data of each time period in the next historical day of the matching historical day and the electricity consumption data of the last time period of the current day, the electricity consumption data of each time period of the next day of the current day can be predicted. While predicting, the degree of deviation from the matching historical day is taken into account to improve the fault tolerance for the subsequent analysis of power supply shortages of power generation facilities.

[0043] Preferably, in one embodiment of the present invention, the method for obtaining the predicted power consumption for each time period of the next day of the current day specifically includes: The next historical day of the matching historical day is taken as the reference historical day, and any time period in the reference historical day is taken as the target time period. The difference in electricity consumption data between the target time period and the adjacent previous time period is taken as the electricity consumption change in the target time period. The electricity consumption change is used to reflect the change in electricity consumption data in the target time period relative to the electricity consumption data in the adjacent previous time period, providing a data basis for subsequent electricity consumption prediction.

[0044] It should be noted that the previous time period adjacent to the first time period of the reference historical day is the day before the reference historical day, that is, the last time period of the matching historical day.

[0045] Then, based on the calculation formula for predicted power consumption, the predicted power consumption for each period of the next day is obtained. The calculation formula for predicted power consumption is: , , in, Indicates the day after the current day. Forecasted electricity consumption for each period; Indicates the day after the current day. The initial power consumption of each period; Indicates the degree of deviation from matching historical days; Indicates the electricity consumption data for the last period of the current day; Indicates the reference historical day The change in electricity consumption during a period of time.

[0046] in, Reflects the period from the last period of the current day to the first period of the next day. Time period, electricity consumption data for the last time period of the current day The cumulative change of and The sum of the values ​​is initially taken as the first At the same time, in order to improve the fault tolerance of subsequent detection of insufficient power supply periods of power generation facilities and ensure the stability of power supply, the deviation degree of matching historical days is used , appropriately increase the next day of the current day Initial power consumption in each period ,and The larger the value, the more inconsistent the electricity consumption data between the historical day and the current day is. The higher the adjustment, the greater the degree.

[0047] Step S3: According to the difference between the predicted meteorological data and the actual meteorological data of each meteorological type on the same day within the preset historical time period, the meteorological deviation degree of each meteorological type is obtained; according to the power generation data of each power generation facility in the same time period of the current day, and the meteorological deviation degree of the meteorological type on which each type of power generation facility depends, the predicted power generation in each time period of the next day of the current day is obtained.

[0048] The above process realizes the prediction of electricity consumption in each time period of the next day after the current day. In order to realize the subsequent accurate prediction of the power supply shortage period of the power generation facilities in the next day after the current day, it is also necessary to predict the power generation in each time period of the next day after the current day. Since the power generation facilities in the embodiments of the present invention all use renewable energy such as wind energy and solar energy to generate electricity, the power generation effect of these power generation facilities is directly affected by weather and meteorology. The greater the difference between the predicted meteorological data and the actual meteorological data of a certain meteorological type, the greater the impact on the power generation prediction of the power generation facilities that rely on this meteorological type. Therefore, the difference between the predicted meteorological data and the actual meteorological data of each meteorological type on the same day within a preset historical time period can be analyzed. The deviation between the predicted meteorological data and the actual meteorological data of each meteorological type is reflected by the obtained meteorological deviation. Subsequently, based on the meteorological deviation, the prediction result of the power generation of the power generation facilities that rely on a certain meteorological type can be adjusted to improve the fault tolerance of the subsequent detection of the power supply shortage period of the power generation facilities, ensure the stability of the power supply, and improve the effect of the final power supply control.

[0049] Preferably, in one embodiment of the present invention, the method for obtaining the meteorological deviation degree of each meteorological type specifically includes: First, any meteorological type is taken as the target meteorological type, and the absolute value of the difference between the predicted meteorological data and the actual meteorological data of the target meteorological type on the same day within the preset historical time period is taken as the initial deviation of the target meteorological type on each day. The larger the initial deviation, the greater the deviation between the predicted meteorological data and the actual meteorological data of the target meteorological type on the same day.

[0050] Then, the average value of the initial deviation of the target meteorological type on all days can be normalized, and the calculation result can be limited to range, thereby obtaining the meteorological deviation degree of the target meteorological type.

