TY - GEN
T1 - Scaling up analogy-based software effort estimation
T2 - International Workshop on Innovative Software Development Methodologies and Practices, InnoSWDev 2014
AU - Phannachitta, Passakorn
AU - Keung, Jacky
AU - Monden, Akito
AU - Matsumoto, Kenichi
N1 - Publisher Copyright:
Copyright © 2014 ACM.
PY - 2014/11/16
Y1 - 2014/11/16
N2 - Analogy-based estimation (ABE) is one of the most time consuming and compute intensive method in software de- velopment effort estimation. Optimizing ABE has been a dilemma because simplifying the procedure can reduce the estimation performance, while increasing the procedure com- plexity with more sophisticated theory may sacrifice an ad- vantage of the unlimited scalability for a large data input. Motivated by an emergence of cloud computing technology in software applications, in this study we present 3 different implementation schemes based on Hadoop MapReduce to optimize the ABE process across multiple computing in- stances in the cloud-computing environment. We experimentally compared the 3 MapReduce implementation schemes in contrast with our previously proposed GPGPU approach (named ABE-CUDA) over 8 high-performance Amazon EC2 instances. Results present that the Hadoop solution can pro- vide more computational resources that can extend the scalability of the ABE process. We recommend adoption of 2 different Hadoop implementations (Hadoop streaming and RHadoop) for accelerating the computation specifically for compute-intensive software engineering related tasks.
AB - Analogy-based estimation (ABE) is one of the most time consuming and compute intensive method in software de- velopment effort estimation. Optimizing ABE has been a dilemma because simplifying the procedure can reduce the estimation performance, while increasing the procedure com- plexity with more sophisticated theory may sacrifice an ad- vantage of the unlimited scalability for a large data input. Motivated by an emergence of cloud computing technology in software applications, in this study we present 3 different implementation schemes based on Hadoop MapReduce to optimize the ABE process across multiple computing in- stances in the cloud-computing environment. We experimentally compared the 3 MapReduce implementation schemes in contrast with our previously proposed GPGPU approach (named ABE-CUDA) over 8 high-performance Amazon EC2 instances. Results present that the Hadoop solution can pro- vide more computational resources that can extend the scalability of the ABE process. We recommend adoption of 2 different Hadoop implementations (Hadoop streaming and RHadoop) for accelerating the computation specifically for compute-intensive software engineering related tasks.
KW - Analogy-based estimation
KW - CUDA
KW - Cloud computing
KW - Map reduce
KW - Software effort estimation
UR - http://www.scopus.com/inward/record.url?scp=84942782262&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84942782262&partnerID=8YFLogxK
U2 - 10.1145/2666581.2666582
DO - 10.1145/2666581.2666582
M3 - Conference contribution
AN - SCOPUS:84942782262
T3 - International Workshop on Innovative Software Development Methodologies and Practices, InnoSWDev 2014 - Proceedings
SP - 65
EP - 72
BT - International Workshop on Innovative Software Development Methodologies and Practices, InnoSWDev 2014 - Proceedings
PB - Association for Computing Machinery
Y2 - 16 November 2014
ER -