A Decision Tree Classification Model For Determining The Location For Solar Power Plant A PRESENTATION BY-  DISHANT MITTAL  DEV GAURAV VIT UNIVERSITY,VELLORE.

Slides:



Advertisements
Similar presentations
The SRP Powering Our Future Classroom Outreach Presentation
Advertisements

Random Forest Predrag Radenković 3237/10
CHAPTER 9: Decision Trees
Decision Tree Approach in Data Mining
K-NEAREST NEIGHBORS AND DECISION TREE Nonparametric Supervised Learning.
© NERC All rights reserved Storms rare but important Balance dataset otherwise storms look like noise Features selected like Split: training set, validation.
SLIQ: A Fast Scalable Classifier for Data Mining Manish Mehta, Rakesh Agrawal, Jorma Rissanen Presentation by: Vladan Radosavljevic.
On the Influence of Weather Forecast Errors in Short-Term Load Forecasting Models Damien Fay, John V. Ringwood IEEE POWER SYSTEMS, 2010.
Civil and Environmental Engineering Carnegie Mellon University Sensors & Knowledge Discovery (a.k.a. Data Mining) H. Scott Matthews April 14, 2003.
Decision Tree Rong Jin. Determine Milage Per Gallon.
Constructing a Large Node Chow-Liu Tree Based on Frequent Itemsets Kaizhu Huang, Irwin King, Michael R. Lyu Multimedia Information Processing Laboratory.
© Prentice Hall1 DATA MINING Introductory and Advanced Topics Part II Margaret H. Dunham Department of Computer Science and Engineering Southern Methodist.
Distributed Representations of Sentences and Documents
Ordinal Decision Trees Qinghua Hu Harbin Institute of Technology
What is Nuclear Energy? Nuclear energy or atomic energy is the energy that is released spontaneously or artificially in nuclear reactions. The main feature.
Attention Deficit Hyperactivity Disorder (ADHD) Student Classification Using Genetic Algorithm and Artificial Neural Network S. Yenaeng 1, S. Saelee 2.
3.3 Energy Resources Human Population, Carrying Capacity, and Resource Use.
BIOLOGY 157: LIFE SCIENCE: AN ENVIRONMENTAL APPROACH (Energy needs: Fuel)
Kara Steeland Adena Kass William Finnicum Global Change 1-Section 5.
Group 27!(:. The way naturalight works Fossil fuels  Fossil fuels are fuels formed by natural processes such as anaerobic decomposition of buried dead.
Tutorial 3: Weather boundary conditions Q1. List the weather parameters that influence a building's energy consumption and environmental conditions. 1.
DATA MINING : CLASSIFICATION. Classification : Definition  Classification is a supervised learning.  Uses training sets which has correct answers (class.
U NIVERSITY OF M ASSACHUSETTS A MHERST Department of Computer Science 2011 Predicting Solar Generation from Weather Forecasts Using Machine Learning Navin.
Reducing gas emissions By: Justin, Ryan, Chris and Declan.
ERB’S PERSPECTIVE TO THE FUTURISTIC BUILT ENVIRONMENT AS PERTAINS TO ENERGY CONSERVATION & EFFICIENCY BUTLER SITALI EXECUTIVE DIRECTOR ENERGY REGULATION.
Did the recession impact recent decreases in observed sulfate concentrations? Shao-Hang Chu, US EPA/OAQPS/AQAD October, 2011.
Link Building PV project By: Culver Matt Labaume Natasha Narnio Guillaume Roux Arnaud Stanton Andrew Thompson Matt Troyano Joana ENS Renewable.
Energy & Power Unit 5, Lesson 1 Explanation
Energy Exploration Climate Change: Connections and Solutions Lesson 5.
Treatment Learning: Implementation and Application Ying Hu Electrical & Computer Engineering University of British Columbia.
Energy Literacy. Energy sources fall into two categories RenewableNon-Renewable.
CSC 196k Semester Project: Instance Based Learning
CS 782 – Machine Learning Lecture 4 Linear Models for Classification  Probabilistic generative models  Probabilistic discriminative models.