[0051] As an example, in one embodiment of the present invention, the expression of the weather deviation degree of the target weather type may be specifically, for example, as follows: , in, Indicates the meteorological deviation degree of the target meteorological type; Indicates that the target weather type is the first Forecast weather data for the day; Indicates that the target weather type is the first Actual weather data for the day; Indicates the number of days in the preset historical time period; Indicates the target weather type in Initial deviation of the day; Represents the normalization function.

[0052] Then, based on the power generation data of each power generation facility in the same period of the current day and the meteorological deviation of the meteorological type on which each type of power generation facility depends, the predicted power generation for each period of the day after the current day can be obtained, thereby realizing the power generation prediction for each period of the day after the current day.

[0053] Preferably, in one embodiment of the present invention, the method for obtaining the predicted power generation in each time period of the next day of the current day specifically includes: Based on the calculation formula of predicted power generation, the predicted power generation for each period of the next day of the current day is obtained. The calculation formula of predicted power generation is: , in, Indicates the day after the current day. Forecasted power generation for each period; Indicates the current day The first Electricity generation data for various types of power generation facilities; Indicates The degree of meteorological deviation of the meteorological type on which the type of power generation facilities depends; The number representing the type of power generation facility.

[0054] The embodiment of the present invention integrates the power generation data of all types of power generation facilities in the same period of the current day. , to predict the power generation in the corresponding period of the next day of the current day. At the same time, in order to improve the fault tolerance of the subsequent detection of insufficient power supply periods of power generation facilities and ensure the stability of power supply, use , appropriately reduce the next day of the current day The results of power generation forecast for each period, and The larger the The greater the impact of the meteorological type on the power generation of a type of power generation facility, the greater the impact on the power generation of that type of power generation facility. The greater the reduction, the greater the reduction in power generation forecast.

[0055] So far, through the above steps, the prediction of electricity consumption and power generation in each period of the next day from the current day has been realized.

[0056] Step S4: According to the difference between the predicted power consumption and the predicted power generation in the same time period on the next day after the current day, obtain the power shortage time period on the next day after the current day; according to the predicted power consumption of each time period in each power shortage time period and the number of all time periods, control the power supply mode of each power shortage time period.

[0057] Since power generation facilities using renewable energy are easily affected by weather, the power generation may be insufficient to meet the power consumption. In order to ensure stable power supply, the power supply mode needs to be switched. Therefore, we can first obtain the power supply shortage time period of the next day based on the difference between the predicted power consumption and the predicted power generation in the same period of the next day from the current day, and realize the prediction of the power supply shortage situation of the next day from the current day, so as to facilitate the subsequent timely switching of the power supply mode to ensure stable power supply.

[0058] Preferably, in one embodiment of the present invention, the method for obtaining the power shortage time period of the next day of the current day specifically includes: In the next day after the current day, the time period when the predicted power generation is less than the predicted power consumption is taken as the time period to be analyzed, that is, the time period of insufficient power supply. Then, the time period composed of consecutive time periods to be analyzed is taken as the time period of insufficient power supply.

[0059] It should be noted that, for a single time period to be analyzed, the time periods on both sides thereof are non-time periods to be divided. In this case, the time period to be analyzed is also regarded as a power shortage time period.

[0060] The greater the predicted power consumption in each time period in a power shortage time period and the longer the power shortage time period is, the more the power shortage time period needs energy storage batteries to supply power to ensure stable power supply during the power shortage time period. Therefore, the power supply mode of each power shortage time period can be controlled according to the predicted power consumption in each time period in each power shortage time period and the number of all time periods to improve the final power supply control effect.

[0061] Preferably, in one embodiment of the present invention, the method for obtaining the control of the power supply mode in each power shortage time period specifically includes: First, any power shortage time period in the next day after the current day is taken as the target power shortage time period, the sum of the predicted power consumption of all time periods in the target power shortage time period is taken as the numerator, the total power of the energy storage battery is taken as the denominator, and the ratio is taken as the power consumption proportion of the target power shortage time period, wherein the total power of the energy storage battery is a known value.

[0062] Then, the proportion of electricity consumption in the target power shortage time period and the number of all time periods in the target power shortage time period are integrated and normalized to obtain the power supply necessity of the energy storage battery in the target power shortage time period. The greater the power supply necessity, the longer the power shortage time in the target power shortage time period and the more electricity is required, which means that it is more necessary to use energy storage batteries for power supply to ensure stable power supply.

