New power system load estimation method and system combining multi-dimensional features

Abstract

The present application relates to the field of big data processing, and in particular to a method and system for estimating power load of a new type of power system combined with multi-dimensional features, the method comprising obtaining historical feature information of a target area within N historical evaluation cycles, the historical multi-dimensional feature information comprising historical population information, historical weather information and historical power load, determining the power consumption pattern and population change pattern of the target cycle based on the historical feature information within N historical evaluation cycles; determining the estimated population information of the target area within the target cycle based on the population change pattern, the target cycle being a future time period; obtaining the estimated weather information of the target area within the target cycle; determining the estimated power load of the target area within the target cycle based on the estimated weather information, the estimated population information and the power consumption pattern. The present application has the effect of being able to more accurately estimate the power load.

Description

Technical Field

[0001] The present application relates to the field of big data processing, and in particular to a method and system for estimating power load of a new power system combining multi-dimensional features. Background Art

[0002] Electricity is the main energy source in today's society. Ensuring a stable power supply plays a vital role in ensuring the quality of life of the people and the growth of the national economy. By analyzing the historical power consumption and predicting the future power load, we can understand the changing pattern of power load in a certain area, which makes it easier to carry out sufficient power dispatching before the peak period of power consumption.

[0003] In related technologies, the product output method or the elasticity coefficient method is usually used to predict future electricity load. However, the product output method is mainly based on industrial electricity consumption and is suitable for predicting electricity load in areas with more industrial areas; the elasticity coefficient method is directly related to the growth of national economic output value and is suitable for predicting electricity load from a larger time span, such as a whole year or even two years.

[0004] However, in practice, the electricity load in a short period is often affected by many factors. Therefore, how to more accurately estimate the electricity load in a short period is an urgent problem to be solved. Summary of the invention

[0005] In order to more accurately estimate the power load, the present application provides a method and system for estimating the power load of a new power system that combines multi-dimensional features.

[0006] In the first aspect, the present application provides a new method for estimating power load of a power system combining multi-dimensional features, which adopts the following technical solutions:

[0007] A new power system load estimation method combining multi-dimensional features, including:

[0008] Obtaining historical characteristic information of the target area within N historical evaluation cycles, wherein the historical multidimensional characteristic information includes historical population information, historical weather information, and historical electricity load, where N is greater than 5;

[0009] Based on the historical characteristic information in the N historical evaluation periods, determine the electricity consumption pattern and population change pattern of the target period;

[0010] Determine estimated population information in a target area within a target period based on the population change law, where the target period is a future time period;

[0011] Obtaining estimated weather information for the target area within a target period;

[0012] Based on the estimated weather information, the estimated population information and the electricity consumption pattern, an estimated electricity load of the target area within a target period is determined.

[0013] By adopting the above technical scheme, the power consumption pattern and population change pattern of the target area can be determined through the historical characteristic information of the target area in multiple historical evaluation periods, and the multi-dimensional information of the target area's estimated weather information in the target period, power consumption pattern and the estimated population information of the target area in the target period predicted based on the population change law are combined for prediction, so as to obtain a more accurate estimated power load.

[0014] In a possible implementation manner, determining the power usage pattern of the target period based on the historical feature information in the N historical evaluation periods includes:

[0015] Determine the average daily electricity load per capita based on the historical population information and historical electricity load in the N historical and evaluation periods;

[0016] Based on the historical weather information and historical power load in the N historical and evaluation periods, determining the corresponding relationship between power load and weather, wherein the corresponding relationship between power load and weather includes the corresponding relationship between power load and temperature and the power load growth ratio corresponding to each abnormal weather type;

[0017] The electricity consumption pattern includes the average daily electricity load per capita and the corresponding relationship between the electricity load and the weather.

[0018] In a possible implementation, determining the population change law of the target period based on the historical characteristic information in the N historical evaluation periods includes:

[0019] The historical population information includes daily population totals;

[0020] Based on the historical population information in the N historical evaluation periods, determine the population base and population flow pattern, the population base is the average daily population on regular dates, the population flow pattern includes the net population increase corresponding to each type of key date, and the population change pattern includes the average population base and population flow pattern;

[0021] Accordingly, the step of determining the estimated population information in the target area within the target period based on the population change law includes:

[0022] Determine the distribution information of regular dates and key dates within the target period;

[0023] Based on the population base, the population flow pattern and the distribution information of regular dates and key dates in the target period, the estimated population information of the target area in the target period is determined.

[0024] In one possible implementation, the method further includes:

[0025] For any historical assessment period, historical population information is obtained including:

[0026] Obtain daily mobile phone signaling data of the target area within any of the historical evaluation periods;

[0027] The daily mobile phone signaling data within any of the historical evaluation periods is preprocessed to obtain historical population information, wherein the preprocessing includes data cleaning, data deduplication, and data validity screening.

