@article{DESHPANDE2024101444,title={Third-party software library migration at the method-level using multi-objective evolutionary search},journal={Swarm and Evolutionary Computation},volume={84},pages={101444},year={2024},issn={2210-6502},doi={https://doi.org/10.1016/j.swevo.2023.101444},url={https://www.sciencedirect.com/science/article/pii/S221065022300216X},author={Deshpande, Niranjana and Mkaouer, Mohamed Wiem and Ouni, Ali and Sharma, Naveen},}
2022
EvoApps
Search-based third-party library migration at the method-level
Niranjana Deshpande , Mohamed Wiem Mkaouer , Ali Ouni , and 1 more author
In International Conference on the Applications of Evolutionary Computation (Part of EvoStar) , 2022
@inproceedings{deshpande2022search,title={Search-based third-party library migration at the method-level},author={Deshpande, Niranjana and Mkaouer, Mohamed Wiem and Ouni, Ali and Sharma, Naveen},booktitle={International Conference on the Applications of Evolutionary Computation (Part of EvoStar)},pages={173--190},year={2022},doi={https://doi.org/10.1007/978-3-031-02462-7_12},}
GECCO
Addressing tactic volatility in self-adaptive systems using evolved recurrent neural networks and uncertainty reduction tactics
Aizaz Ul Haq , Niranjana Deshpande , AbdElRahman ElSaid , and 2 more authors
In Proceedings of the Genetic and Evolutionary Computation Conference , 2022
Self-adaptive systems frequently use tactics to perform adaptations. Tactic examples include the implementation of additional security measures when an intrusion is detected, or activating a cooling mechanism when temperature thresholds are surpassed. Tactic volatility occurs in real-world systems and is defined as variable behavior in the attributes of a tactic, such as its latency or cost. A system’s inability to effectively account for tactic volatility adversely impacts its efficiency and resiliency against the dynamics of real-world environments. To enable systems’ efficiency against tactic volatility, we propose a Tactic Volatility Aware (TVA-E) process utilizing evolved Recurrent Neural Networks (eRNN) to provide accurate tactic predictions. TVA-E is also the first known process to take advantage of uncertainty reduction tactics to provide additional information to the decision-making process and reduce uncertainty. TVA-E easily integrates into popular adaptation processes enabling it to immediately benefit a large number of existing self-adaptive systems. Simulations using 52,106 tactic records demonstrate that: I) eRNN is an effective prediction mechanism, II) TVA-E represents an improvement over existing state-of-the-art processes in accounting for tactic volatility, and III) Uncertainty reduction tactics are beneficial in accounting for tactic volatility. The developed dataset and tool can be found at https://tacticvolatility.github.io/
@inproceedings{10.1145/3512290.3528745,author={Haq, Aizaz Ul and Deshpande, Niranjana and ElSaid, AbdElRahman and Desell, Travis and Krutz, Daniel E.},title={Addressing tactic volatility in self-adaptive systems using evolved recurrent neural networks and uncertainty reduction tactics},year={2022},isbn={9781450392372},publisher={Association for Computing Machinery},address={New York, NY, USA},url={https://doi.org/10.1145/3512290.3528745},doi={10.1145/3512290.3528745},booktitle={Proceedings of the Genetic and Evolutionary Computation Conference},pages={1299–1307},numpages={9},keywords={adaptive systems, deep learning, recurrent neural networks, uncertainty},location={Boston, Massachusetts},series={GECCO '22},}
ICWS
Online Learning Using Incomplete Execution Data for Self-Adaptive Service-Oriented Systems
Niranjana Deshpande , Naveen Sharma , Qi Yu , and 1 more author
In 2022 IEEE International Conference on Web Services (ICWS) , 2022
@inproceedings{9885741,author={Deshpande, Niranjana and Sharma, Naveen and Yu, Qi and Krutz, Daniel E.},booktitle={2022 IEEE International Conference on Web Services (ICWS)},title={Online Learning Using Incomplete Execution Data for Self-Adaptive Service-Oriented Systems},year={2022},volume={},number={},pages={296-301},doi={10.1109/ICWS55610.2022.00051},}
2021
GECCO LBA
Algorithm selection using transfer learning
Niranjana Deshpande , and Naveen Sharma
In Proceedings of the Genetic and Evolutionary Computation Conference Companion , 2021
@inproceedings{10.1145/3449726.3462736,author={Deshpande, Niranjana and Sharma, Naveen},title={Algorithm selection using transfer learning},year={2021},isbn={9781450383516},publisher={Association for Computing Machinery},address={New York, NY, USA},url={https://doi.org/10.1145/3449726.3462736},doi={10.1145/3449726.3462736},booktitle={Proceedings of the Genetic and Evolutionary Computation Conference Companion},pages={51–52},numpages={2},keywords={algorithm selection, service composition, transfer learning, travelling salesman problem},location={Lille, France},series={GECCO '21},}
ICWS
R-CASS: Using algorithm selection for self-adaptive service-oriented systems
Niranjana Deshpande , Naveen Sharma , Qi Yu , and 1 more author
In 2021 IEEE International Conference on Web Services (ICWS) , 2021
@inproceedings{deshpande2021r,title={R-CASS: Using algorithm selection for self-adaptive service-oriented systems},author={Deshpande, Niranjana and Sharma, Naveen and Yu, Qi and Krutz, Daniel E},booktitle={2021 IEEE International Conference on Web Services (ICWS)},pages={61--72},year={2021},organization={IEEE},doi={10.1109/ICWS53863.2021.00021},}
2020
ECSA CASA
Composition algorithm adaptation in service-oriented systems
Niranjana Deshpande , and Naveen Sharma
In European Conference on Software Architecture , 2020
@inproceedings{deshpande2020composition,title={Composition algorithm adaptation in service-oriented systems},author={Deshpande, Niranjana and Sharma, Naveen},booktitle={European Conference on Software Architecture},pages={170--179},year={2020},organization={Springer},doi={https://doi.org/10.1007/978-3-030-59155-7_13},}