CN101116094A - Identify data sources for neural network - Google Patents
Identify data sources for neural network Download PDFInfo
- Publication number
- CN101116094A CN101116094A CNA2006800038642A CN200680003864A CN101116094A CN 101116094 A CN101116094 A CN 101116094A CN A2006800038642 A CNA2006800038642 A CN A2006800038642A CN 200680003864 A CN200680003864 A CN 200680003864A CN 101116094 A CN101116094 A CN 101116094A
- Authority
- CN
- China
- Prior art keywords
- day
- measure
- data
- module
- data set
- 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
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A system, method, and device for identifying data sources for a neural network are disclosed. The exemplary system may have a module for determining load curves for each selected data set. The system may also have a module for determining a global difference measure and a global similarity measure for each load curve of each selected data set. The system may have a module for determining a set of data sets with lowest value global difference measure. The system may also have a module for determining a set of data sets with largest value global similarity measure. The system may also have a module for determining a union of the sets of lowest value difference measure and the sets of largest value similarity measure. The system may also have a module for determining for each set in the union one of a local similarity measure and a local difference measure and a module for selecting a set of reduced data sets based on one of the local similarity measure and the local difference measure.
Description
Cross Reference to Related Applications
This application is related to U.S. provisional patent applications 60/649,677, 60/649,877, 60/649,876 and 60/649,803, all filed on 3/2/2005, which are hereby incorporated by reference in their entirety.
Technical Field
The present invention relates to identifying neural network data sources, and more particularly, to an apparatus, method and system for identifying neural network matching data sources based on very short term load prediction.
Background
An Artificial Neural Network (ANN) is a device in which multiple interconnected elements process information simultaneously, adapting to and learning past patterns. The ANN may be used to predict future responses of the control system over time. For example, electrical energy consumption in the power generation industry may vary over time. To efficiently operate a power plant, it is useful to identify future consumption patterns. A very short term load limit predictor (VSTLP) provides a means of predicting the power output demand of a system from the current point in time within a predetermined future time period, e.g., 60 minutes or less.
Very Short Term Load Predictor (VSTLP) based neural networks require that the actual load data source be determined and made available for offline training of the neural network. The neural network will be used for online prediction and further online training/adaptation to improve the accuracy of the prediction. Load data for up to five full-day load curves are used for offline neural network training. The annual value of the load data over a specified time period is stored in a VSTLP database with a 10 year value of also storing holiday load data. Accordingly, there is a need for an apparatus, method, and system that can efficiently utilize offline data to provide ANN-based VSTLP training.
Disclosure of Invention
The present invention is a novel apparatus, system, and method of identifying a neural network data source. The exemplary method determines a load curve for each selected data set. The method determines a global difference measure and a global match measure for each load curve for each selected data set. The method also determines a set of data sets having the minimum global difference measure and determines a set of data sets having the maximum global match measure. The method also determines a union of the minimum value difference measure set and the maximum value match measure. For each set in the union, the method determines a local match measure or a local difference measure, and selects a reduced set of data sets based on the local match measure or the local difference measure.
The present invention includes the following embodiments. In an exemplary embodiment, the method selects a group of reduced data sets from the group of union based on the data set having the largest value of the local match measure. In another embodiment, the method selects a group of reduced data sets from the group of union based on the data set having the minimum value of the local measure of difference. In another embodiment, the data set is a day of data, and the method may modify the reference load profile based on daylight savings time. In yet another embodiment, the method may select a day of the selected data set based on the reference day data set. The days of the selected data set may include: a method of selecting a selected data set from data sets including any day between tuesday and thursday of the same week when the first and last days after the reference day are included; a method of selecting a selected data set from data sets including previous monday, sunday, and tuesday when the next day after the reference day is monday; and a method of selecting the selected data set from the data sets including the previous thursday, friday, and saturday when the next day after the reference day is friday. The method further selects the selected data set from data sets on previous friday, weekend and monday when the next day after the reference day is weekend, and selects the selected data set from data sets including the same previous holiday and no more than two days earlier or later than this holiday when the next day after the reference day is holiday.
Importantly, the present invention is not limited to systems or methods that must meet one or more of any of the stated objects or features of the present invention. It is also important that the invention not be limited to the exemplary embodiments described herein. Modifications and substitutions by one of ordinary skill in the art are considered to be within the scope of the present invention, which is not to be limited except by the following claims.
Drawings
These and other features and advantages of the present invention will be better understood by reading the following detailed description and by reference to the drawings, in which:
FIG. 1 is a block diagram of an exemplary ANN-based VSTLP embodiment 1000 system in accordance with the present invention.
