CN116843358A - Electric power price measuring and calculating method and system based on Kalmam Filters - Google Patents
Electric power price measuring and calculating method and system based on Kalmam Filters Download PDFInfo
- Publication number
- CN116843358A CN116843358A CN202310208191.XA CN202310208191A CN116843358A CN 116843358 A CN116843358 A CN 116843358A CN 202310208191 A CN202310208191 A CN 202310208191A CN 116843358 A CN116843358 A CN 116843358A
- Authority
- CN
- China
- Prior art keywords
- power price
- power
- value
- historical
- price
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000011156 evaluation Methods 0.000 claims abstract description 81
- 230000002159 abnormal effect Effects 0.000 claims abstract description 46
- 238000012795 verification Methods 0.000 claims abstract description 35
- 238000004364 calculation method Methods 0.000 claims abstract description 26
- 238000005259 measurement Methods 0.000 claims abstract description 18
- 230000008569 process Effects 0.000 claims abstract description 17
- 238000012545 processing Methods 0.000 claims abstract description 6
- 238000000691 measurement method Methods 0.000 claims abstract description 3
- 230000008859 change Effects 0.000 claims description 54
- 230000006870 function Effects 0.000 claims description 26
- 238000012216 screening Methods 0.000 claims description 13
- 238000012937 correction Methods 0.000 claims description 12
- 230000005611 electricity Effects 0.000 claims description 7
- 238000012163 sequencing technique Methods 0.000 claims description 7
- 238000013210 evaluation model Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 3
- 238000011161 development Methods 0.000 description 10
- 238000004458 analytical method Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0206—Price or cost determination based on market factors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Tourism & Hospitality (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to the technical field of power price measurement and calculation, and particularly relates to a power price measurement and calculation method and system based on Kalman Filters. According to the invention, the Kalmam Filters model is utilized to fuse the historical power price with the predicted power price, the error between the historical power price and the predicted power price is subjected to closed loop processing to obtain the first predicted value, the abnormal power price affecting power price measurement and calculation can be screened out in the process, meanwhile, the selected evaluation period can be optimized, the required verification period and the corresponding historical power price are obtained, trend operation is performed on the basis of the required verification period to obtain the second predicted value, and the second predicted value is subjected to weighting operation, so that the error in the prediction process is further reduced, and the finally obtained predicted value of the future power price of the measurement and calculation area is more accurate.
Description
Technical Field
The invention belongs to the technical field of power price measurement and calculation, and particularly relates to a power price measurement and calculation method and system based on Kalman Filters.
Background
The electric power is an energy source taking electric energy as power, is one of the most commonly used energy sources in daily life of people at present, is an electric power production and consumption system consisting of links of power generation, power transmission, power transformation, power distribution, power consumption and the like, converts primary energy in nature into electric power through a mechanical energy device, then supplies the electric power to each user through the power transmission, the power transformation and the power distribution, and along with the economic development, the electric power price is continuously adjusted, but because the economic development states of all areas are different, the electric power price of all areas is also different, and therefore, the economic development condition of all areas can be reflected by measuring and calculating the electric power price.
The existing power price measuring and calculating method is single in form, direct calculation is carried out based on historical power price, but factors influencing the power price are many, transient adjustment is possible to occur, or the adjustment process is relatively random and uncontrollable in order to adapt to the current economy, and the result obtained by the traditional measuring and calculating mode is definitely caused to have larger error.
Disclosure of Invention
The invention aims to provide a power price measuring and calculating method and system based on Kalman Filters, which can fuse historical power price and predicted power price together by using a Kalman Filters model, and conduct closed-loop processing on errors between the historical power price and the predicted power price to obtain high-accuracy future power price.
The technical scheme adopted by the invention is as follows:
a power price measuring and calculating method based on Kalmam Filters comprises the following steps:
acquiring a measuring and calculating area and power price information of the measuring and calculating area, wherein the power price information comprises a current power price and a historical power price;
acquiring an evaluation period and all historical power prices in the evaluation period;
constructing a Kalman Filters model, and inputting the historical electric power price into the Kalman Filters model to obtain a first predicted value of the historical electric power price;
comparing the first predicted value with a current power price, and outputting a power price deviation value;
obtaining a standard deviation value and comparing the standard deviation value with the electric power price deviation value;
if the standard deviation value is larger than the power price deviation value, inputting the historical power price into a trend change model, outputting a power price change trend value of a measuring and calculating area, and synchronously outputting a second predicted value;
if the standard deviation value is smaller than or equal to the electric power price deviation value, the first predicted value of the historical electric power price is invalid, the historical electric power price is input into a correction model, and abnormal electric power price is screened out;
sequencing all abnormal power prices according to the sequence of occurrence time, checking the abnormal power prices one by one according to the sequence of the reverse order to obtain check nodes, calibrating a period after the check nodes as a check period, and calibrating historical power prices in the check period as check power prices;
and inputting the verification power price into a Kalmam Filters model for verification until a power price deviation value smaller than a standard deviation value is obtained, and synchronously outputting a power price change trend value and a second predicted value of the measuring and calculating area.
