Akshay Ajagekar

Akshay Ajagekar

Auto-generated profile, based on publicly available information

Akshay Ajagekar

Cornell University, Ithaca, NY, USA

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 December 2022 in IEEE Transactions on Sustainable Energy
Verified
Journal Article
Closed access
AAAkshay Ajagekar
Akshay Ajagekar
FYFengqi You
Fengqi You
The intermittent nature of renewable energy sources and fluctuating electricity demand induce significant uncertainty that needs to be tackled with computationally efficient solution techniques to provide reliable and cost-effective generation schedules of power systems. In this work, we present a deep reinforcement learning (DRL) based approach for the day-ahead scheduling of generation resources under demand and wind power uncertainties. The proposed approach yields a causal policy relying only on historical uncertainty realizations and forecast data that is trained with an actor-critic-based reinforcement learning algorithm. Through safe exploration, the DRL-based approach guarantees a feasible commitment schedule without any operational constraint violations. We conduct computational experiments on the IEEE 39-bus and 118-bus test cases to demonstrate the effectiveness of the proposed solution strategy and improvement over existing approaches, including a deterministic approach with point forecasts and the stochastic dual dynamic integer programming method. The results show that the proposed approach enjoys superior performance in terms of computational efficiency and incurred operational costs, with significant reduction in penalty costs caused by insufficient net load supply than the deterministic approach.

29 June 2022 in IEEE Transactions on Quantum Engineering
Verified
Journal Article
Open access
AAAkshay Ajagekar
Akshay Ajagekar
KHKumail Al Hamoud
Kumail Al Hamoud
FYFengqi You
Fengqi You
Quantum computing (QC) holds great promise to open up a new era of computing and has been receiving significant attention recently. To overcome the performance limitations of near-term QC, utilizing the current quantum computers to complement classical techniques for solving real-world problems is of utmost importance. In this article, we develop QC-based solution strategies that exploit quantum annealing and classical optimization techniques for solving large-scale scheduling problems in manufacturing systems. The applications of the proposed algorithms are illustrated through two case studies in production scheduling. First, we present a hybrid QC-based solution approach for the job-shop scheduling problem. Second, we propose a hybrid QC-based parametric method for the multipurpose batch scheduling problem with a fractional objective. The proposed hybrid algorithms can tackle optimization problems formulated as mixed-integer linear and mixed-integer fractional programs, respectively, and provide feasibility guarantees. Performance comparison between state-of-the-art exact and heuristic solvers and the proposed QC-based hybrid solution techniques is presented for both job-shop and batch scheduling problems. Unlike conventional classical solution techniques, the proposed hybrid frameworks harness quantum annealing to supplement established deterministic optimization algorithms and demonstrate performance efficiency over standard off-the-shelf optimization solvers.

7 March 2022 in AIChE Journal
Verified
Journal Article
Closed access
DNDavid Bernal Neira
David Bernal Neira
AAAkshay Ajagekar
Akshay Ajagekar
SHStuart M. Harwood
Stuart M. Harwood
SSSpencer T. Stober
Spencer T. Stober
DTDimitar Trenev
Dimitar Trenev
FYFengqi You
Fengqi You

20 December 2024 in Science Advances
Verified
Journal Article
Open access
RVRaul Conchello Vendrell
Raul Conchello Vendrell
AAAkshay Ajagekar
Akshay Ajagekar
MBMichael T. Bergman
Michael T. Bergman
CHCarol K. Hall
Carol K. Hall
FYFengqi You
Fengqi You
De novo peptide design exhibits great potential in materials engineering, particularly for the use of plastic-binding peptides to help remediate microplastic pollution. There are no known peptide binders for many plastics—a gap that can be filled with de novo design. Current computational methods for peptide design exhibit limitations in sampling and scaling that could be addressed with quantum computing. Hybrid quantum-classical methods can leverage complementary strengths of near-term quantum algorithms and classical techniques for complex tasks like peptide design. This work introduces a hybrid quantum-classical generative framework for designing plastic-binding peptides combining variational quantum circuits with a variational autoencoder network. We demonstrate the framework’s effectiveness in generating peptide candidates, evaluate its efficiency for property-oriented design, and validate the candidates with molecular dynamics simulations. This quantum computing–based approach could accelerate the development of biomolecular tools for environmental and biomedical applications while advancing the study of biomolecular systems through quantum technologies.

11 October 2020
Verified
Conference Paper
Closed access
AAAkshay Ajagekar
Akshay Ajagekar
FYFengqi You
Fengqi You
Quantum computing and deep learning methods hold great promise to open up a new era of computing and have been receiving significant attention recently. This paper presents quantum computing (QC) based deep learning methods for fault diagnosis that are capable of overcoming the computational challenges faced by conventional techniques performed on classical computers. The shortcomings of such classical data-driven techniques are addressed by the proposed QC-based fault diagnosis model. A quantum computing assisted generative training process followed by supervised discriminative training is used to train this model. The applicability of proposed model and methods is demonstrated by applying them to process monitoring of Tennessee Eastman (TE) process. The proposed QC-based deep learning approach enjoys superior performance with an average fault diagnosis rate of 80% and tremendously low false alarm rates for the TE process.