Figure 2 is a block diagram of a conventional system according to an exemplary ANN-based VSTLP embodiment 2000 of the present invention.
Figure 3 is a block diagram of a next time system of an exemplary ANN-based VSTLP embodiment 3000 according to the invention.
Fig. 4 is a flow chart of an initial method according to the first and second exemplary embodiments of the present invention.
Fig. 5 is a flow chart of a continuous method according to a first exemplary embodiment of the present invention.
FIG. 6 is a flowchart of a method for selecting an exemplary embodiment of a reduced data set in accordance with the reduced data set of the present invention.
Fig. 7 is a flow chart of a continuous method according to a second exemplary embodiment of the present invention.
Detailed Description
The invention provides a neural network-based Very Short Term Load Predictor (VSTLP). Aspects of VSTLPs are described in more detail in U.S. patent application 2004/0249775 to Chen, 2004/0246643 to Chen, 2004/0257059 to Mansingh et al, 2004/0260489 to Mansingh et al, 2004/0257858 to Mansingh et al, and these applications are incorporated herein by reference. VSTLP requires determining the actual load data source and training off-line neural networks for on-line prediction and on-line training/tuning to improve prediction accuracy to obtain the actual load data source.
Load data for up to five whole day load curves are used for offline neural network training. The annual value of the specified time period load data is stored in the VSTLP database, where the 10-year value of the holiday load data is also stored. The dates of these load curves are used to identify potential sources of load data. In other words, the load data source is specified by date. The determination of the actual load data source for neural network training is achieved in two stages. The first stage involves the user specifying the date of one or more data sources. The second stage involves looking up the remaining best match dates with the closest load curve using the exemplary algorithm described below. The date of the first load data source may be specified by the user. The first set of load data is used to generate a reference load curve. Additional date data sets, for example four, may be specified by the user or looked up by the proposed algorithm.
Referring to fig. 1, a Very Short Term Load Predictor (VSTLP) module 1000 is a tool that predicts very short term system loads. VSTLP module 1000 uses a set of neural networks to predict system load for short term periods and short term intervals, such as predicting system load for the next 30 minute increment of 1 minute. If available, VSTLP module 1000 uses past load data and short term load prediction (STLF) data from an STFL module (not shown) to predict the upcoming load trend for the next 15 minutes.
Because the STLF module has recorded and simulated weather information, VSTLP module 1000 may not directly consider weather information or input weather information. However, it should be understood that the day pattern may be derived from a weather adaptive load prediction or manually entered. But weather change information is not used directly in the ANN-based VSTLP1000 (although other embodiments would use), but the STLF hourly predicted load value would be used to adjust the ANN-based VSTLP1000 predicted load value per minute.
To record load over season, weekday/weekend/holiday, and off-peak/peak time, a neural network may be trained to acquire a load pattern that is performed during a particular season, a particular day, and a particular time of day. Initially, one year is divided into spring (1 to 3 months), summer (4 to 6 months), autumn (7 to 9 months), and winter (10 to 12 months). This division may vary depending on the actual load characteristics of the particular location to which the VSTL module 1000 is applied. For example, the load properties on weekends (saturday and sunday) are different from those on weekdays (monday through friday). The division between weekdays and weekends can be made and based on the construction, the real environment. For example, weekends may include saturday, sunday, and monday, while weekdays may include tuesday through friday. Generally, the load characteristics on weekdays and weekends are usually recurring. However, the load characteristics on holidays are very different from those on regular weekdays/weekends. Holidays may be particularly considered, particularly large festivals such as thanksgiving and christmas. The load characteristics of the day before and after the holiday are also affected. For example, when collecting data for training a neural network associated with VSTLP1000, the interval from 6.
The ANN-based VSTLP structure is shown in FIG. 1. The decision algorithm 1010 of fig. 1 processes predicted load values from the corresponding ANN VSTLP module 1012 via 1028 (weekday, month, weekend, and holiday) at the end of each time limit and minimizes the effects of switching of the ANN VSTLP module 1000. The decision algorithm 1010 is implemented by a neural network. Over a shorter time period, and as shown in fig. 2, for each individual day, 6 neural networks (NN 1, NN2, NN3, NN4, NN5, NN 6) may be used to cover a 24-hour period (time period). In this embodiment, each neural network is responsible for a 4 hour period (sub-period), although other time allocations and numbers of neural networks may be employed. For example NN1, NN2, NN3, NN4, NN5 and NN6 cover 12. To ensure a smooth transition from one 4 hour period to the next, another half hour is added at the end of each 4 hour period. For example, NN1 covers 11 30pm to 4 30am, nn2 covers 3 30am to 8. Dividing a whole day into 6 different 4 hour periods reflects the fact that the load changes dynamically throughout the day. It should be understood that different time allocations, overlaps, and numbers of neural networks may be used. The use of multiple neural networks for different time periods of the day can be predicted more accurately. Such partitioning may vary according to the pattern of the real conditions. Thus, as also shown in FIG. 2, each ANN VSTLP module 1012-1028 shown in FIG. 1 has multiple ANNs to predict loads corresponding to a particular time period.