In a preferred embodiment, the step of obtaining the evaluation period, and all historical power prices in the evaluation period, includes:
acquiring historical electricity year in the measuring and calculating area;
acquiring a time node with the largest historical power price fluctuation value in each historical power consumption year, and calibrating the time node as a demarcation point;
acquiring historical power utilization months corresponding to each demarcation point, and calibrating the historical power utilization months as nodes to be evaluated;
the occupation ratio of each node to be evaluated is obtained, and the node to be evaluated with the highest occupation ratio is marked as a critical point;
and acquiring time intervals between adjacent critical points, calibrating the time intervals as evaluation periods, and independently summarizing historical electric power prices in each evaluation period.
In a preferred embodiment, the evaluation periods are sequentially ordered after being generated, and the historical electric power prices input into the Kalmam Filters model and the trend change model are set to belong to the evaluation periods at the same rank.
In a preferred embodiment, the step of inputting the historical power price into a trend change model, outputting a power price change trend value of a measurement area, and synchronously outputting a second predicted value includes:
acquiring all historical power prices in an evaluation period;
obtaining a standard function from the trend change model;
inputting all historical electric power prices into a standard function to obtain an electric power price change trend value of a measuring area;
and acquiring the power price in the previous state, carrying out combined calculation with the power price change trend value, and outputting a second predicted value.
In a preferred scheme, after the power price change trend value is obtained, the power price change trend value is input into an evaluation model to obtain evaluation confidence, and the specific process is as follows:
equally dividing the evaluation period into a plurality of nodes to be evaluated;
acquiring historical power prices of each node to be evaluated, calibrating the historical power prices to be evaluated, and arranging all the power prices to be evaluated according to a time sequence;
acquiring an evaluation function from the evaluation model;
acquiring adjacent power prices to be evaluated, and inputting the adjacent power prices to be evaluated and the power price change trend value into an evaluation function together to obtain power trend prices;
acquiring the price of the electric power to be evaluated of the next level, performing offset processing to obtain an evaluation interval, and comparing the evaluation interval with the electric power trend price;
screening all the power trend prices which accord with the evaluation interval and the corresponding power prices to be evaluated, calculating the occupation ratio of the power trend prices to be evaluated in all the power prices to be evaluated, and calibrating the power trend prices to be evaluated as evaluation confidence;
acquiring a confidence judgment threshold value;
if the evaluation confidence coefficient is greater than or equal to a confidence coefficient judgment threshold value, judging that the power price change trend value executes the calculation of a second predicted value
And if the evaluation confidence coefficient is smaller than a confidence coefficient judgment threshold value, judging that the power price trend value is invalid, and not executing calculation of a second predicted value.
In a preferred scheme, after the second predicted value is obtained, the second predicted value and the first predicted value are input into a pre-estimation function together for weighted calculation to obtain an electric power price predicted value;
comparing the power price estimated value with the current power price, and outputting a comparison result as a rechecked power price;
comparing the rechecked power price with the power price deviation value;
if the rechecked power price is smaller than or equal to the power price deviation value, recalculating a power price trend value;
and if the rechecked power price is larger than the power price deviation value, determining the prediction function as a standard function in the measuring and calculating area.
In a preferred embodiment, the step of inputting the historical electricity prices into a correction model and screening out abnormal electricity prices includes:
acquiring all historical power prices in an evaluation period;
acquiring fluctuation values between adjacent historical power prices, and outputting the fluctuation values as power price fluctuation values;
obtaining a standard fluctuation value and comparing the standard fluctuation value with the electric power price fluctuation value;
and screening all the power price fluctuation values larger than the standard fluctuation value, calibrating the power price fluctuation values as abnormal fluctuation values, and calibrating the historical power price corresponding to the abnormal fluctuation values as abnormal power price.
In a preferred scheme, the step of sorting all the abnormal power prices according to the sequence of the occurrence time, and checking the abnormal power prices one by one according to the sequence of the reverse order to obtain check nodes includes:
acquiring interval time periods between adjacent abnormal fluctuation values, and calibrating the interval time periods as time periods to be checked;
obtaining a standard time period, screening all time periods to be checked which are larger than the standard time period, and calibrating the time period to be checked which is positioned at the last bit occurrence time as a check period;
and calibrating a starting point of the check period as a check node, and discarding the historical electric power price before the check node.