[0028] In a possible implementation, determining the estimated power load of the target area within a target period based on the estimated weather information, the estimated population information, and the power consumption pattern includes:

[0029] Determining a first benchmark load based on the estimated personnel distribution information and the average daily electricity load per capita;

[0030] Determine a first reference load based on the estimated weather information and the corresponding relationship between the power load and the weather;

[0031] Based on the first reference load and the second reference load, the power load of the target area in a target period is predicted.

[0032] In a possible implementation, determining the estimated power load of the target area in a target period based on the first benchmark load and the first reference load includes:

[0033] determining coefficients n and s based on the first reference load and the second reference load;

[0034] Predicting the power load of the target area within a target period based on the first benchmark load, the second benchmark load and a prediction formula;

[0035] The prediction formula is W=nw1+sw2, where W is the estimated power load, w1 is the first benchmark load, w2 is the first benchmark load, and n+s=1.

[0036] In a possible implementation manner, determining coefficients n and s based on the first reference load and the second reference load includes:

[0037] If the first benchmark load is greater than the second benchmark load, determining a first mean square error based on the population of each regular date in the N historical evaluation periods, and determining n and s based on the first mean square error, wherein n is greater than s;

[0038] If the first benchmark load is less than the second benchmark load, a second mean square error is determined based on the daily average temperature of non-abnormal weather types in the N historical evaluation periods, and n and s are determined based on the second mean square error, where n is less than s.

[0039] In the second aspect, the present application provides a new type of power system load estimation system combining multi-dimensional features, which adopts the following technical solutions:

[0040] A new type of power system load estimation system combining multi-dimensional features, including:

[0041] A historical characteristic information acquisition module is used to acquire historical characteristic information of a target area within N historical evaluation cycles, wherein the historical multi-dimensional characteristic information includes historical population information, historical weather information, and historical power load, and N is greater than 5;

[0042] A rule determination module, used to determine the power consumption rule and population change rule of the target period based on the historical characteristic information in the N historical evaluation periods;

[0043] An estimated population information determination module, used to determine the estimated population information in a target area within a target period based on the population change law, wherein the target period is a future time period;

[0044] An estimated weather information acquisition module is used to acquire the estimated weather information of the target area within a target period;

[0045] The estimated power load determination module is used to determine the estimated power load of the target area within a target period based on the estimated weather information, the estimated population information and the power consumption pattern.

[0046] In a possible implementation, when the rule determination module determines the power usage rule of the target period based on the historical feature information in the N historical evaluation periods, it is specifically used to:

[0047] Determine the average daily electricity load per capita based on the historical population information and historical electricity load in the N historical and evaluation periods;

[0048] Based on the historical weather information and historical power load in the N historical and evaluation periods, determining the corresponding relationship between power load and weather, wherein the corresponding relationship between power load and weather includes the corresponding relationship between power load and temperature and the power load growth ratio corresponding to each abnormal weather type;

[0049] The electricity consumption pattern includes the average daily electricity load per capita and the corresponding relationship between the electricity load and the weather.

[0050] In a possible implementation, when the law determination module determines the population change law of the target period based on the historical feature information in the N historical evaluation periods, it is specifically used to:

[0051] The historical population information includes daily population totals;

[0052] Based on the historical population information in the N historical evaluation periods, determine the population base and population flow pattern, the population base is the average daily population on regular dates, the population flow pattern includes the net population increase corresponding to each type of key date, and the population change pattern includes the average population base and population flow pattern;

[0053] Accordingly, the step of determining the estimated population information in the target area within the target period based on the population change law includes:

[0054] Determine the distribution information of regular dates and key dates within the target period;

[0055] Based on the population base, the population flow pattern and the distribution information of regular dates and key dates in the target period, the estimated population information of the target area in the target period is determined.

[0056] In a possible implementation, the system further includes a historical population information acquisition module. For any historical evaluation period, the historical population information acquisition module is specifically used to:

[0057] Obtain daily mobile phone signaling data of the target area within any of the historical evaluation periods;

[0058] The daily mobile phone signaling data within any of the historical evaluation periods is preprocessed to obtain historical population information, wherein the preprocessing includes data cleaning, data deduplication, and data validity screening.

[0059] In a possible implementation, when the estimated power load determination module determines the estimated power load of the target area within the target period based on the estimated weather information, the estimated population information and the power consumption pattern, it is specifically used to:

[0060] Determining a first benchmark load based on the estimated personnel distribution information and the average daily electricity load per capita;

[0061] Determining a second reference load based on the estimated weather information and the corresponding relationship between the power load and the weather;

[0062] The power load of the target area within a target period is predicted based on the first reference load and the second reference load.

[0063] In a possible implementation, when the estimated power load determination module determines the estimated power load of the target area within the target period based on the first reference load and the first reference load, it is specifically used to:

[0064] determining coefficients n and s based on the first reference load and the second reference load;

[0065] Determine the estimated power load of the target area within the target period based on the first reference load, the second reference load and a prediction formula;

[0066] The prediction formula is W=nw1+sw2, where W is the estimated power load, w1 is the first benchmark load, w2 is the first benchmark load, and n+s=1.