The decision algorithm 1010 in the daily ANN-based VSTLP algorithm shown in fig. 2 processes the predicted load values from the corresponding ANN VSTLP module at the end of each time limit and minimizes the effect of ANN VSTLP module switching. Decision algorithm unit 2010 may also be implemented by a neural network and may employ linear or non-linear decision algorithms as well as neural network transfer functions. Each NN will be implemented in one or two hidden layers depending on the complexity of the load dynamics it has to learn. More specifically, one or more neurons may be used in each neural network with varying weights, biases, linear and non-linear transfer functions. It should be understood that the inputs are affected by the weights and biases assigned to each neuron.
In the following equation, the load is represented by P. The next predicted load value for 15 minutes may be expressed as a function of the current load and the previous load value for N1-minutes:
here, P n+i (i is 1. Ltoreq. M) is the predicted load of the ith step (minute) in the future from the current time i. P n 、P n-i 、P n-2 、...、P n-N Is the actual load value for the current time and the previous N minutes. In this description, M represents a value of 15. The choice of N depends on the complexity of the load dynamics and will be determined by a method of trial-and-error experiment (trial-and-error experimental) with any load dynamics reasoning information available。
It was observed that the kinetics change with time in the above equation. However, the time-varying effect can be ignored over any single time period suitably divided over the entire day for 24 hours (23 or 25 when DST occurs). The load dynamics vary over different individual time periods. Thus, multiple NNs are used to address time-varying load dynamics. Within each individual time period, the load dynamics can be simply expressed as:
the above equation can be rewritten as a vector format as follows.
Because f is 1 、f 2 、...、f M Are unknown, so the exact form of these functions is also unknown, and with the available historical load data, a feed-forward neural network with the appropriate layers can be trained to approximate such functions.
Here, θ is a parameter vector containing the weights between adjacent layers and all neuron deviations, and is adjusted to minimize the difference between future calculated and actual values expressed in performance indices.
And training the neural network off line by adopting historical load data. After the neural network training and validation is complete, it is ready for online use. The weights may be adjusted to account for only the display load characteristics of the previous day by limiting on a daily basis. The weights may also be updated offline.
When the actual value P is available n 、P n-i 、P n-2 、...、P n-N The predicted load value P can be calculated immediately n+i (i is more than or equal to 1 and less than or equal to M). When P is not available n 、P n-i 、P n-2 、...、P n-N Will instead use the estimate generated from the ANN-based VSTLP at the previous time and further predict future loads. This can be repeated until all the minute-by-minute predicted values for the entire hour are calculated, as shown in fig. 3.
An adaptation scaling (adaptive scaling) unit 3010 in the ANN-based VSTLP of fig. 3 at the next time graph processes the original per minute predicted load values introduced from the four ANN-based VSTLP modules 3012-3018. Each of these VSTLP modules 3012-3018 is responsible for a prediction time period that is 15 minutes long and is scaled based on the predicted load value per hour issued by the STLF.
Assume that the number of inputs M is not greater than 15. Thus, at any instant n, when the prediction of the next hour's load value begins, the first ANN-based VSTLP will calculate the next 15 minute load value, P, based on the actual previous load value n+i (i is more than or equal to 1 and less than or equal to 15). When predicting load values for a time period from n +16 to n +30, the second ANN-based VSTLP will use some of the available predicted load values P per minute, since the actual load values for that time period are not yet available n+i (i is more than or equal to 1 and less than or equal to 15). In the same manner, the second ANN-based VSTLP predicts a load value P for a time period from n +16 to n +30 n+i (16. Ltoreq. I.ltoreq.30) plus { curvature sign. Similarly, both the third and fourth ANN-based VSTLPs will produce another predicted load value of 15 minutes, P n+i (31. Ltoreq. I. Ltoreq.45) and P n+i (i is more than or equal to 45 and less than or equal to 60). These four ANN-based VSTLPs will collectively yield the next 60 minute predicted load value. However, if the timestamp associated therewith exceeds the current hour, some of these predicted load values will not be employed in the adaptive scaling. If the current time is i minutes after the hour, then for a time period from n-i +1 to n,can obtain P n-i+1 、P n-i+2 、P n-i+3 、...、P n Actual values, and for the rest of the time period in this hour, only predicted values P can be obtained n+k (1. Ltoreq. K. Ltoreq.60-i) plus { curvature sign. The predicted load value P will be discarded according to the final application n+k (60-i + 1. Ltoreq. K. Ltoreq.60-i) or not predicting the corresponding time period at all.