The invention also provides a power price measuring and calculating system based on Kalman Filters, which is applied to the power price measuring and calculating method based on Kalman Filters, and comprises the following steps:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring a measuring and calculating area and power price information of the measuring and calculating area, and the power price information comprises a current power price and a historical power price;
the second acquisition module is used for acquiring an evaluation period and all historical electric power prices in the evaluation period;
the prediction module is used for constructing a Kalman Filters model, inputting the historical electric power price into the Kalman Filters model and obtaining a first predicted value of the historical electric power price;
the measuring and calculating module is used for comparing the first predicted value with the current power price and outputting a power price deviation value;
the judging module is used for acquiring a standard deviation value and comparing the standard deviation value with the electric power price deviation value;
if the standard deviation value is larger than the power price deviation value, inputting the historical power price into a trend change model, outputting a power price change trend value of a measuring and calculating area, and synchronously outputting a second predicted value;
if the standard deviation value is smaller than or equal to the electric power price deviation value, the first predicted value of the historical electric power price is invalid, the historical electric power price is input into a correction model, and abnormal electric power price is screened out;
the verification module is used for sequencing all abnormal power prices according to the sequence of occurrence time, verifying the abnormal power prices one by one according to the sequence of the reverse order to obtain a verification node, calibrating a period after the verification node as a verification period, and calibrating historical power prices in the verification period as verification power prices;
and the correction module is used for inputting the verification power price into a Kalman Filters model for verification until a power price deviation value smaller than a standard deviation value is obtained, and synchronously outputting a power price change trend value and a second predicted value of the measuring and calculating area.
And, a power price measuring terminal based on Kalmam Filters, comprising:
at least one processor;
and a memory communicatively coupled to the at least one processor;
wherein the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the Kalmam Filters-based power price estimation method described above.
The invention has the technical effects that:
according to the invention, the Kalmam Filters model is utilized to fuse the historical power price with the predicted power price, the error between the historical power price and the predicted power price is subjected to closed loop processing to obtain the first predicted value, the abnormal power price affecting power price measurement and calculation can be screened out in the process, meanwhile, the selected evaluation period can be optimized, the required verification period and the corresponding historical power price are obtained, trend operation is performed on the basis of the required verification period to obtain the second predicted value, and the second predicted value is subjected to weighting operation, so that the error in the prediction process is further reduced, and the finally obtained predicted value of the future power price of the measurement and calculation area is more accurate.
Drawings
FIG. 1 is a flow chart of a method provided by an embodiment of the present invention;
fig. 2 is a system block diagram provided by an embodiment of the present invention.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to specific embodiments thereof which are illustrated in the appended drawings.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways other than those described herein, and persons skilled in the art will readily appreciate that the present invention is not limited to the specific embodiments disclosed below.
Further, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic can be included in at least one implementation of the invention. The appearances of the phrase "in one preferred embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
Referring to fig. 1 and 2, the invention provides a power price measuring and calculating method based on kalman Filters, which comprises the following steps:
s1, acquiring a measuring and calculating area and power price information of the measuring and calculating area, wherein the power price information comprises a current power price and a historical power price;
s2, acquiring an evaluation period and all historical power prices in the evaluation period;
s3, constructing a Kalman Filters model, and inputting the historical electric power price into the Kalman Filters model to obtain a first predicted value of the historical electric power price;
s4, comparing the first predicted value with the current power price, and outputting a power price deviation value;
s5, acquiring a standard deviation value and comparing the standard deviation value with the power price deviation value;
if the standard deviation value is larger than the power price deviation value, inputting the historical power price into a trend change model, outputting a power price change trend value of the measuring and calculating area, and synchronously outputting a second predicted value;
if the standard deviation value is smaller than or equal to the electric power price deviation value, the first predicted value of the historical electric power price is invalid, the historical electric power price is input into a correction model, and the abnormal electric power price is screened out;
s6, sorting all abnormal power prices according to the sequence of occurrence time, checking the abnormal power prices one by one according to the sequence of the reverse order to obtain check nodes, calibrating the time period after the check nodes as a check period, and calibrating the historical power prices in the check period as check power prices;
and S7, inputting the checked electric power price into a Kalmam Filters model for checking until an electric power price deviation value smaller than the standard deviation value is obtained, and synchronously outputting an electric power price change trend value and a second predicted value of the measuring and calculating area.
