Slide 1Slide 2Slide 3Slide 4Slide 5Slide 6Slide 7Slide 8Slide 9Slide 10ECE 539 Project2010 Fall1An Initial ANN Approach to LMP Classification & PredictionHonghao ZhengUniversity of Wisconsin – Madison©Honghao Zheng 2010ECE 539 Project2010 Fall2Motivation•Locational Marginal Price (LMP), which is usually referred to as “shadow price” of the power grid, gives efficient measurement of power production and the consumption of energy at the different bus nodes.•The prediction of LMP at different zonal price could benefit the individual biding for the electricity at different nodes in the power system.•If we could locate the feature vector, then we could use ANN method to predict the PMU value at certain time in certain place.ECE 539 Project2010 Fall3Previous WORK[1] Zonal Prices Analysis Supported by a Data Mining Based Methodology, J. Ferreira, S. Ramos, Z. Vale and J. P. Soares. IEEE Conference Proceedings, 2010.[2] Zone Clustering LMP with Location information using an Improved Fuzzy C-Mean, Se-Hwan Jang, Jin-Ho Kim, Sang-Hyuk Lee and June-Ho Park, IEEE Conference Proceedings.[3] High value wind: A method to explore the relationship between wind speed and electricity locational marginal price, Geoffrey McD. LewisECE 539 Project2010 Fall4The first step of the project would be manually filtering the large amount of LMP hourly data into different groups.The LMP data is downloaded from the website of Midwest Independent System Operator (Midwest ISO). Filters: Time = April, Value = LMP, Type = LoadZoneMethodologyStep No.1ECE 539 Project2010 Fall5MethodologyStep No.2Step No.2 mainly concerns with the feature vector selection.Major Issue that may influence the value of LMP: 1. Grid structure; 2. Weekday or Weekend (7 days in one week); 3. Different period in a day (Morning/Noon/Evening)1. Generate physical position of different load zones;2. Grant different weights to the seven days;3. Choose 4 hours to be one period, all have high LMP.Feature Vector Dimension: 4ECE 539 Project2010 Fall6ALTE ALTW AMRN CILC CIN CONS CWLD CWLP3 11 35 3 13 21 3 3DECO DPC EKPC FE GRE HE IP IPL24 6 1 15 9 2 10 2IGEE MDU MGE MP NIPS NSP OTP SIGE4 4 1 8 4 26 15 4SIPC TVA UPPC WEC WPS WR TOTAL1 1 1 5 2 1 238MethodologyStep No.2(Cont’d)Generate Geographic Location:ECE 539 Project2010 Fall7MethodologyStep No.3The Step No.3 Using MLP Mapping to Test the data1. Classification Criterion: <35 LOW LMP, 35~50 MID LMP, >50 HIGH LMP2. Separate the 28 days in Apr into 4 weeks, labeled W1, W2, W3, W4.3. Formulate 3 tests: Training Set (W1, W1&W2, W1&W2&W3), Testing Set (W2&W3&W4, W3&W4, W4)Here the testing set functions as the prediction, because in the future if we know the feature vector, we could use MLP to predict the LMP value directly.ECE 539 Project2010 Fall8Simulation ResultWays of Training Layer = 3, Neurons/Layer = 5 Layer = 4, Neurons/Layer = 6TrainingRate PredictionRate TrainingRate PredictionRateT.1 71.47% 55.12% 83.87% 50.26%T.2 67.98% 54.89% 67.467% 53.12%T.3 65.55% 53.20% 63.15% 61.50%Training Training Set Testing SetT.1 W1 W2,W3,W4T.2 W1,W2 W3,W4T.3 W1,W2,W3 W4Comment:1. Training Rate does not have necessary relationship with the Prediction Rate2. Prediction Rate (Testing Rate) is not that high as expected.3. The randomly-generated location may result in the inconsistency.ECE 539 Project2010 Fall9DiscussionDisturbance & Ways to ImproveDisturbance:1. Inconsistency in the location2. The classification of the LMP may be too rough to determine the exact position of LMP.3. Possible feature difference not quite clear.Ways to Improve:1. Acquire actual geographic location (longitude, latitude).2. Classify the LMP value range smaller.3. To make the range difference between the features to be obvious.ECE 539 Project2010 Fall10Conclusion1. ANN: quite a useful tool in the power system, yet the application of prediction for LMP value is rare.2. The result that has the best performance (63%) is roughly acceptable, yet not the expected value.3. Outlook: make the model more realistic; trying to get the location data from the government; change MLP algorithm to better suitable for LMP
View Full Document
Unlocking...