[0067] In a possible implementation, when the estimated power load determination module determines the coefficients n and s based on the first reference load and the second reference load, it is specifically used to:

[0068] If the first benchmark load is greater than the second benchmark load, determining a first mean square error based on the population of each regular date in the N historical evaluation periods, and determining n and s based on the first mean square error, wherein n is greater than s;

[0069] If the first benchmark load is less than the second benchmark load, a second mean square error is determined based on the daily average temperature of non-abnormal weather types in the N historical evaluation periods, and n and s are determined based on the second mean square error, where n is less than s.

[0070] In a third aspect, the present application provides an electronic device, which adopts the following technical solution:

[0071] An electronic device, comprising:

[0072] at least one processor;

[0073] Memory;

[0074] At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the above-mentioned new power system power load estimation method combining multi-dimensional features.

[0075] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution:

[0076] A computer-readable storage medium includes: a computer program that can be loaded by a processor and execute the above-mentioned new power system power load estimation method combining multi-dimensional features.

[0077] In summary, the present application includes at least one of the following beneficial technical effects:

[0078] 1. It is possible to determine the power consumption pattern and population change pattern of the target area through the historical characteristic information of the target area in multiple historical evaluation periods, and combine the multi-dimensional information of the estimated weather information, power consumption pattern and estimated population information of the target area in the target period predicted based on the population change law to obtain a more accurate estimated power load. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] Figure 1 is a flow chart of a method for estimating power load in an embodiment of the present application;

[0080] Figure 2 is a schematic diagram of a process for determining a power usage pattern in an embodiment of the present application;

[0081] Figure 3 This is a schematic diagram of a specific process for estimating power load in an embodiment of the present application;

[0082] Figure 4 It is a logical schematic diagram of the data relationship in the embodiment of the present application;

[0083] Figure 5 is a schematic diagram of the structure of the power load estimation system in an embodiment of the present application;

[0084] Figure 6 It is a schematic diagram of the structure of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0085] The following is combined with Figure 1 -Attached Figure 6 This application is described in further detail.

[0086] After reading this specification, those skilled in the art may make non-creative modifications to this embodiment as needed, but such modifications are protected by patent law as long as they are within the scope of the claims of this application.

[0087] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0088] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0089] An embodiment of the present application provides a method for estimating power load of a new power system combining multi-dimensional features, which is executed by electronic devices, wherein the electronic devices include but are not limited to: mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc., and can also be servers, etc.

[0090] Reference Figure 1 The new power system load estimation method combining multi-dimensional features includes steps S10 to S50, wherein:

[0091] Step S10: Obtain historical characteristic information of the target area within N historical evaluation cycles, where the historical multi-dimensional characteristic information includes historical population information, historical weather information, and historical electricity load, and N is greater than 5.

[0092] For the embodiment of the present application, the target area is an area selected by the user. A year is pre-divided into at least a plurality of equal evaluation cycles. The historical evaluation cycle is a cycle that has ended, wherein the historical characteristic information of each historical evaluation cycle is the actual characteristic information; for example, an evaluation cycle includes the three months of July, August and September, then the historical population information is the actual population information counted after the end of the three months of July, August and September; the historical weather information is also the actual weather information actually counted for the three months of July, August and September; the historical power load is also the actual power load in July, August and September based on the actual power consumption data. Among them, N can be selected by the user or can be a preset value. The number of N is determined based on the number of days in each evaluation cycle. The specific relationship is that the longer the number of days in each evaluation cycle, the smaller N is; the shorter the number of days in each evaluation cycle, the larger N is.

[0093] Step S20: Based on the historical characteristic information in N historical evaluation periods, determine the electricity consumption pattern and population change pattern of the target period.

[0094] For the embodiments of the present application, for a region, its population changes and electricity consumption patterns always have periodic changes; for example, for a tourist area, the population always increases in certain months of the year, so the electricity load will also increase. Similarly, in certain months, the population tends to be stable and the electricity load will also be relatively stable. Specifically, the electricity consumption pattern includes the daily per capita electricity load and the correspondence between the electricity load and the weather. Among them, the daily per capita electricity load is determined based on the historical electricity load and historical population information of each of N historical evaluation periods; the correspondence between the electricity load and the weather is determined based on the historical electricity load and historical weather information of each of N historical evaluation periods.

[0095] Step S30: Determine the estimated population information in the target area within a target period based on the population change law, where the target period is a future time period.

[0096] For the embodiment of the present application, the target period is a time period in the future, which can be an evaluation period or any time period selected by the user. After determining the population change law of the target area, a prediction is made based on the population change law to obtain the estimated population information of the target area within the target period.