As described in the above steps S1-S7, because of the difference in economic development of each region, the power intervals are correspondingly different, for some regions with better development, the resident economic capacity is higher, the power price of the region is relatively higher, for regions with later economic development, the power price of a region is relatively lower, so that the power price of a region is measured and calculated as a way reflecting the economic development of the region, when the power price of a region is measured and calculated, research and analysis are required based on the change condition of the historical power price, based on this, the embodiment provides a method for measuring and calculating the power price based on the Kalmam Filters model, firstly, the region to be studied is required to be determined, the embodiment calibrates the region to be measured, firstly, the current power price and the historical power price in the region are required to be obtained, so as to analyze the future economic development trend of the region, the range of the research is determined by constructing an evaluation period, and when the evaluation period is established, the current economic development is used as a way, the moment of the current development is required to be used, the fluctuation of the price is not required to be accurately supported, and the fluctuation amount of the current fluctuation is required to be relatively large, and the data can be accurately analyzedThe historical electric power price of the electric power is input into a Kalman Filters model for calculation, wherein the estimated function in the Kalman Filters model is as follows:wherein x is tt-1 Representing the first predicted value, F t Representing a state transition matrix>The prediction value of the power price in the previous state is represented to obtain a first prediction value, then the first prediction value is compared with the current power price, the accuracy of the output result of the model is judged, so that whether the future power price is feasible or not is judged, on the premise that the output result of a Kalmam Filters model is feasible, trend analysis is carried out on the historical power price, specifically, the trend value of the power price is output through a trend change model, a second prediction value is calculated on the basis of the trend value, the first prediction value and the second prediction value are combined together to obtain a prediction function capable of more accurately reflecting the future power price, and in the process, abnormal data generated due to the influence of instantaneous data or other factors are difficult to be prevented.
In a preferred embodiment, the step of obtaining an evaluation period, and all historical power prices within the evaluation period, comprises:
s201, acquiring historical electricity year in a measuring and calculating area;
s202, acquiring a time node with the largest historical power price fluctuation value in each historical power consumption year, and calibrating the time node as a demarcation point;
s203, acquiring historical power utilization months corresponding to each demarcation point, and calibrating the historical power utilization months as nodes to be evaluated;
s204, obtaining the occupation ratio of each node to be evaluated, and calibrating the node to be evaluated with the highest occupation ratio as a critical point;
s205, acquiring time intervals between adjacent critical points, calibrating the time intervals as evaluation periods, and independently summarizing historical power prices in each evaluation period.
As described in the above steps S201-S205, the power price is limited by seasons, so that the historical power price has a stepwise fluctuation in each power year, so that when the evaluation period is set, the historical power price needs to be divided according to the fluctuation periods.
And after the evaluation period is generated, sequentially sequencing, setting the historical power prices input into the Kalmam Filters model and the trend change model to belong to the evaluation period under the same level, and if 7-9 months in the historical power consumption year are one evaluation period, inputting the historical power prices into the Kalmam Filters model and the trend change model are 7-9 months in the historical year.
In a preferred embodiment, the step of inputting the historical power price into the trend change model, outputting the power price change trend value of the measurement area, and synchronously outputting the second predicted value includes:
s501, acquiring all historical power prices in an evaluation period;
s502, obtaining a standard function from a trend change model;
s503, inputting all historical power prices into a standard function to obtain a power price change trend value of a measuring and calculating area;
s504, acquiring the power price in the previous state, combining the power price with the power price change trend value, calculating, and outputting a second predicted value.
After the evaluation period is determined and the Kalmam Filters model is determined to be viable, the power price trend value can be measured, as described in steps S501-S504 above, and the historical power price is also measured based on the historical power price, by inputting the historical power price into the standard function:
wherein Q represents a power price change trend value, n, m, r represents the number of historical power prices participating in measurement and calculation, D a ，D b ，D z The values of a, b … … z are gradually increased and are positive integers, the evaluation interval is divided into a plurality of time periods based on the above, the specific division number is set according to actual requirements, only one example is given here, the division of the evaluation interval is not limited, the influence of instantaneous change values or other factors in the historical power price (such as adjacent historical power price fluctuation and the subsequent trend is stable, the historical power price before the node is not suitable for trend judgment) can be eliminated conveniently, the calculation of the power price trend value is more accurate, and then the historical power price adjacent to the current power price and the power price trend value are summed to obtain the second predicted value.