For example, let the scaling factor be s n Let STLF predict load value per hour for current time as P stlf . To match the predicted load per minute during this hour with the predicted load per hour with satisfactory accuracy for STLF, the following equation is used:
therefore, the temperature of the molten metal is controlled,
the modified predicted load per minute value for the future time period from n +1 to n +60-i in the current hour is then s n P n+k (k is more than or equal to 1 and less than or equal to 60-i). However, it should be understood that Sn changes in time as the predicted 15 minute sliding window updates every minute. S. the n Is also a performance marker for ANN-based VSTLP. If S is n With a small fluctuation around 1 (or substantially around 1), and assuming that the hourly load pattern is fully captured by STLF with satisfactory accuracy, this indicates that the ANN-based VSTLP performs reasonably well in the sense that the predicted load values per minute produced by the ANN-based VSTLP are consistent with the predicted load values per hour of STLF. In addition, it should be noted that inconsistent loads must be addressed and separately processed or filtered out to minimize or eliminate their effect on ANN-based VSTLP prediction accuracy. In addition, in some instances, STLF should be more than the most load-predicted oneThe large prediction period is still long.
The historical load data stored in HFD/HIS1030 must be formatted in an appropriate format before it can be used to train the ANN-based VSTLP neural network. This may be accomplished through an interface program that retrieves the historical data from the HFD/HIS, reformats it, and sends it to the main program responsible for neural network training. The historical data is preferably divided into two different sets. The first set of data is used to train the neural network, while the second set of data is used to evaluate the performance of the trained neural network to prevent over-training of the neural network. Based on the performance assessment, the number of training sessions can be specified and the final training achieved with all available and useful historical data. Information related to the ANN-based VSTLP1000, such as the number of layers, the number of neurons in each layer, the initiation functions, weights and offsets, etc., are stored in a file.
Structural and parameter information related to the ANN-based VSTLP1000 is retrieved to initialize the neural network of the ANN-based VSTLP. As with VSTLP offline training, the interface program retrieves historical load data, or other online application that temporarily stores historical load data, from HFD/HIS5030 and sends it to the initialized neural network for load prediction. The resulting predicted load per minute values will be used for generation, scheduling and display purposes. These load values are also stored for post-hoc performance evaluation.
The weights and biases of the neural network can be updated online by using the actual load values in the immediate past and the predicted load values generated from the neural network. This is based on the fact that the passing load characteristics can be used to improve the accuracy of predicting the next future load. Beyond a certain period of time (e.g., the time period defined by a daily ANN-based VSTLP map), the weights and biases are discarded and the initial weights and biases are reinstalled. The weights and biases can also be updated monthly, weekly, daily, hourly or even at shorter intervals depending on the real environment.
The algorithms of the first and second exemplary embodiments take into account two conditions: the candidate load curve is similar to the user-specified reference load curve and the candidate load curve displays a degree of deviation from the reference load curve. The first condition selected load curves are close to the reference curves, so that these load curves show a dominant load trend that is very good for capturing neural networks by training. The second condition requires that the selected load curve be varied around the reference curve so that the neural network can be generalized after the training is completed.
Regarding the first load curve specified by the user as the reference load curve, the reference load curve is represented by t e (0, 1440)](t in min) of C r (t) represents. The summer time (DST) can be treated as follows: for long DST days, load data of repeated hours is not used; for a short DST day, the load data for the second hour was repeated for a time period from 2 00. With this treatment, there was a load curve comprising 1440 1-minute load data points or 288 5-minute load data points per day. For explanation, but without loss of generality, the loading curve is assumed to have 1440 1-minute load data points.
Can be formed by i E [1,N]C with N less than or equal to 4 i lll (t) represents the load curve for the best match date (still to be identified based on the algorithm of the exemplary embodiment). Any date in the year can be represented by the subscript k, 1 ≦ k ≦ 365 and n represents C for the year when the holiday search was performed k n (t) represents the load curve stored in the VSTLP at any date. Target slave C k n (t)'s search for C i lll (t)′s。
Referring to fig. 4, a first exemplary algorithm 400 utilizes both whole load curve matching and part load curve matching. The user provides a reference date, and the system retrieves a reference load curve C r Reference data of (t) (section 402). The system may make the DST adjustment t e (1, 1440) as previously described](element 404). The system determines which day to reduce based on the next day of the week (i.e., the day after the reference day) (element 406). Once the data set is determined, load data for these dates is retrieved from the VSTLP database (element 408). Data can be stored in storage load data for annual valueIn the special table (2). The best matching date (and thus the load data of the neural network training) may be selected on the current day, and the trained neural network used to predict the load characteristics the next day. The screening step to determine the reduced date set Ω is described in more detail in FIG. 6, described below.