[0097] Step S40: Obtain the estimated weather information of the target area within the target period.

[0098] For the embodiment of the present application, the estimated weather information can be predicted, but in the prior art, the time length of the weather information that can be predicted is limited, for example, usually only the weather information within the next month can be predicted. If the length of the target period is three months, only the estimated weather information within one month is used, and the estimated weather information of the other two months of the target period is averaged based on the weather information of the same period of previous years.

[0099] Step S50: Determine the estimated power load of the target area within the target period based on the estimated weather information, the estimated population information and the power consumption pattern.

[0100] For the embodiments of the present application, usually the industrial electricity consumption of a region needs to be predicted based on the production demand planning of each enterprise, but there is always a difference in market selection between the actual production demand of the enterprise and the demand planning. Therefore, industrial electricity consumption is always difficult to predict. However, there are usually certain rules in residential electricity consumption, that is, there is a positive correlation between the electricity load and the population, and there is a certain rule between the electricity load and the weather temperature and the number of days with abnormal weather. Therefore, after determining the electricity consumption rules, the estimated electricity load of the target area in the target period can be determined based on the estimated weather information, the estimated population information and the electricity consumption rules.

[0101] Compared with the related art, the scheme of the embodiment of the present application can determine the power consumption pattern and population change pattern of the target area through the historical characteristic information of the target area in multiple historical evaluation periods, and combines the estimated weather information of the target area in the target period, the power consumption pattern and the multi-dimensional information of the estimated population information of the target area in the target period predicted based on the population change law to make a prediction, so as to obtain a more accurate estimated power load.

[0102] Furthermore, for any historical evaluation period, obtaining historical population information includes: obtaining daily mobile phone signaling data of the target area within any historical evaluation period; preprocessing the daily mobile phone signaling data within any historical evaluation period to obtain historical population information, and the preprocessing includes data cleaning, data deduplication and data validity screening.

[0103] Specifically, there are multiple communication base stations in the target area, and mobile phone signaling data is generated by the communication between the user's mobile device and the communication base station. When the user's mobile device is located in the coverage area of ​​the communication base station, it can exchange information with the communication base station to generate signaling data. A mobile phone signaling data usually includes the base station ID, user identity, access and disconnection time, and access duration.

[0104] Specifically, data cleaning is to filter out the mobile phone signaling data whose total access time with the base station in the target area is less than the first threshold every day. If the total access time with the base station in the target area is less than the first threshold, it means that the person corresponding to the mobile device may have left the target area or is a short-term access passing by, and can therefore be regarded as an invalid person. Data deduplication is to treat the mobile phone signaling data with the same user identity as one data, reducing the error of repeated population calculation caused by one user holding multiple mobile devices. Data validity screening refers to screening and deleting mobile phone signaling data with specific identifiers such as marketing identifiers and spam identifiers marked by operators.

[0105] Based on the pre-processed daily mobile phone signaling data, the total daily population, that is, the historical population data, is obtained. By pre-processing the daily mobile phone signaling data of the target area within a historical evaluation period, effective mobile phone signaling data that relatively accurately reflects the population of the target area can be obtained.

[0106] Further, refer to Figure 2 In step S20, based on the historical characteristic information in N historical evaluation periods, the power consumption pattern of the target period is determined, which may specifically include step S211 and step S212, wherein:

[0107] Step S211: Determine the average daily electricity load per capita based on the historical population information and historical electricity load in the N historical and evaluation periods.

[0108] Specifically, the historical electricity load in a historical evaluation period includes the daily electricity load. The daily electricity load of the target area in a historical evaluation period is divided by the daily total population to obtain the daily per capita electricity load of the target area in a historical evaluation period. The daily per capita electricity load is arithmetic averaged to obtain the per capita daily electricity load.

[0109] Step S212, historical weather information and historical power load in N historical and evaluation periods, determine the corresponding relationship between power load and weather, the corresponding relationship between power load and weather includes the corresponding relationship between power load and temperature and the power load growth ratio corresponding to each abnormal weather type.

[0110] Specifically, historical weather information includes daily average temperature and weather type. First, the dates of abnormal weather types and non-abnormal weather types in each historical evaluation cycle are calibrated, and the daily average temperature and power load corresponding to all non-abnormal weather types in N historical evaluation cycles are calibrated as a coordinate point in a two-dimensional coordinate system to make a curve of daily power consumption and daily average temperature. Then, fitting is performed based on the change curve to obtain the functional relationship between the growth ratio of daily average temperature and daily power load, that is, the corresponding relationship between power load and temperature.

[0111] For each abnormal weather type date, the growth ratio of the daily electricity load on the date of the abnormal weather type and the daily electricity load on the day before the date of the abnormal weather type is calculated as an electricity contribution corresponding to the abnormal weather type. For any abnormal weather type, all electricity contributions corresponding to the abnormal weather type in N historical evaluation cycles are arithmetic averaged to obtain the growth ratio of the electricity load corresponding to the abnormal weather type. Among them, the abnormal weather type includes but is not limited to rain, sandstorm, snow, etc. The specific abnormal weather type can be set by the user, and this is not specifically limited in the embodiments of the present application.