In a preferred embodiment, after the power price change trend value is obtained, the power price change trend value is input into an evaluation model to obtain an evaluation confidence coefficient, and the specific process is as follows:
stp1, equally dividing the evaluation period into a plurality of nodes to be evaluated;
stp2, acquiring historical power prices under each node to be evaluated, calibrating the historical power prices to be evaluated, and arranging all the power prices to be evaluated according to a time sequence;
stp3, obtaining an evaluation function from the evaluation model;
stp4, acquiring adjacent power prices to be evaluated, and inputting the adjacent power prices to be evaluated and the power price change trend value into an evaluation function to obtain power trend prices;
stp5, obtaining the price of the electric power to be evaluated of the next round, performing offset processing to obtain an evaluation interval, and comparing the evaluation interval with the trend price of the electric power;
stp6, screening all the power trend prices which accord with the evaluation interval and the corresponding power prices to be evaluated, calculating the occupation ratio of the power trend prices to be evaluated in all the power prices to be evaluated, and calibrating the power trend prices to be the evaluation confidence;
stp7, obtaining a confidence coefficient judgment threshold value;
if the evaluation confidence coefficient is greater than or equal to the confidence coefficient judgment threshold value, judging the power price change trend value to execute the calculation of the second predicted value
If the evaluation confidence is smaller than the confidence judgment threshold, judging that the power price trend value is invalid, and not executing calculation of the second predicted value.
As described in the above steps Stp1-Stp7, after the trend value of the power price is obtained, the feasibility of the trend value of the power price needs to be further evaluated, in this embodiment, the trend value of the power price is calibrated to be an evaluation confidence level, specifically, the evaluation is performed on the basis of a known historical power price, and then the feasibility of the trend value of the power price can be determined by calculating the occupation ratio of the trend value of the power price conforming to the evaluation interval, for example, if the confidence level determination threshold is set to 90%, the occupation ratio of the trend value of the power price conforming to the evaluation interval is greater than 90%, the second predicted value can be determined to be feasible, otherwise, the influence of the instantaneous value or other factors detected in the evaluation process is removed, and repeated calculation is performed, so that the process is repeated until the evaluation confidence level is higher than 90%.
In a preferred embodiment, after the second predicted value is obtained, the second predicted value and the first predicted value are input into a prediction function together for weighted calculation to obtain an estimated value of the electric power price;
s505, comparing the power price predicted value with the current power price, and outputting a comparison result as a rechecked power price;
s506, comparing the rechecked power price with the power price deviation value;
if the rechecking power price is smaller than or equal to the power price deviation value, recalculating a power price trend value;
and if the rechecking power price is larger than the power price deviation value, determining the prediction function as a standard function in the measuring and calculating area.
As described in the above steps S505-S506, the weighting operation may be performed on the premise that the first predicted value and the second predicted value are both determined to be viable, where the determination of the weights of the first predicted value and the second predicted value may be performed by using CRITIC weighting method or information amount weighting method, or expert scoring data, which is a common technical means for those skilled in the art, and the determination is not limited herein, and then the rechecking of the price of the electric power may be performed, and then compared with the deviation value of the price of the electric power to determine whether to recalculate the trend value of the price of the electric power to improve the accuracy.
In a preferred embodiment, the step of inputting the historical electricity prices into the correction model, and screening out the abnormal electricity prices includes:
s507, acquiring all historical power prices in an evaluation period;
s508, acquiring fluctuation values between adjacent historical power prices and outputting the fluctuation values as power price fluctuation values;
s509, acquiring a standard fluctuation value and comparing the standard fluctuation value with a power price fluctuation value;
s510, screening all power price fluctuation values larger than the standard fluctuation value, calibrating the power price fluctuation values as abnormal fluctuation values, and calibrating the historical power price corresponding to the abnormal fluctuation values as abnormal power price.
In the process of screening abnormal power prices, the preset standard fluctuation value is compared with the power price fluctuation value to screen out the power price fluctuation value larger than the standard fluctuation value, so as to implement the process of eliminating abnormal data, and then the historical power price corresponding to the power price fluctuation value lower than the standard fluctuation value is input into a Kalmam Filters model for repeated measurement and calculation until the power price deviation value smaller than the standard deviation value is obtained.
In a preferred embodiment, the step of sorting all the abnormal power prices according to the sequence of the occurrence time, and checking the abnormal power prices one by one according to the sequence of the reverse order to obtain check nodes includes:
s601, acquiring interval time periods between adjacent abnormal fluctuation values, and calibrating the interval time periods as time periods to be checked;
s602, acquiring a standard period, screening out all periods to be checked which are larger than the standard period, and calibrating the period to be checked which is positioned at the last bit occurrence time as a check period;
s603, calibrating a starting point of the check period to be a check node, and discarding the historical electric power price before the check node.
As described in the above steps S601-S603, in order to ensure that the historical power prices input into the kalman Filters model are sufficient, when the abnormal power prices are screened, the interval period between adjacent abnormal fluctuation values is calibrated, when the accuracy of the measurement result is considered, the interval period conforming to the standard is ordered, the period closest to the current power price is selected and calibrated as a verification period, the historical power prices outside the verification period are discarded, the historical power prices in the verification period are input into the kalman Filters model for running again until the power price deviation value smaller than the standard deviation value is obtained, and the power price change trend value and the second predicted value of the measurement area are output according to the above process, so that repeated details are omitted.