The system loops through the reduced date set Ω (element 410). The system may be driven from a VSTLPDatabase retrieval of one load curve at a time, C k n (t) (element 412). The system may make the necessary DST adjustments te e (1, 1440) for each set of date data as previously described](element 413). For each set of date data, calculate each curve C k n The global difference measure and the match measure of (t) (element 414). Reference curve C r (t) and C k n The integrated square of the difference between (t) is as follows:
curve C k n (t) vs. reference curve C r The matching of (t) is as follows:
referring to FIG. 5, the system pairs all A 1 (n, k) sorting to pick the desired lowest value, whereby A 1 (n 1 ，k 1 )≤A 1 (n 2 ，k 2 )≤A 1 (n 3 ，k 3 )≤A 1 (n 4 ，k 4 )≤A 1 (n, k) where the pair of (n, k) identifies not four identification dates (n) 1 ，k 1 )、(n 2 ，k 2 )、(n 3 ，k 3 )、 (n 4 ，k 4 ) Unique date (date k in year n), and definition D 1 ＝ {(n 1 ，k 1 )，(n 2 ，k 2 )，(n 3 ，k 3 )，(n 4 ，k 4 ) A reference date (element 516).According to the exemplary embodiment herein, the desired number is 4, but the present invention is not limited to four sets.
The system also applies to all A 2 (n, k) ordering to pick the four maxima, thus A 2 (n 5 ，k 5 )≤A 2 (n 6 ，k 6 )≤A 2 (n 7 ，k 7 )≤A 2 (n 8 ，k 8 )≤A 2 (n, k) where the pair of (n, k) identifications is not four identification dates (n) 5 ，k 5 )、(n 6 ，k 6 )、(n 7 ，k 7 )、(n 8 ，k 8 ) Unique date of, and definition D 2 ＝{(n 5 ，k 5 )，(n 6 ，k 6 )，(n 7 ，k 7 )，(n 8 ，k 8 ) The reference date (element 518). Similarly, according to the exemplary embodiment herein, the desired number is 4, but the present invention is not limited to four sets. The system then generates a union of dates D = D 1 ∪D 2 To remove any duplicate dates and therefore have at least four dates and a maximum of eight dates according to exemplary embodiment D (element 520).
The system then cycles through the date set D for the dates identified by pair (n, k) (element 522). The system according to the first exemplary embodiment may calculate the following local match measure (element 524). Local match measure at time period T = { T | N 1 ≤t≤N 2 Match curve C k n (t) and reference curve C r (t), whereby the neural network is trained to be responsible for load prediction. Is defined as follows:
as described above, the entire day is divided into a number of non-overlapping time segments, and for each time segment there is a neural network designed and trained to be responsible for providing load predictions. As described in more detail with reference to the second exemplary embodiment, the local match measure is used when loading the training and predictionThe degree is more reasonable than the local measure of difference. The system is to all A 3 (N, k) sorting to pick the maximum of N (depending on how many automatically generated matching dates N ≦ 4 are required) and find the corresponding date- -depending on the three matching criteria applied: a1, A2, A3 serve as best match dates providing best load curve matching (element 526).
Referring to FIG. 6, the system determines a reduced date set based on the next day of the week (i.e., the base day) according to reduced date data set selection embodiment 600 (element 406). If the system determines that the next first and last day is included inland between Tuesday and Thursday, then any workday between Tuesday and Thursday that includes the same week may be included in the selected set of dates (element 602). If the system determines that the next day is Monday, then the previous Monday, sunday, and Tuesday are included in the selected set of dates (element 604). If the system determines that the next day is Friday, then the previous Thursday, friday, and Saturday are included in the selected set of dates (element 606). If the system determines that the next day is any of the weekends, then the previous Friday, weekend, and Monday are included in the selected set of dates (element 608). These behaviors allow the system to consider the day of the week selected for the data set.
The system also takes holidays into account when selecting dates for the reduced data set. If the system determines that the next day is a holiday, the selected set of dates includes the same holiday before and no more than two days earlier or later than the holiday (element 610). In addition, the system also prevents the reference date from being used as a data set (element 612). The system also provides a data set that takes into account the day of the week and the holiday for the reference date.