[0112] Furthermore, based on the historical characteristic information within N historical evaluation cycles, the population change pattern of the target period is determined, which may specifically include the following steps: based on the historical population information within N historical evaluation cycles, the population base and population flow pattern are determined, the population base is the average daily population on regular dates, the population flow pattern includes the net population increase corresponding to each type of key date, and the population change pattern includes the average population base and the population flow pattern.

[0113] Specifically, for N historical evaluation cycles, identify key date types, such as holidays, weekends, weekdays, etc. Associate the date type with the daily population data. Filter out the data of all regular dates, calculate the average daily population of these dates, and obtain the average population base. For each type of key date (such as weekends, holidays, and major event days), calculate the corresponding net population increase. Among them, net population increase = total population on the key date - average daily population on the adjacent regular dates.

[0114] Furthermore, the net population growth trends and patterns of different key date types are analyzed to obtain the laws of population change; and the data from the most recent evaluation cycle are used to verify the accuracy of the determined average population base and population flow laws.

[0115] The population change pattern of the target area can be determined based on a trained mathematical model of population pattern analysis and statistics. Specifically, the mathematical model can be obtained based on reinforcement learning training.

[0116] Further, based on the population change pattern, estimated population information in the target area within the target period is determined, including: determining distribution information of regular dates and key dates within the target period;

[0117] Based on the population base, population flow patterns, and distribution information of regular dates and key dates within the target period, determine the estimated population information of the target area within the target period.

[0118] Further, refer to Figure 3 In step S50, based on the estimated weather information, the estimated population information and the electricity consumption pattern, the estimated electricity load of the target area within the target period is determined, which may specifically include steps S51 to S53, wherein:

[0119] Step S51: Determine a first reference load based on the estimated personnel distribution information and the average daily electricity load per person.

[0120] Specifically, coefficients n and s are determined based on the first benchmark load and the second benchmark load, where n+s=1; the power load of the target area within the target period is predicted based on the first benchmark load, the second benchmark load and the prediction formula; the prediction formula is W=nw1+sw2, where W is the estimated power load, w1 is the first benchmark load, and w2 is the first benchmark load.

[0121] Step S52: determining a second reference load based on the estimated weather information and the corresponding relationship between the power load and the weather;

[0122] Step S53: predicting the estimated power load of the target area within the target period based on the first reference load and the second reference load.

[0123] Specifically, in the embodiment of the present application, the data logic for determining the estimated power load of the target area within the target period based on the historical characteristic information of each of the N historical evaluation periods is as follows: Figure 4 In the embodiment of the present application, the average daily electricity load per capita is determined by the historical population information of each of the N evaluation periods and the historical electricity load of each of the N historical evaluation periods; the estimated population information of the target area in the target period is determined by the historical population information of each of the N evaluation periods, and then the first benchmark load is determined based on the estimated population information and the average daily electricity load per capita.

[0124] Furthermore, in the embodiment of the present application, the correspondence between the power load and the weather is determined by the historical power load of each of the N historical evaluation periods and the historical weather information of each of the N historical evaluation periods, and the second reference load is determined by the correspondence between the power load and the weather and the estimated weather information of the target area in the target period. Then, the estimated power load is determined based on the first reference load and the second reference load.

[0125] Further, based on the first reference load and the second reference load, predicting the estimated power load of the target area within the target period may specifically include:

[0126] If the first benchmark load is greater than the second benchmark load, determining a first mean square error based on the population of each regular date in N historical evaluation periods, and determining n and s based on the first mean square error, wherein n is greater than s;

[0127] If the first benchmark load is less than the second benchmark load, the second mean square error is determined based on the daily average temperature of non-abnormal weather types in N historical evaluation periods, and n and s are determined based on the second mean square error, where n is less than s.

[0128] Generally, for the stability of power supply, sufficient redundancy needs to be maintained, that is, the estimated power load should be greater than the actual power load, and the less the estimated power load exceeds the actual power load, the more accurate the prediction is. In the embodiment of the present application, there are two influencing factors for the predicted power load of the target area within the target period, one is the weather factor, corresponding to the estimated weather information; the other is the population factor, corresponding to the estimated population information.

[0129] Therefore, when determining that the first benchmark load is greater than the second benchmark load, the population information may be the main factor affecting the power load of the target area. In this case, n and s are determined based on the first mean square error determined based on the population on each regular date in N historical evaluation cycles, and n is greater than s. Among them, the larger the first variance, the greater the fluctuation of the daily population in the target area on each regular date in the N historical evaluation cycles. At this time, n is set to be greater than s so that the estimated power load can be greater than the actual power load, thereby maintaining sufficient redundancy for power supply.