The invention also provides a power price measuring and calculating system based on Kalman Filters, which is applied to the power price measuring and calculating method based on Kalman Filters, and comprises the following steps:
the first acquisition module is used for acquiring the measuring and calculating area and the power price information of the measuring and calculating area, wherein the power price information comprises the current power price and the historical power price;
the second acquisition module is used for acquiring an evaluation period and all historical electric power prices in the evaluation period;
the prediction module is used for constructing a Kalman Filters model, inputting the historical power price into the Kalman Filters model and obtaining a first predicted value of the historical power price;
the measuring and calculating module is used for comparing the first predicted value with the current power price and outputting a power price deviation value;
the judging module is used for acquiring the standard deviation value and comparing the standard deviation value with the power price deviation value;
if the standard deviation value is larger than the power price deviation value, inputting the historical power price into a trend change model, outputting a power price change trend value of the measuring and calculating area, and synchronously outputting a second predicted value;
if the standard deviation value is smaller than or equal to the electric power price deviation value, the first predicted value of the historical electric power price is invalid, the historical electric power price is input into a correction model, and the abnormal electric power price is screened out;
the verification module is used for sequencing all abnormal power prices according to the sequence of occurrence time, verifying the abnormal power prices one by one according to the sequence of the reverse order to obtain a verification node, calibrating the time period after the verification node as a verification period, and calibrating the historical power prices in the verification period as verification power prices;
the correction module is used for inputting the verification power price into the Kalmam Filters model for verification until a power price deviation value smaller than the standard deviation value is obtained, and synchronously outputting the power price change trend value and the second predicted value of the measuring and calculating area.
In the above, when the power price of the measurement area is measured, the first acquisition module is used for determining the historical power price in the measurement area, then the second acquisition module is used for acquiring the evaluation period, determining the corresponding historical power price, then the historical power price is input to the prediction module, the first predicted value of the historical power price is measured through the Kalmam Filters model, in order to ensure the feasibility of the first predicted value, the measurement module and the judgment module can judge the feasibility of the first predicted value, the process can be realized based on the condition function if … … else by step in a nested manner, the calibration module and the calibration module can be used for calibrating the first predicted value under the condition that the first predicted value does not meet the execution condition, and finally the standard function capable of carrying out future power price of the measurement area can be obtained.
And, a power price measuring terminal based on Kalmam Filters, comprising:
at least one processor;
and a memory communicatively coupled to the at least one processor;
wherein the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the kalman Filters-based power price estimation method described above.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, apparatus, article or method that comprises the element.
The foregoing is merely a preferred embodiment of the present invention and it should be noted that modifications and adaptations to those skilled in the art may be made without departing from the principles of the present invention, which are intended to be comprehended within the scope of the present invention. Structures, devices and methods of operation not specifically described and illustrated herein, unless otherwise indicated and limited, are implemented according to conventional means in the art.
Claims (10)
1. A power price measuring and calculating method based on Kalmam Filters is characterized in that: comprising the following steps:
acquiring a measuring and calculating area and power price information of the measuring and calculating area, wherein the power price information comprises a current power price and a historical power price;
acquiring an evaluation period and all historical power prices in the evaluation period;
constructing a Kalman Filters model, and inputting the historical electric power price into the Kalman Filters model to obtain a first predicted value of the historical electric power price;
comparing the first predicted value with a current power price, and outputting a power price deviation value;
obtaining a standard deviation value and comparing the standard deviation value with the electric power price deviation value;
if the standard deviation value is larger than the power price deviation value, inputting the historical power price into a trend change model, outputting a power price change trend value of a measuring and calculating area, and synchronously outputting a second predicted value;
if the standard deviation value is smaller than or equal to the electric power price deviation value, the first predicted value of the historical electric power price is invalid, the historical electric power price is input into a correction model, and abnormal electric power price is screened out;
sequencing all abnormal power prices according to the sequence of occurrence time, checking the abnormal power prices one by one according to the sequence of the reverse order to obtain check nodes, calibrating a period after the check nodes as a check period, and calibrating historical power prices in the check period as check power prices;
and inputting the verification power price into a Kalmam Filters model for verification until a power price deviation value smaller than a standard deviation value is obtained, and synchronously outputting a power price change trend value and a second predicted value of the measuring and calculating area.