[0063] In an embodiment of the present invention, the combination of the two can be achieved by calculating the power consumption ratio of the target power shortage time period and the sum or product of the number of all time periods in the target power shortage time period, which is not limited here.

[0064] As an example, in one embodiment of the present invention, the expression of the power supply necessity of the energy storage battery in the target power shortage time period can be specifically, for example, as follows: , in, Indicates the necessity of power supply of energy storage battery during the target power shortage period; Indicates the number of all time periods in the target power shortage time period; Indicates the target power shortage period. Forecasted electricity consumption for each period; Indicates the total power of the energy storage battery; Indicates the proportion of electricity consumption during the target power shortage period; Represents the normalization function.

[0065] At the same time, in order to reduce the frequent discharge of energy storage batteries and avoid the attenuation of their battery capacity and service life, when the power supply necessity of the energy storage battery in the target power shortage time period is greater than the preset necessity threshold, the power supply mode is switched from power supply by power generation facilities to power supply by energy storage batteries during the target power shortage time period. Otherwise, the power supply mode is switched from power supply by power generation facilities to power supply by AC power during the target power shortage time period, wherein the preset necessity threshold is set to 0.4, and the specific value of the preset necessity threshold can also be set by the implementer according to the specific implementation scenario, which is not limited here.

[0066] By using the same method as above, the power supply mode in each power shortage time period in the next day after the current day can be controlled.

[0067] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0068] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A communication power supply control method for multi-energy power supply, characterized in that: The method comprises: Obtain the electricity consumption data for each period of each day in different cycles within a preset historical time period and the power generation data of different types of power generation facilities, and obtain the predicted meteorological data and actual meteorological data of different meteorological types for each day within the preset historical time period, wherein each power generation facility depends on one meteorological type; The last cycle is taken as the current cycle, the cycles other than the current cycle are taken as historical cycles, the last day is taken as the current day, the days other than the current day are taken as historical days, and the fluctuation similarity of each historical cycle is obtained according to the difference in the distribution of all the power consumption data between each historical cycle and the current cycle; based on the fluctuation similarity, the matching historical cycle of the current cycle is screened out from all historical cycles; the degree of deviation of each historical day in the matching historical cycle is obtained according to the difference in the power consumption data of the same time period between each historical day and the current day in the matching historical cycle; based on the degree of deviation, the matching historical day of the current day is screened out from all historical days in the matching historical cycle; according to the change in the power consumption data of each time period in the next historical day of the matching historical day, the power consumption data of the last time period of the current day, and the degree of deviation of the matching historical day, the predicted power consumption of each time period of the next day of the current day is obtained; According to the difference between the predicted meteorological data and the actual meteorological data of each meteorological type on the same day within the preset historical time period, the meteorological deviation degree of each meteorological type is obtained; according to the power generation data of each power generation facility in the same time period of the current day, and the meteorological deviation degree of the meteorological type on which each type of power generation facility depends, the predicted power generation in each time period of the next day of the current day is obtained; According to the difference between the predicted power consumption and the predicted power generation in the same time period on the day after the current day, the power shortage time period on the day after the current day is obtained; according to the predicted power consumption in each time period in each power shortage time period and the number of all time periods, the power supply mode of each power shortage time period is controlled.

2. A communication power supply control method for multi-energy power supply according to claim 1, characterized in that: The method of obtaining the fluctuation similarity of each historical period includes: The current cycle or any historical cycle is taken as the target cycle, and the average value of the power consumption data in all time periods on all days in the target cycle is taken as the overall power consumption of the target cycle; The standard deviation of the power consumption data in all time periods of all days in the target cycle is used as the power consumption dispersion of the target cycle; Based on the calculation formula of fluctuation similarity, the fluctuation similarity of each historical period is obtained. The calculation formula of fluctuation similarity is: ， in, Indicates Similarity of fluctuations in historical cycles; Indicates The overall electricity consumption in the historical period; Indicates the overall power consumption of the current cycle; Indicates The dispersion of electricity consumption in a historical period; Indicates the power consumption dispersion of the current cycle; Represents the normalization function.