[0130] When it is determined that the second benchmark load is greater than the first benchmark load, the weather information may be the main factor affecting the power load in the target area. In this case, n and s are determined based on the first mean square error determined based on the daily average temperature of each non-abnormal weather type in N historical evaluation periods, and n is less than s. Among them, the larger the second variance, the greater the fluctuation of the daily average temperature of the non-abnormal weather type in the N historical evaluation periods. At this time, n is set to be less than s so that the estimated power load can be greater than the actual power load, thereby maintaining sufficient redundancy for power supply.

[0131] The above-mentioned embodiment introduces a method for estimating power load of a new power system combining multi-dimensional features from the perspective of method flow. The following embodiment introduces a system for estimating power load of a new power system combining multi-dimensional features from the perspective of a virtual module or a virtual unit. For details, please see the following embodiments.

[0132] The present application embodiment provides a new type of power system load estimation system combining multi-dimensional features, such as Figure 5 As shown, the system may specifically include:

[0133] The historical characteristic information acquisition module 501 is used to acquire the historical characteristic information of the target area within N historical evaluation cycles, the historical multi-dimensional characteristic information includes historical population information, historical weather information and historical power load, and N is greater than 5;

[0134] A rule determination module 502 is used to determine the electricity consumption rule and population change rule of the target period based on the historical characteristic information in N historical evaluation periods;

[0135] An estimated population information determination module 503 is used to determine estimated population information in a target area within a target period based on a population change rule, where the target period is a future time period;

[0136] The estimated weather information acquisition module 504 is used to acquire the estimated weather information of the target area within the target period;

[0137] The estimated power load determination module 505 is used to determine the estimated power load of the target area within the target period based on the estimated weather information, the estimated population information and the power consumption pattern.

[0138] In an embodiment of the present application, the system can determine the electricity consumption patterns and population change patterns of the target area through the historical characteristic information of the target area in multiple historical evaluation periods, and combine the estimated weather information of the target area in the target period, the electricity consumption patterns, and the multi-dimensional information of the estimated population information of the target area in the target period predicted based on the population change patterns to make predictions, so as to obtain a more accurate estimated electricity load.

[0139] In a possible implementation, when the rule determination module 502 determines the power usage rule of the target period based on the historical feature information in N historical evaluation periods, it is specifically used to:

[0140] Based on the historical population information and historical electricity load in N historical and evaluation periods, determine the average daily electricity load per capita;

[0141] Based on the historical weather information and historical power load in N historical and evaluation periods, determine the corresponding relationship between power load and weather. The corresponding relationship between power load and weather includes the corresponding relationship between power load and temperature and the power load growth ratio corresponding to each abnormal weather type.

[0142] Among them, electricity consumption patterns include the average daily electricity load per capita and the corresponding relationship between electricity load and weather.

[0143] In a possible implementation, when the law determination module 502 determines the population change law of the target period based on the historical feature information in N historical evaluation periods, it is specifically used to:

[0144] Historical population information includes daily population totals;

[0145] Based on the historical population information in N historical evaluation cycles, determine the population base and population flow pattern. The population base is the average daily population on regular dates. The population flow pattern includes the net population increase corresponding to each type of key date. The population change pattern includes the average population base and population flow pattern.

[0146] Accordingly, the estimated population information in the target area within the target period is determined based on the law of population change, including:

[0147] Determine the distribution information of regular dates and key dates within the target period;

[0148] Based on the population base, population flow patterns, and distribution information of regular dates and key dates within the target period, determine the estimated population information of the target area within the target period.

[0149] In a possible implementation, the system further includes a historical population information acquisition module. For any historical evaluation period, the historical population information acquisition module is specifically used to:

[0150] Obtain daily mobile phone signaling data for the target area within any historical evaluation period;

[0151] The daily mobile phone signaling data within any historical evaluation period is preprocessed to obtain historical population information. The preprocessing includes data cleaning, data deduplication, and data validity screening.

[0152] In a possible implementation, the estimated power load determination module 505 determines the estimated power load of the target area within the target period based on the estimated weather information, the estimated population information and the power consumption pattern, and is specifically used to:

[0153] Determine a first benchmark load based on the estimated personnel distribution information and the average daily electricity load per capita;

[0154] Determining a second reference load based on the estimated weather information and the corresponding relationship between the power load and the weather;

[0155] An estimated power load of the target area within a target period is determined based on the first reference load and the second reference load.

[0156] In a possible implementation, when the estimated power load determination module 505 determines the estimated power load of the target area within the target period based on the first reference load and the second reference load, it is specifically used to:

[0157] Determining coefficients n and s based on the first reference load and the second reference load;

[0158] Predicting the power load of the target area within the target period based on the first benchmark load, the second benchmark load and the prediction formula;

[0159] The prediction formula is W=nw1+sw2, where W is the estimated power load, w1 is the first benchmark load, w2 is the first benchmark load, and n+s=1.