An increasing load curve is formed from the load curve. Slave load curve C k n (t) is formed by Δ C k n (t)(t∈1，1440]) Curve of increasing load represented, where t e (1, 1440)]. For illustration purposesThe same interval for the exemplary embodiment is1 minute, but the invention is not limited to 1 minute increments. Various increments may be used, for exampleFor example, the increment may be 5 minutes, in which case, p + -t e (1, 1440)]， Neural network based very short term load prediction provides a method that will also train and predict based on load increments. To better apply this method, curve matching based on load increments is an alternative choice.
The second exemplary algorithm 700 also utilizes global load curve matching as well as partial load curve matching. The second exemplary algorithm 700 performs the same steps as described in the first exemplary algorithm 400 with reference to fig. 4. The second exemplary algorithm 700 continues from element 414 of fig. 4 to element 716 of fig. 7.
The system is to all A 1 (n, k) sorting to pick the lowest value desired, thus A 1 (n 1 ，k 1 )≤A 1 (n 2 ，k 2 )≤A 1 (n 3 ，k 3 )≤A 1 (n 4 ，k 4 )≤A 1 (n, k) where the pair of (n, k) identifications is not four identification dates (n) 1 ，k 1 )、(n 2 ，k 2 )、(n 3 ，k 3 )、(n 4 ，k 4 ) Unique date (date k in year n), and definition D 1 ＝{(n 1 ，k 1 )，(n 2 ，k 2 )， (n 3 ，k 3 )，(n 4 ，k 4 ) The reference date (element 716). According to the exemplary embodiment herein, the desired number is 4, but the present invention is not limited to four sets.
The system also applies to all A 2 (n, k) ordering to pick the four maxima, thus A 2 (n 5 ，k 5 )≤A 2 (n 6 ，k 6 )≤A 2 (n 7 ，k 7 )≤A 2 (n 8 ，k 8 )≤A 2 (n, k) where the pair of (n, k) identifications is not four identification dates (n) 5 ，k 5 )、(n 6 ，k 6 )、(n 7 ，k 7 )、(n 8 ，k 8 ) Unique date of, and definition D 2 ＝{(n 5 ，k 5 )，(n 6 ，k 6 )，(n 7 ，k 7 )，(n 8 ，k 8 ) The reference date (element 718). Similarly, according to the exemplary embodiment herein, the desired number is 4, but the present invention is not limited to four groups. The system then generates a union of dates D = D 1 ∪D 2 To remove any duplicate dates and therefore have at least four dates and a maximum of eight dates according to exemplary embodiment D (element 720).
The system then cycles through the set of dates D for the dates identified by pair (n, k) (element 7522). The system according to the first exemplary embodiment may calculate the following local match measure (element 724). The system loops through the set of dates D for each date identified by pair (n, k) and calculates a local difference measure. In a time period T = { T | N 1 ≤t≤N 2 Reference curves Δ Cr (t) and Δ C on which the neural network is trained to be responsible for load prediction k n (t) the integrated square of the difference is:
the day is divided into a number of non-overlapping time segments, and for each time segment there is a neural network designed and trained to be responsible for providing load predictions. When the load is added to the entire curve match, the local difference measure is more reasonable than the local match measure of the first embodiment. The system is to all A 3 (N, k) are ordered to pick the minimum value of N (depending on how many automatically generated matching dates N ≦ 4 are needed) (element 726). The system looks up the corresponding date-according to the three matching criteria applied: a1, A2, A3 are used as the best matching dates for providing the best load curve matching.
The systems and methods employed in the first exemplary embodiment 400 and the second exemplary embodiment may be implemented in various ways. Exemplary embodiments use the set of power generation data at different time periods. The present invention is not limited to power generation data. As understood by those skilled in the art, the ANN VSTLP may be used for various simulation and training purposes.
The system and method may be implemented in hardwired or programmable hardware. The systems and methods may be implemented within the scope of software that utilizes various components to implement the embodiments described herein. Aspects disclosed in the exemplary embodiments may be utilized independently or in conjunction with other exemplary embodiments. Moreover, it will be understood that the foregoing is only illustrative of the principles of the invention, and that various modifications can be made by those skilled in the art without departing from the scope and spirit of the invention. Those skilled in the art will appreciate that the present invention can be practiced by other than the described embodiments, which are presented for purposes of illustration and not of limitation, and the present invention is limited only by the claims that follow.
