Transcript

8/6/2019 Viet - Prediction of Natural Gas Consumption With Feed-Forward and Fuzzy Neural Networks

http://slidepdf.com/reader/full/viet-prediction-of-natural-gas-consumption-with-feed-forward-and-fuzzy-neural 1/17

Prediction of Natural GasConsumption with Feed-forward andFuzzy Neural Networks

N.H. Viet Institute of Fundamental Tech. Research

Polish Academy of Sciences Poland,

J. MadziukFaculty of Mathematics and Information Science

Warsaw University of Technology Poland.

8/6/2019 Viet - Prediction of Natural Gas Consumption With Feed-Forward and Fuzzy Neural Networks

http://slidepdf.com/reader/full/viet-prediction-of-natural-gas-consumption-with-feed-forward-and-fuzzy-neural 2/17

N.H. Viet, J. Madziuk: Prediction of Natural Gas Consumption with Neural Networks

Presentations schedule

Introduction

Feed-forward neural networks

Fuzzy neural networks

Experimental results and conclusions

8/6/2019 Viet - Prediction of Natural Gas Consumption With Feed-Forward and Fuzzy Neural Networks

http://slidepdf.com/reader/full/viet-prediction-of-natural-gas-consumption-with-feed-forward-and-fuzzy-neural 3/17

N.H. Viet, J. Madziuk: Prediction of Natural Gas Consumption with Neural Networks

Introduction

Prediction of gas consumption is an important element in business planning.

The challenges:

the volatility of consumer profile, the strong dependency on weather conditions,

the lack of historical data.

The purpose of this work: an application to gas

load prediction using various neural networkmodels.

8/6/2019 Viet - Prediction of Natural Gas Consumption With Feed-Forward and Fuzzy Neural Networks

http://slidepdf.com/reader/full/viet-prediction-of-natural-gas-consumption-with-feed-forward-and-fuzzy-neural 4/17

N.H. Viet, J. Madziuk: Prediction of Natural Gas Consumption with Neural Networks

Introduction

Three types of prediction: One day (short-term) prediction,

One week (mid-term) prediction,

Four week (long-term) prediction.

8/6/2019 Viet - Prediction of Natural Gas Consumption With Feed-Forward and Fuzzy Neural Networks

http://slidepdf.com/reader/full/viet-prediction-of-natural-gas-consumption-with-feed-forward-and-fuzzy-neural 5/17

N.H. Viet, J. Madziuk: Prediction of Natural Gas Consumption with Neural Networks

Introduction

The data contains the daily gas loads and the averagedaily temperatures.

Seasonality

Strongdependency ontemperature.

 An overview of the data:

8/6/2019 Viet - Prediction of Natural Gas Consumption With Feed-Forward and Fuzzy Neural Networks

http://slidepdf.com/reader/full/viet-prediction-of-natural-gas-consumption-with-feed-forward-and-fuzzy-neural 6/17

N.H. Viet, J. Madziuk: Prediction of Natural Gas Consumption with Neural Networks

Introduction

The inputs: Historical daily gas loads,

 Average daily temperatures

Time factor (the season inputs) For the n-day period: [t + 1, t + n], two values were used:

Where:

One additional bit indicating the work day/weekend day inthe case of daily prediction.

8/6/2019 Viet - Prediction of Natural Gas Consumption With Feed-Forward and Fuzzy Neural Networks

http://slidepdf.com/reader/full/viet-prediction-of-natural-gas-consumption-with-feed-forward-and-fuzzy-neural 7/17

N.H. Viet, J. Madziuk: Prediction of Natural Gas Consumption with Neural Networks

Feed-forward model

General network architecture:

Previous daily loads

Previous daily temperatures

Time encoding

8/6/2019 Viet - Prediction of Natural Gas Consumption With Feed-Forward and Fuzzy Neural Networks

http://slidepdf.com/reader/full/viet-prediction-of-natural-gas-consumption-with-feed-forward-and-fuzzy-neural 8/17

N.H. Viet, J. Madziuk: Prediction of Natural Gas Consumption with Neural Networks

Feed-forward model

Chosen configurations: One day prediction: 9(3+3+3)-8(3+3+2)-3-1

One week prediction: 12(5+5+2)-10(4+4+2)-4-1

Four week prediction: 16(7+7+2)-10(4+4+2)-4-1

8/6/2019 Viet - Prediction of Natural Gas Consumption With Feed-Forward and Fuzzy Neural Networks

http://slidepdf.com/reader/full/viet-prediction-of-natural-gas-consumption-with-feed-forward-and-fuzzy-neural 9/17