VUJE, a. s., Okružná 5, Trnava Strengthening the European Union Energy Security Prepared by Peter Líška (Slovak proposal) Brussels, 14th September.
Exploiting Context Analysis for Combining Multiple Entity Resolution Systems -Ramu Bandaru Zhaoqi Chen Dmitri V.kalashnikov Sharad Mehrotra.
STRATEGIC ENVIRONMENTAL ASSESSMENT METHODOLOGY AND TECHNIQUES.
April 19, 2004 International Energy Outlook 2004 Guy Caruso Administrator Energy Information Administration Thirty-First Annual International Energy Conference.
Exploit of Online Social Networks with Community-Based Graph Semi-Supervised Learning Mingzhen Mo and Irwin King Department of Computer Science and Engineering.
Patch Based Prediction Techniques University of Houston By: Paul AMALAMAN From: UH-DMML Lab Director: Dr. Eick.
Energy The ability to do work or cause change Examples – kinetic or potential Non-example – matter, ideas Related Words – forms, sources, transfer, transformation.
Demand Side Management in Smart Grid Using Heuristic Optimization (IEEE TRANSACTIONS ON SMART GRID, VOL. 3, NO. 3, SEPTEMBER 2012) Author : Thillainathan.
Introduction: Energy Unit Technology Foundations.
Hybrid Load Forecasting Method With Analysis of Temperature Sensitivities Authors: Kyung-Bin Song, Seong-Kwan Ha, Jung-Wook Park, Dong-Jin Kweon, Kyu-Ho.
Random Forests Ujjwol Subedi. Introduction What is Random Tree? ◦ Is a tree constructed randomly from a set of possible trees having K random features.
LEFT CLICK OR PRESS SPACE BAR TO ADVANCE, PRESS P BUTTON TO GO BACK, PRESS ESC BUTTON TO END LEFT CLICK OR PRESS SPACE BAR TO ADVANCE, PRESS P BUTTON.
Advanced Environmental Technology Geographic Distributions of Natural Resources TEK 7D.
Predicting the Location and Time of Mobile Phone Users by Using Sequential Pattern Mining Techniques Mert Özer, Ilkcan Keles, Ismail Hakki Toroslu, Pinar.
Name Of The College & Dept
Learning Photographic Global Tonal Adjustment with a Database of Input / Output Image Pairs.
Identifying “Best Bet” Web Search Results by Mining Past User Behavior Author: Eugene Agichtein, Zijian Zheng (Microsoft Research) Source: KDD2006 Reporter:
Combining multiple learners Usman Roshan. Decision tree From Alpaydin, 2010.
CIS 335 CIS 335 Data Mining Classification Part I.
An Effective Hybridized Classifier for Breast Cancer Diagnosis DISHANT MITTAL, DEV GAURAV & SANJIBAN SEKHAR ROY VIT University, India.
Stock market forecasting using LASSO Linear Regression model
Operation and Control Strategy of PV/WTG/EU Hybrid Electric Power System Using Neural Networks Faculty of Engineering, Elminia University, Elminia, Egypt.
Worcester Polytechnic Institute CS548 Spring 2016 Decision Trees Showcase By Yi Jiang and Brandon Boos ---- Showcase work by Zhun Yu, Fariborz Haghighat,
IEEE CS 70 th Anniversary Student Challenge Project proposal entitled “Hybrid Power Generation System Using Wind Energy and Solar Energy” Submitted by:
© 2016 Global Market Insights, Inc. USA. All Rights Reserved Concentrated Solar Power Market share to hit 24 GW by 2025 : Fractovia.org.
Energy Consumption Forecast Using JMP® Pro 11 Time Series Analysis
Renewable or Nonrenewable?
k-Nearest neighbors and decision tree
Prepared by: Mahmoud Rafeek Al-Farra
DESIGN AND SIMULATION OF GRID CONNECTED
On Spatial Joins in MapReduce
Prepared by: Mahmoud Rafeek Al-Farra
iSRD Spam Review Detection with Imbalanced Data Distributions
Classification and Prediction
CS548 Fall 2018 Model and Regression Trees
CSCI N317 Computation for Scientific Applications Unit Weka
Nearest Neighbors CSC 576: Data Mining.
Presentation transcript:

A Decision Tree Classification Model For Determining The Location For Solar Power Plant A PRESENTATION BY-  DISHANT MITTAL  DEV GAURAV VIT UNIVERSITY,VELLORE

ABSTRACT  The identification of sites for establishing power plants operated by renewable sources of energy is a pressing need in the 21st century as non- renewable sources are no longer fit for our energy needs. This is especially important in a country like India, where supply to demand ratio is very low.  In this paper, a machine learning technique named Decision Tree (CART) is proposed as a novel method to predict whether the site is liable of establishing solar power plant.  The decision tree method is able to do feature selection implicitly and performs very well even when the dataset is huge.  Experiments were performed with the dataset gathered from the model proposed by Dev Gaurav et al. [2].

WHY DETERMINING LOCATION FOR SOLAR POWER PLANT IS CRUCIAL ?  No other energy source matches to the energy potential of sunshine. Coal, Uranium, Petroleum, and Natural Gas are TOTAL recoverable reserves, whereas the solar energy has a giant potential per year.  Non renewable energy, such as coal and petroleum, require costly explorations and potentially dangerous mining and drilling, and they will become more expensive as supplies shrink and demand surges.  Renewable energy yields only minute levels of carbon emissions and thus helps combat climate change triggered by fossil fuel usage.

RELATED WORKS  Zamo, M., Mestre, O., Arbogast, P., and Pannekoucke, O.: A benchmark of statistical regression methods for short-term forecasting of photovoltaic electricity production. Part II: Probabilistic forecast of daily production. In Solar Energy, vol. 105, pp (2014)  Gaurav, D., Mittal, D., Vaidya, B. and Mathew, J.: A GSM based low cost weather monitoring system for solar and wind energy generation. In Applications of Digital Information and Web Technologies (ICADIWT), IEEE, 2014 Fifth International Conference, pp (2014)  Jung, J., and Broadwater, R. P.: Current status and future advances for wind speed and power forecasting. In Renewable and Sustainable Energy Reviews, 31, pp (2014)

 Pedro, H. T., and Coimbra, C. F.: Assessment of forecasting techniques for solar power production with no exogenous inputs. in Solar Energy, vol. 86(7), pp (2012)  Diagne, M., David, M., Lauret, P., Boland, J., and Schmutz, N.: Review of solar irradiance forecasting methods and a proposition for small-scale insular grids. in Renewable and Sustainable Energy Reviews, vol. 27, pp (2013)  Sharma, N., Sharma, P., Irwin, D., and Shenoy, P.: Predicting solar generation from weather forecasts using machine learning. In Smart Grid Communications (SmartGridComm), 2011 IEEE International Conference on IEEE, pp , October. (2011) RELATED WORKS

Proposed Model-Decision Tree Model  Decision tree approach is a technique under supervised learning, the learning proceeds through a set of decision rules by using the attributes available in the dataset. A tree is constructed having the information related to decision rules.  For each data located at particular node, the algorithm splits it into feature and threshold value.  The function that minimizes the impurity function H() is given by

 The function that classify samples according to class labels is  This technique is simple and efficient, does not require data normalization and the cost is logarithmic in the number of samples used for training. It is able to do feature selection implicitly. Proposed Model-Decision Tree Model

Data Preparation  Research data utilized for classification was gathered from the model proposed by Dev Gaurav et al. [2].  The total number of instances for this experimentation was 8000 recorded rows over a period of eight months, from September 2012 to April  The features taken into consideration are comprised of daily weather conditions including  Light intensity  Temperature  Relative humidity

Data Preparation  The class label for each instance was either “1” signifying that the conditions are favorable in context of setting up power plant or “0” signifying that the weather conditions are not favorable to set up power plant.  A comparison study for analyzing the model which we have proposed, with the Nearest centroid model and stochastic gradient descent (SGD) was incorporated. Decision Tree does not entail any parameter values in opposition to stochastic gradient descent.

Evaluation Metrics  The performance of proposed and comparison models was measured by computing accuracy utilizing confusion matrix criteria.  Confusion Matrix Predicted Class Class=1Class=0 Actual Class Class=1F 11 F 10 Class=0F 01 F 00  The accuracy is then given by

Results  Nearest Centroid

Results  Stochastic Gradient descent

Results  Decision tree

Results MethodTraining Accuracy Testing Accuracy Stochastic Gradient descent Nearest Centroid Decision Tree

Conclusion  The results indicate that the proposed model outperforms Nearest Centroid and Stochastic Gradient Descent models.  This technique was a novel and peculiar approach towards the problem of determining the feasibility of a location for setting up solar power plant.  It encourages the use of renewable energy sources and ensure the utilization of non-renewable resources in a sustainable way.

SAVE THE NATURE AND NATURE WILL SAVE YOU THANK YOU