Claims (20)
1. A system for identifying a neural network data source, comprising:
a module for determining a load curve for each selected data set;
a module for determining a global difference measure and a global matching measure for each load curve of each selected data set;
a module for determining a set of data sets having a minimum global measure of difference;
a module for determining a set of data sets having a maximum global measure of match;
a module for determining a union of the minimum difference measure and the maximum match measure;
a module to determine each set in a union of local match measures and local difference measures; and
a module that selects a reduced set of data sets based on one of a local measure of match and a local measure of difference.
2. The system of claim 1, further comprising:
a module for selecting a reduced set of data from the union set based on the data set having the largest value of the local match measure.
3. The system of claim 1, further comprising:
a module for selecting a reduced set of data from the union set based on the data set having the local measure of difference minimum.
4. The system of claim 1, wherein the data set is a one-day period of data, and further comprising:
and a module that modifies the baseline load curve based on the daylight savings time system.
5. The system of claim 1, wherein the data set is a one-day period of data, and further comprising:
a module that selects a selected data set day based on the reference day data set.
6. The system of claim 5, further comprising:
selecting the selected data set from data sets including any day between tuesday and thursday of the same week when the first and last days of the next day after the reference day are included; selecting the selected data set from the data sets including previous monday, sunday, and tuesday when the next day after the reference day is monday; and a module that selects the selected data set from the data sets including previous thursday, friday, and saturday when the next day after the reference day is friday.
7. The system of claim 5, further comprising:
selecting the selected data set from the data sets including previous friday, weekend and monday when the next day after the reference day is any day of the weekend;
and when the next day after the reference day is a holiday, selecting the selected data set from data sets including the same previous holiday and no more than two days earlier or later than the holiday.
8. A method of identifying a neural network data source, comprising the acts of:
determining a load curve for each selected data set;
determining a global difference measure and a global matching measure for each load curve of each selected data set;
determining a set of data sets having a minimum global measure of difference;
determining a set of data sets having a maximum global matching measure;
determining a union of the minimum difference measure and the maximum matching measure;
determining each set in a union of local match measures and local difference measures; and
a reduced set of data sets is selected based on one of a local match measure and a local difference measure.
9. The method of claim 8, further comprising the acts of:
a reduced set of data sets is selected from the union set based on the data set having the local match measure maximum.
10. The method of claim 8, further comprising the acts of:
a reduced set of data sets is selected from the union of sets based on the data sets having the local measure of difference minimum.
11. The method of claim 8, wherein the data set is a one-day period of data, and further comprising the acts of:
the baseline load curve is modified based on the daylight savings time system.
12. The method of claim 8, wherein the data set is a one-day period of data, and further comprising the acts of:
the day of the selected data set is selected based on the reference day data set.
13. The method of claim 12, further comprising the acts of:
selecting the selected data set from data sets including any day between tuesday and thursday of the same week when the first and last days of the next day after the reference day are included;
selecting the selected data set from the data sets including previous monday, sunday, and tuesday when the next day after the reference day is monday; and
when the next day of the reference day is friday, the selected data set is selected from the data sets including the previous thursday, friday, and saturday
14. The method of claim 12, further comprising the acts of:
selecting the selected data set from the data sets including previous friday, weekend and monday when the next day after the reference day is any day of the weekend;
and when the next day after the reference day is a holiday, selecting the selected data set from data sets including the same previous holiday and no more than two days earlier or later than the holiday.
15. The method of claim 12, further comprising the acts of:
selecting the selected data set for any day not including the reference day.
16. A system for identifying a neural network based very short term load forecast match data source in operating a power generation unit, comprising:
a module for determining a load curve for each of the selected date data sets;
a module for determining a global difference measure and a global match measure for each load curve for each selected date data set;
a module for determining a set of date data sets having a minimum global measure of difference;
a module for determining a set of date data sets having a maximum global match measure;
a module for determining a union of the minimum difference measure date set and the maximum matching measure date set;
a module for determining each date set in a union of local match measures and local difference measures; and
a module for selecting a data set of a reduced set of data sets based on one of a local measure of match and a local measure of difference.
17. The system of claim 16, further comprising:
a module for selecting a data set of reduced date data sets from the data sets of the union based on the date data set having the largest value of the local match measure.
18. The system of claim 16, further comprising:
a module for selecting a data set of reduced date data sets from the data sets of the union based on the date data set having the smallest value of the local difference measure.
19. The system of claim 16, further comprising:
and a module that modifies the baseline load curve based on the daylight savings time system.
20. The system of claim 16, further comprising:
selecting the selected date data set from the date data sets including any day between tuesday and thursday of the same week when the first and last days of the next day after the reference day are included; selecting the selected date data set from the date data sets including previous monday, sunday, and tuesday when the next day after the reference day is monday; and a module that selects the selected date data set from the date data sets including the previous thursday, friday, and saturday when the next day after the reference day is friday.