[0160] In a possible implementation, when the estimated power load determination module 505 determines the coefficients n and s based on the first reference load and the second reference load, it is specifically used to:

[0161] If the first benchmark load is greater than the second benchmark load, determining a first mean square error based on the population of each regular date in N historical evaluation periods, and determining n and s based on the first mean square error, wherein n is greater than s;

[0162] If the first benchmark load is less than the second benchmark load, the second mean square error is determined based on the daily average temperature of non-abnormal weather types in N historical evaluation periods, and n and s are determined based on the second mean square error, where n is less than s.

[0163] An electronic device is provided in an embodiment of the present application, such as Figure 6 As shown, Figure 6 The electronic device 600 shown includes: a processor 601 and a memory 603. The processor 601 and the memory 603 are connected, such as through a bus 602. Optionally, the electronic device 600 may also include a transceiver 604. It should be noted that in actual applications, the transceiver 604 is not limited to one, and the structure of the electronic device 600 does not constitute a limitation on the embodiments of the present application.

[0164] Processor 601 may be a CPU (Central Processing Unit), a general purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. Processor 601 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0165] The bus 602 may include a path to transmit information between the above components. The bus 602 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 602 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0166] The memory 603 can be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to these.

[0167] The memory 603 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 601. The processor 601 is used to execute the application code stored in the memory 603 to implement the contents shown in the above method embodiment.

[0168] The electronic devices include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and fixed terminals such as digital TVs, desktop computers, etc. It can also be a server, etc. Figure 6 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0169] An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer can execute the corresponding content in the aforementioned method embodiment.

[0170] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0171] The above are only some implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A new method for estimating power load of a power system combining multi-dimensional features, characterized in that: include: Obtain historical characteristic information of the target area within N historical evaluation cycles. The historical multidimensional characteristic information includes historical population information, historical weather information, and historical electricity load. N is greater than 5. Based on the historical characteristic information in the N historical evaluation periods, determine the electricity consumption pattern and population change pattern of the target period; Determine estimated population information in a target area within a target period based on the population change law, where the target period is a future time period; Obtaining estimated weather information for the target area within a target period; Determining an estimated power load of the target area within a target period based on the estimated weather information, the estimated population information, and the power consumption pattern; The determining of the power consumption pattern of the target period based on the historical characteristic information in the N historical evaluation periods includes: determining the per capita daily power load based on the historical population information and the historical power load in the N historical and evaluation periods; determining the corresponding relationship between the power load and the weather based on the historical weather information and the historical power load in the N historical and evaluation periods, wherein the corresponding relationship between the power load and the weather includes the corresponding relationship between the power load and the temperature and the power load growth ratio corresponding to each abnormal weather type; wherein the power consumption pattern includes the per capita daily power load and the corresponding relationship between the power load and the weather; Among them, the historical electricity load includes the daily electricity load, and the historical weather information includes the daily average temperature and weather type; the dates of abnormal weather types and non-abnormal weather types in each historical evaluation period are calibrated, and the daily average temperature and electricity load corresponding to all non-abnormal weather types in N historical evaluation periods are calibrated as a coordinate point in a two-dimensional coordinate system to make a change curve of daily electricity consumption and daily average temperature; fitting is performed based on the change curve to obtain the functional relationship between the growth ratio of daily average temperature and daily electricity load, that is, the corresponding relationship between electricity load and temperature; for each abnormal weather type date, the growth ratio is calculated based on the daily electricity load on the date of the abnormal weather type and the daily electricity load on the day before the date of the abnormal weather type, as an electricity contribution corresponding to the abnormal weather type; for any abnormal weather type, all electricity contributions corresponding to the abnormal weather type in N historical evaluation periods are arithmetic averaged to obtain the growth ratio of electricity load corresponding to the abnormal weather type; The determining the estimated power load of the target area within the target period based on the estimated weather information, the estimated population information and the power consumption pattern includes: Determine a first benchmark load based on the estimated personnel distribution information and the average daily electricity load per capita; Based on the estimated weather information and the correspondence between the power load and the weather, a second reference load is determined; if the target period is longer than one month, only the estimated weather information of the first month is used, and the estimated weather period in the subsequent period is determined based on the average weather information of the same period in previous years; determining coefficients n and s based on the first reference load and the second reference load; Determine the estimated power load of the target area within the target period based on the first reference load, the second reference load and a prediction formula; The prediction formula is ,in, To estimate the power load, is the first reference load, is the second reference load, where n+s=1; The determining coefficients n and s based on the first reference load and the second reference load comprises: If the first benchmark load is greater than the second benchmark load, determining a first mean square error based on the population of each regular date in the N historical evaluation periods, and determining n and s based on the first mean square error, wherein n is greater than s; If the first benchmark load is less than the second benchmark load, a second mean square error is determined based on the daily average temperature of non-abnormal weather types in the N historical evaluation periods, and n and s are determined based on the second mean square error, where n is less than s.