3. The method for controlling a communication power supply using multiple energy sources according to claim 1, characterized in that: The matching historical periods of the current period are selected from all historical periods, including: The historical period corresponding to the maximum value of fluctuation similarity is taken as the matching historical period of the current period.

4. The method for controlling a communication power supply using multiple energy sources according to claim 1, characterized in that: The obtaining of the deviation degree of each historical day in the matching historical period includes: Match any historical day in the historical period as the target historical day; The sequence formed by sorting the power consumption data of all time periods in the target historical day in chronological order is used as the first power consumption sequence of the target historical day, and the sequence formed by sorting the power consumption data of all time periods in the current day in chronological order is used as the second power consumption sequence of the current day; The mean square error between the first electricity consumption sequence and the second electricity consumption sequence is normalized and used as the degree of deviation of the target historical day.

5. The method for controlling a communication power supply using multiple energy sources according to claim 1, characterized in that: The matching historical days of the current day are selected from all the historical days in the matching historical period, including: The historical day corresponding to the maximum value of the deviation degree in the matching historical period is used as the matching historical day of the current day.

6. The method for controlling a communication power supply using multiple energy sources according to claim 1, characterized in that: The method of obtaining the predicted power consumption for each period of the next day of the current day includes: The next historical day of the matching historical day is used as a reference historical day, any time period in the reference historical day is used as a target time period, and the difference between the power consumption data of the target time period and the adjacent previous time period is used as the power consumption change of the target time period; Based on the calculation formula for predicted power consumption, the predicted power consumption for each period of the next day of the current day is obtained. The calculation formula for predicted power consumption is: ， ， in, Indicates the day after the current day. Forecasted electricity consumption for each period; Indicates the day after the current day. The initial power consumption of each period; Indicates the degree of deviation from matching historical days; Indicates the electricity consumption data for the last period of the current day; Indicates the reference historical day The change in electricity consumption during a period of time.

7. The method for controlling a communication power supply using multiple energy sources according to claim 1, characterized in that: The obtaining of the meteorological deviation degree of each meteorological type comprises: Taking any meteorological type as the target meteorological type, taking the absolute value of the difference between the predicted meteorological data and the actual meteorological data of the target meteorological type on the same day within a preset historical time period as the initial deviation degree of the target meteorological type on each day; The average value of the initial deviations of the target meteorological type on all days is normalized to obtain the meteorological deviation of the target meteorological type.

8. The method for controlling a communication power supply using multiple energy sources according to claim 1, characterized in that: The method of obtaining the predicted power generation in each time period of the next day of the current day includes: Based on the calculation formula for predicted power generation, the predicted power generation for each period of the next day of the current day is obtained. The calculation formula for predicted power generation is: ， in, Indicates the day after the current day. Forecasted power generation for each period; Indicates the current day The first Electricity generation data for various types of power generation facilities; Indicates The degree of meteorological deviation of the meteorological type on which the type of power generation facility depends; The number representing the type of power generation facility.

9. The method for controlling a communication power supply using multiple energy sources according to claim 1, characterized in that: The obtaining of the power shortage time period of the next day of the current day includes: In the next day after the current day, the time period when the predicted power generation is less than the predicted power consumption is used as the time period to be analyzed, and the time period formed by the continuous time periods to be analyzed is used as the insufficient power supply time period.

10. The method for controlling a communication power supply using multiple energy sources according to claim 1, characterized in that: The controlling of the power supply mode in each power shortage time period includes: Taking any power shortage time period in the next day after the current day as the target power shortage time period, taking the sum of the predicted power consumption of all time periods in the target power shortage time period as the numerator, taking the total power of the energy storage battery as the denominator, and taking the ratio as the power consumption proportion of the target power shortage time period; The power consumption proportion in the target power shortage time period and the number of all time periods in the target power shortage time period are integrated and normalized to obtain the power supply necessity of the energy storage battery in the target power shortage time period; When the power supply necessity of the energy storage battery during the target power supply shortage time period is greater than the preset necessity threshold, the power supply mode is switched from power supply by the power generation facility to power supply by the energy storage battery during the target power supply shortage time period; otherwise, the power supply mode is switched from power supply by the power generation facility to power supply by the AC power supply during the target power supply shortage time period.

Images