Applications Claiming Priority (6)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| US64967705P | 2005-02-03 | 2005-02-03 | |
| US60/649,877 | 2005-02-03 | ||
| US60/649,876 | 2005-02-03 | ||
| US60/649,677 | 2005-02-03 | ||
| US60/649,803 | 2005-02-03 | ||
| US11/345,438 | 2006-02-01 |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410007810.XA Division CN103729679A (en) | 2005-02-03 | 2006-02-02 | System and method for identifying data sources for neutral network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN101116094A true CN101116094A (en) | 2008-01-30 |
Family
ID=39023484
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNA2006800038642A Pending CN101116094A (en) | 2005-02-03 | 2006-02-02 | Identify data sources for neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101116094A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112330077A (en) * | 2021-01-04 | 2021-02-05 | 南方电网数字电网研究院有限公司 | Power load prediction method, power load prediction device, computer equipment and storage medium |
-
2006
- 2006-02-02 CN CNA2006800038642A patent/CN101116094A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112330077A (en) * | 2021-01-04 | 2021-02-05 | 南方电网数字电网研究院有限公司 | Power load prediction method, power load prediction device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP1856657B1 (en) | Identify data sources for neural network | |
| US10660241B2 (en) | Cooling unit energy optimization via smart supply air temperature setpoint control | |
| US20230125805A1 (en) | Controller training based on historical data | |
| Senjyu et al. | Next day load curve forecasting using hybrid correction method | |
| Wi et al. | Holiday load forecasting using fuzzy polynomial regression with weather feature selection and adjustment | |
| Fernández et al. | Efficient building load forecasting | |
| Lee et al. | Individualized short-term electric load forecasting with deep neural network based transfer learning and meta learning | |
| US20070185823A1 (en) | Load prediction based on-line and off-line training of neural networks | |
| US11815863B2 (en) | Predictive modeling and control for water resource infrastructure | |
| CN115696533B (en) | 5G-based communication base station energy consumption optimization method and equipment | |
| de Andrade et al. | Very short-term load forecasting based on NARX recurrent neural networks | |
| KR101662809B1 (en) | Apparatus and method for forecasting electrical load in railway station | |
| CN101116094A (en) | Identify data sources for neural network | |
| Jung et al. | Very short-term electric load forecasting for real-time power system operation | |
| Raza et al. | A comparative analysis of PSO and LM based NN short term load forecast with exogenous variables for smart power generation | |
| Aburto et al. | A sequential hybrid forecasting system for demand prediction | |
| JPH0922402A (en) | Estimating method for daily maximum power demanded | |
| Mishra et al. | Monthly energy consumption forecasting based on windowed momentum neural network | |
| JP4298581B2 (en) | Power demand forecasting device, power demand forecasting system, power demand forecasting program, recording medium, and power demand forecasting method | |
| Hutama et al. | Medium term power load forecasting for Java and Bali power system using artificial neural network and SARIMAX | |
| JPH0830581A (en) | Method for predicting quantity of demand | |
| EP1270827A1 (en) | Water distribution amount predicting system | |
| JPH11126102A (en) | Predictive method for demand of gas | |
| CN117709520A (en) | Time sequence prediction method for weight adjustment based on particle swarm optimization | |
| CN114118591A (en) | Online learning-based method and system for predicting power load interval of transformer area |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| ASS | Succession or assignment of patent right |
Owner name: SIEMENS ENERGY INC. Free format text: FORMER OWNER: SIEMENS POWER TRANSMISSION AND DISTRIBUTION CO., LTD. Effective date: 20120224 |
|
| C41 | Transfer of patent application or patent right or utility model | ||
| C53 | Correction of patent of invention or patent application | ||
| CB02 | Change of applicant information |
Address after: Munich, Germany Applicant after: SIEMENS AG Address before: American Florida Applicant before: SIEMENS ENERGY, Inc. Address after: American Florida Applicant after: SIEMENS ENERGY, Inc. Address before: American Florida Applicant before: SIEMENS POWER GENERATION, Inc. |
|
| COR | Change of bibliographic data |
Free format text: CORRECT: APPLICANT; FROM: SIEMENS POWER GENERATION INC. TO: SIEMENS AG Free format text: CORRECT: APPLICANT; FROM: SIEMENS ENERGY INC. TO: SIEMENS POWER GENERATION INC. |
|
| TA01 | Transfer of patent application right |
Effective date of registration: 20120224 Address after: American Florida Applicant after: SIEMENS POWER GENERATION, Inc. Address before: North Carolina Applicant before: Siemens Power Transmission & Distribution, Inc. |
|
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20080130 |