2. The method according to claim 1, characterized in that: The determining of the population change law of the target period based on the historical characteristic information in the N historical evaluation periods includes: The historical population information includes daily population totals; Based on the historical population information in the N historical evaluation periods, determine the population base and population flow pattern, the population base is the average daily population on regular dates, the population flow pattern includes the net population increase corresponding to each type of key date, and the population change pattern includes the average population base and population flow pattern; Accordingly, the step of determining the estimated population information in the target area within the target period based on the population change law includes: Determine the distribution information of regular dates and key dates within the target period; Based on the population base, the population flow pattern and the distribution information of regular dates and key dates in the target period, the estimated population information of the target area in the target period is determined.

3. The method according to claim 2, characterized in that: The method further comprises: For any historical assessment period, historical population information is obtained including: Obtain daily mobile phone signaling data of the target area within any of the historical evaluation periods; The daily mobile phone signaling data within any of the historical evaluation periods is preprocessed to obtain historical population information, wherein the preprocessing includes data cleaning, data deduplication, and data validity screening.

4. A new type of power system load estimation system combining multi-dimensional features, characterized in that: include: A historical characteristic information acquisition module is used to obtain historical characteristic information of the target area within N historical evaluation cycles. The historical multi-dimensional characteristic information includes historical population information, historical weather information, and historical power load, where N is greater than 5; A rule determination module, used to determine the power consumption rule and population change rule of the target period based on the historical characteristic information in the N historical evaluation periods; An estimated population information determination module, used to determine the estimated population information in a target area within a target period based on the population change law, wherein the target period is a future time period; An estimated weather information acquisition module is used to acquire the estimated weather information of the target area within a target period; An estimated power load determination module, configured to determine an estimated power load of the target area within a target period based on the estimated weather information, the estimated population information and the power consumption pattern; The rule determination module is specifically used to: determine the per capita daily electricity load based on the historical population information and historical electricity load in the N historical and evaluation periods; determine the corresponding relationship between the electricity load and the weather based on the historical weather information and historical electricity load in the N historical and evaluation periods, wherein the corresponding relationship between the electricity load and the weather includes the corresponding relationship between the electricity load and the temperature and the growth ratio of the electricity load corresponding to each abnormal weather type; wherein the electricity consumption rule includes the per capita daily electricity load and the corresponding relationship between the electricity load and the weather; Among them, the historical electricity load includes the daily electricity load, and the historical weather information includes the daily average temperature and weather type; the dates of abnormal weather types and non-abnormal weather types in each historical evaluation period are calibrated, and the daily average temperature and electricity load corresponding to all non-abnormal weather types in N historical evaluation periods are calibrated as a coordinate point in a two-dimensional coordinate system to make a change curve of daily electricity consumption and daily average temperature; fitting is performed based on the change curve to obtain the functional relationship between the growth ratio of daily average temperature and daily electricity load, that is, the corresponding relationship between electricity load and temperature; for each abnormal weather type date, the growth ratio is calculated based on the daily electricity load on the date of the abnormal weather type and the daily electricity load on the day before the date of the abnormal weather type, as an electricity contribution corresponding to the abnormal weather type; for any abnormal weather type, all electricity contributions corresponding to the abnormal weather type in N historical evaluation periods are arithmetic averaged to obtain the growth ratio of electricity load corresponding to the abnormal weather type; The estimated power load determination module is specifically used to: determine a first reference load based on the estimated personnel distribution information and the average daily power load per capita; Based on the estimated weather information and the correspondence between the power load and the weather, a second reference load is determined; if the target period is longer than one month, only the estimated weather information of the first month is used, and the estimated weather period in the subsequent period is determined based on the average weather information of the same period in previous years; determining coefficients n and s based on the first reference load and the second reference load; Determine the estimated power load of the target area within the target period based on the first reference load, the second reference load and a prediction formula; The prediction formula is ,in, To estimate the power load, is the first reference load, is the second reference load, where n+s=1; If the first benchmark load is greater than the second benchmark load, determining a first mean square error based on the population of each regular date in the N historical evaluation periods, and determining n and s based on the first mean square error, wherein n is greater than s; If the first benchmark load is less than the second benchmark load, a second mean square error is determined based on the daily average temperature of non-abnormal weather types in the N historical evaluation periods, and n and s are determined based on the second mean square error, where n is less than s.

5. An electronic device, characterized in that: The electronic device includes: at least one processor; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the method for estimating power load of a new power system combining multi-dimensional features as described in any one of claims 1-3.

6. A computer-readable storage medium, characterized in that: include: A computer program is stored which can be loaded by a processor and execute a novel method for estimating power load of a power system combining multi-dimensional features as described in any one of claims 1 to 3.

Images