2. The electric power price measuring and calculating method based on Kalmam Filters according to claim 1, wherein: the step of obtaining the evaluation period and all historical power prices in the evaluation period comprises the following steps:
acquiring historical electricity year in the measuring and calculating area;
acquiring a time node with the largest historical power price fluctuation value in each historical power consumption year, and calibrating the time node as a demarcation point;
acquiring historical power utilization months corresponding to each demarcation point, and calibrating the historical power utilization months as nodes to be evaluated;
the occupation ratio of each node to be evaluated is obtained, and the node to be evaluated with the highest occupation ratio is marked as a critical point;
and acquiring time intervals between adjacent critical points, calibrating the time intervals as evaluation periods, and independently summarizing historical electric power prices in each evaluation period.
3. The electric power price measuring and calculating method based on Kalmam Filters according to claim 1, wherein: and sequentially sequencing the evaluation periods after generating, and setting the historical electric power prices input into the Kalmam Filters model and the trend change model to belong to the evaluation periods under the same rank.
4. The electric power price measuring and calculating method based on Kalmam Filters according to claim 1, wherein: the step of inputting the historical power price into a trend change model, outputting a power price change trend value of a measuring and calculating area and synchronously outputting a second predicted value comprises the following steps:
acquiring all historical power prices in an evaluation period;
obtaining a standard function from the trend change model;
inputting all historical electric power prices into a standard function to obtain an electric power price change trend value of a measuring area;
and acquiring the power price in the previous state, carrying out combined calculation with the power price change trend value, and outputting a second predicted value.
5. The electric power price measuring and calculating method based on Kalmam Filters according to claim 1, wherein: after the power price change trend value is obtained, the power price change trend value is input into an evaluation model to obtain evaluation confidence, and the specific process is as follows:
equally dividing the evaluation period into a plurality of nodes to be evaluated;
acquiring historical power prices of each node to be evaluated, calibrating the historical power prices to be evaluated, and arranging all the power prices to be evaluated according to a time sequence;
acquiring an evaluation function from the evaluation model;
acquiring adjacent power prices to be evaluated, and inputting the adjacent power prices to be evaluated and the power price change trend value into an evaluation function together to obtain power trend prices;
acquiring the price of the electric power to be evaluated of the next level, performing offset processing to obtain an evaluation interval, and comparing the evaluation interval with the electric power trend price;
screening all the power trend prices which accord with the evaluation interval and the corresponding power prices to be evaluated, calculating the occupation ratio of the power trend prices to be evaluated in all the power prices to be evaluated, and calibrating the power trend prices to be evaluated as evaluation confidence;
acquiring a confidence judgment threshold value;
if the evaluation confidence coefficient is greater than or equal to a confidence coefficient judgment threshold value, judging that the power price change trend value executes the calculation of a second predicted value
And if the evaluation confidence coefficient is smaller than a confidence coefficient judgment threshold value, judging that the power price trend value is invalid, and not executing calculation of a second predicted value.
6. The electric power price measuring and calculating method based on Kalmam Filters according to claim 1, wherein: after the second predicted value is obtained, the second predicted value and the first predicted value are input into a pre-estimation function together for weighted calculation, and a power price predicted value is obtained;
comparing the power price estimated value with the current power price, and outputting a comparison result as a rechecked power price;
comparing the rechecked power price with the power price deviation value;
if the rechecked power price is smaller than or equal to the power price deviation value, recalculating a power price trend value;
and if the rechecked power price is larger than the power price deviation value, determining the prediction function as a standard function in the measuring and calculating area.
7. The electric power price measuring and calculating method based on Kalmam Filters according to claim 1, wherein: the step of inputting the historical power price into a correction model and screening out abnormal power price comprises the following steps:
acquiring all historical power prices in an evaluation period;
acquiring fluctuation values between adjacent historical power prices, and outputting the fluctuation values as power price fluctuation values;
obtaining a standard fluctuation value and comparing the standard fluctuation value with the electric power price fluctuation value;
and screening all the power price fluctuation values larger than the standard fluctuation value, calibrating the power price fluctuation values as abnormal fluctuation values, and calibrating the historical power price corresponding to the abnormal fluctuation values as abnormal power price.
8. The electric power price measuring and calculating method based on Kalmam Filters according to claim 1, wherein: the step of sorting all the abnormal power prices according to the sequence of the occurrence time, and checking the abnormal power prices one by one according to the sequence of the reverse order to obtain check nodes comprises the following steps:
acquiring interval time periods between adjacent abnormal fluctuation values, and calibrating the interval time periods as time periods to be checked;
obtaining a standard time period, screening all time periods to be checked which are larger than the standard time period, and calibrating the time period to be checked which is positioned at the last bit occurrence time as a check period;
and calibrating a starting point of the check period as a check node, and discarding the historical electric power price before the check node.