N.H. Viet, J. Madziuk: Prediction of Natural Gas Consumption with Neural Networks

Fuzzy neural model

Why to use the fuzzy neural model?: Impreciseness of data (only average daily

temperature is available),

Fuzzy neural networks generally have a better

performance,

8/6/2019 Viet - Prediction of Natural Gas Consumption With Feed-Forward and Fuzzy Neural Networks

http://slidepdf.com/reader/full/viet-prediction-of-natural-gas-consumption-with-feed-forward-and-fuzzy-neural 10/17

N.H. Viet, J. Madziuk: Prediction of Natural Gas Consumption with Neural Networks

Fuzzy neural model

Fuzzy neural network architecture:

Membership layer Defuzzification layer

8/6/2019 Viet - Prediction of Natural Gas Consumption With Feed-Forward and Fuzzy Neural Networks

http://slidepdf.com/reader/full/viet-prediction-of-natural-gas-consumption-with-feed-forward-and-fuzzy-neural 11/17

N.H. Viet, J. Madziuk: Prediction of Natural Gas Consumption with Neural Networks

Fuzzy neural model

Fuzzy neural network dynamics: Gaussian membership function:

Output:

8/6/2019 Viet - Prediction of Natural Gas Consumption With Feed-Forward and Fuzzy Neural Networks

http://slidepdf.com/reader/full/viet-prediction-of-natural-gas-consumption-with-feed-forward-and-fuzzy-neural 12/17

N.H. Viet, J. Madziuk: Prediction of Natural Gas Consumption with Neural Networks

Fuzzy neural model

FNN can be trained using the gradient-basedtechnique.

 An equivalent rule sets:

8/6/2019 Viet - Prediction of Natural Gas Consumption With Feed-Forward and Fuzzy Neural Networks

http://slidepdf.com/reader/full/viet-prediction-of-natural-gas-consumption-with-feed-forward-and-fuzzy-neural 13/17

N.H. Viet, J. Madziuk: Prediction of Natural Gas Consumption with Neural Networks

Experimental results and conclusions

Training data: from Jan. 01, 2000 to Dec. 31,2001.

Testing data: from Jan. 01 2002 to Jul. 31, 2002.

The moving window technique was used togenerate the training and the testing samples.

The following experiments were performed: Single feed-forward network (SingleN)

Single fuzzy network (FuzzyN) 3 feed-forward networks (3AvgN)

3 temperature context networks (3TempN)

8/6/2019 Viet - Prediction of Natural Gas Consumption With Feed-Forward and Fuzzy Neural Networks

http://slidepdf.com/reader/full/viet-prediction-of-natural-gas-consumption-with-feed-forward-and-fuzzy-neural 14/17

N.H. Viet, J. Madziuk: Prediction of Natural Gas Consumption with Neural Networks

Experimental results and conclusions

Temperature context networks: Divide the training set into 3 overlapping subsets

(denoted by Low, Medium and High ) using theaverage temperature,

Train 3 types of networks with these setsindependently,

Combine 3 networks into one module while testing.

Remark: training the networks within a particular

context should be easier than in the entire input space.

8/6/2019 Viet - Prediction of Natural Gas Consumption With Feed-Forward and Fuzzy Neural Networks

http://slidepdf.com/reader/full/viet-prediction-of-natural-gas-consumption-with-feed-forward-and-fuzzy-neural 15/17

N.H. Viet, J. Madziuk: Prediction of Natural Gas Consumption with Neural Networks

Experimental results and conclusions

8/6/2019 Viet - Prediction of Natural Gas Consumption With Feed-Forward and Fuzzy Neural Networks

http://slidepdf.com/reader/full/viet-prediction-of-natural-gas-consumption-with-feed-forward-and-fuzzy-neural 16/17

N.H. Viet, J. Madziuk: Prediction of Natural Gas Consumption with Neural Networks

Experimental results and conclusions

 An example of one week and four week prediction:

8/6/2019 Viet - Prediction of Natural Gas Consumption With Feed-Forward and Fuzzy Neural Networks

http://slidepdf.com/reader/full/viet-prediction-of-natural-gas-consumption-with-feed-forward-and-fuzzy-neural 17/17

Thank you for your Thank you for your attentionattention


Top Related