2015 IEEE Green Energy and Systems Conference (IGESC)最新文献

筛选

英文中文

Decision tree-based machine learning algorithm for in-node vehicle classification 基于决策树的节点内车辆分类机器学习算法

2015 IEEE Green Energy and Systems Conference (IGESC) Pub Date : 2015-11-09 DOI: 10.1109/IGESC.2015.7359454

Kyle Ying, Alireza Ameri, Ankit Trivedi, D. Ravindra, Darshana Patel, M. Mozumdar

{"title":"Decision tree-based machine learning algorithm for in-node vehicle classification","authors":"Kyle Ying, Alireza Ameri, Ankit Trivedi, D. Ravindra, Darshana Patel, M. Mozumdar","doi":"10.1109/IGESC.2015.7359454","DOIUrl":"https://doi.org/10.1109/IGESC.2015.7359454","url":null,"abstract":"In this paper, we propose an in-node microprocessor-based vehicle classification approach to analyze and determine the types of vehicles passing over a 3-axis magnetometer sensor. Our approach for vehicle classification utilizes J48 classification algorithm implemented in Weka (a machine learning software suite). J48 is a Quinlan's C4.5 algorithm, an extension of decision tree machine learning based on ID3 algorithm. The decision tree model is generated from a set of features extracted from vehicles passing over the 3-axis sensor. The features are attributes provided with correct classifications to the J48 training algorithm to generate a decision tree model with varying degrees of classification rates based on crossvalidation. Ideally, using fewer attributes to generate the model allows for the highest computational efficiency due to fewer features needed to be calculated while minimalizing the tree with fewer branches. The generated tree model can then be easily implemented using nested if-loops in any language on a multitude of microprocessors. In addition, setting an adaptive baseline to negate the effects of the background magnetic field allows reuse of the same tree model in multiple environments. The result of our experiment shows that the vehicle classification system is effective and efficient with the accuracy at nearly 100%.","PeriodicalId":193746,"journal":{"name":"2015 IEEE Green Energy and Systems Conference (IGESC)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125432382","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 13

Performance analysis of energy storage systems connected to a doubly fed induction generator 连接双馈感应发电机的储能系统性能分析

2015 IEEE Green Energy and Systems Conference (IGESC) Pub Date : 2015-11-09 DOI: 10.1109/IGESC.2015.7359387

Youngil Kim, Junda Zhao, R. Harrington

{"title":"Performance analysis of energy storage systems connected to a doubly fed induction generator","authors":"Youngil Kim, Junda Zhao, R. Harrington","doi":"10.1109/IGESC.2015.7359387","DOIUrl":"https://doi.org/10.1109/IGESC.2015.7359387","url":null,"abstract":"Wind Energy is a viable source of renewable energy to solve global problems. However, the disadvantage is that wind power is variable, depending critically on wind speed. The simula- tion tool Power System Computer Aided Design/Electromagnetic Transients Direct Current (PSCAD/EMTDC) is used to simulate the model of the Doubly Fed Induction Generator (DFIG) connected to the Energy Storage Systems (ESS). In terms of technical analysis, DFIG which was equipped with the ESS can partly compensate the unstable active power output from the variable wind output power. In addition, this paper analyzed about the performance of Total Harmonic Distortion (THD) for different ESS options such as Super Capacitor ESS (SCESS), Battery ESS (BESS), Two Layer (TL) ESS in the DFIG as 1.5MW ,60Hz under mean wind speed 12 m/s during the 12 second. From the simulation results, The average THD of Hybrid ESS as SC-B ESS, SC- TLESS is the best options to reduce the THD for power quality improvement compared to other ESS options. In terms of economical analysis, the payback time of Battery ESS and Super Capacitor ESS are 3.47 years and 15.76 years respectively. The pay back time of Hybrid ESS is between these two payback time, therefore the system can still be affordable. This paper will provide a better understanding of the performance of different ESS systems, and will be a help for practical applications of ESS in future wind energy projects.","PeriodicalId":193746,"journal":{"name":"2015 IEEE Green Energy and Systems Conference (IGESC)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134473455","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

A multi-objective optimization approach for efficient energy management in smart grids 智能电网高效能源管理的多目标优化方法

2015 IEEE Green Energy and Systems Conference (IGESC) Pub Date : 2015-11-09 DOI: 10.1109/IGESC.2015.7359383

R. Rajagopalan

{"title":"A multi-objective optimization approach for efficient energy management in smart grids","authors":"R. Rajagopalan","doi":"10.1109/IGESC.2015.7359383","DOIUrl":"https://doi.org/10.1109/IGESC.2015.7359383","url":null,"abstract":"Smart grid uses bi directional flow of information to create a distributed and efficient energy delivery network. Some of the important objectives of a smart grid include improving energy efficiency, maximizing utility, reducing cost, and controlling emission. Smart grids use demand response as an effective strategy to address this challenge. Demand response uses real time scheduling to enable customers to modify their demand according to energy consumption costs. In this paper, we consider the problem of efficient scheduling of energy consumption of users in a smart grid. Efficient energy management involves tradeoffs between the cost associated with energy consumption and a utility function. The utility function can represent the living comfort of users or gross income of the utility company. The utility function is non decreasing with respect to total utilized power. Hence, it is important to understand the tradeoffs between energy consumption and utility. The main contribution of this work is the development of a multi-objective optimization framework for efficient energy scheduling in smart grids. A recently developed multi-objective evolutionary algorithm called the evolutionary multi-objective crowding algorithm (EMOCA) is adapted for simultaneously optimizing the energy cost and utility function subject to a constraint on the power generation capacity. Simulation results show that EMOCA demonstrates the advantages of multi-objective optimization and outperforms a widely used and well known multi-objective evolutionary algorithm.","PeriodicalId":193746,"journal":{"name":"2015 IEEE Green Energy and Systems Conference (IGESC)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116849585","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

首页上一页