9. A power price measurement system based on Kalmam Filters, applied to the power price measurement method based on Kalmam Filters as defined in any one of claims 1 to 8, characterized in that: comprising the following steps:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring a measuring and calculating area and power price information of the measuring and calculating area, and the power price information comprises a current power price and a historical power price;
the second acquisition module is used for acquiring an evaluation period and all historical electric power prices in the evaluation period;
the prediction module is used for constructing a Kalman Filters model, inputting the historical electric power price into the Kalman Filters model and obtaining a first predicted value of the historical electric power price;
the measuring and calculating module is used for comparing the first predicted value with the current power price and outputting a power price deviation value;
the judging module is used for acquiring a standard deviation value and comparing the standard deviation value with the electric power price deviation value;
if the standard deviation value is larger than the power price deviation value, inputting the historical power price into a trend change model, outputting a power price change trend value of a measuring and calculating area, and synchronously outputting a second predicted value;
if the standard deviation value is smaller than or equal to the electric power price deviation value, the first predicted value of the historical electric power price is invalid, the historical electric power price is input into a correction model, and abnormal electric power price is screened out;
the verification module is used for sequencing all abnormal power prices according to the sequence of occurrence time, verifying the abnormal power prices one by one according to the sequence of the reverse order to obtain a verification node, calibrating a period after the verification node as a verification period, and calibrating historical power prices in the verification period as verification power prices;
and the correction module is used for inputting the verification power price into a Kalman Filters model for verification until a power price deviation value smaller than a standard deviation value is obtained, and synchronously outputting a power price change trend value and a second predicted value of the measuring and calculating area.
10. Electric power price measurement and calculation terminal based on Kalmam Filters, its characterized in that: comprising the following steps:
at least one processor;
and a memory communicatively coupled to the at least one processor;
wherein the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the kalman Filters based power price estimation method of any of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310208191.XA CN116843358A (en) | 2023-02-24 | 2023-02-24 | Electric power price measuring and calculating method and system based on Kalmam Filters |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310208191.XA CN116843358A (en) | 2023-02-24 | 2023-02-24 | Electric power price measuring and calculating method and system based on Kalmam Filters |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116843358A true CN116843358A (en) | 2023-10-03 |
Family
ID=88167763
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310208191.XA Pending CN116843358A (en) | 2023-02-24 | 2023-02-24 | Electric power price measuring and calculating method and system based on Kalmam Filters |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116843358A (en) |
-
2023
- 2023-02-24 CN CN202310208191.XA patent/CN116843358A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9209743B2 (en) | Fault detection apparatus and fault detection method | |
| KR101989493B1 (en) | System and method for prediction of electrical energy consumption | |
| CN104392274B (en) | The short-term electro-load forecast method in city based on power load and temperature trend | |
| CN109492709A (en) | Data predication method and device based on mixed model | |
| CN111080477A (en) | Household power load prediction method and system | |
| CN110969282A (en) | Runoff stability prediction method based on LSTM composite network | |
| CN116205310B (en) | Soil water content influence factor sensitive interval judging method based on interpretable integrated learning model | |
| CN113139605A (en) | Power load prediction method based on principal component analysis and LSTM neural network | |
| CN108256693B (en) | Photovoltaic power generation power prediction method, device and system | |
| CN110991761B (en) | Heat supply load prediction method and device | |
| CN115908051A (en) | Method for determining energy storage capacity of power system | |
| CN116823172A (en) | Model optimization-based engineering cost assessment method and system | |
| CN111753461A (en) | Tidal water level correction method, target residual water level acquisition method, device and equipment | |
| Alexander et al. | Identification of static polynomial load model based on remote metering systems information | |
| CN116303480B (en) | Electric energy meter error checking method based on cloud computing | |
| CN116843358A (en) | Electric power price measuring and calculating method and system based on Kalmam Filters | |
| CN108197843A (en) | A kind of level terrain wind power output method of evaluating characteristic | |
| US20230266158A1 (en) | Method and system for eccentric load error correction | |
| CN115561697A (en) | Intelligent ammeter error analysis method | |
| CN115483884A (en) | Power performance evaluation method for batch photovoltaic modules and related equipment | |
| CN112668784A (en) | Regional macro economy prediction model and method based on big data | |
| CN113111573B (en) | Landslide displacement prediction method based on GRU | |
| CN114492923A (en) | Long-time scale power prediction method | |
| CN112581311A (en) | Method and system for predicting long-term output fluctuation characteristics of aggregated multiple wind power plants | |
| CN115796000B (en) | Short-term air temperature forecast set correction method based on stacked machine learning algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |