SBIR-STTR Award

Optimal production planning, sourcing, distribution and routing for complex energy intensive manufacturing companies using High Performance Computing
Award last edited on: 6/2/2022

Sponsored Program
SBIR
Awarding Agency
DOE
Total Award Amount
$1,150,000
Award Phase
2
Solicitation Topic Code
02 a
Principal Investigator
Vijaykumar Hanagandi

Company Information

Optimal Solutions Inc (AKA: OSI)

17 Kershaw Court
Bridgewater, NJ 08807
   (908) 393-1316
   info@osiopt.com
   www.osiopt.com
Location: Multiple
Congr. District: 07
County: Somerset

Phase I

Contract Number: ----------
Start Date: ----    Completed: ----
Phase I year
2013
Phase I Amount
$150,000
Energy costs are the main cost drivers for large industries like chemicals & gaseous products & they depend on massive economies of scale and an efficient supply chain to stay competitive. Todays approaches to supply chain optimization are based on static snap-shot data and are not suitable for real-time use in tactical demand fulfillment. Companies have yet to effectively harness the potential of powerful new computing technologies and algorithms to find solutions for energy and other costly inefficiencies persisting in the supply chain many of which must be solved in real-time. This project addresses DOEs interest in turn-key solutions advancing the use of HPC technology in manufacturing & is intended to result in increased supply chain efficiency, job creation, & reduced carbon emissions. We propose to develop a data-integration and supply chain optimization application that uses High Performance Computing technology to address the issue of real-time supply chain optimization for tactical use in demand fulfillment. In Phase I, we will demonstrate feasibility by developing a generic data integration and supply chain optimization framework and prove the concept on a test-bed. In Phase II, we will address the deeper technical and commercial aspects of handling data confidentiality and security and we will also harden the data-model and the solver code for success in the commercial environment. Our overall objective of the combined Phase I and Phase II projects is to bring to market a cutting-edge, HPC-based supply chain optimization application. Commercial Applications and Other

Benefits:
We are proposing a breakthrough approach compared to what is offered by existing Commercial Off-The-Shelf (COTS) solutions. The envisioned commercial supply chain optimization application will be used to support end-to-end decision-making from sourcing, production planning, and distribution routing for energy intensive manufacturing companies. In large energy intensive manufacturers, typically, more that 70% of costs of goods sold are directly related to energy costs and hence small percentages of costs saved results in huge dollar savings. Through previous studies and isolated implementations, it has been shown that the cost savings obtained from implementing the proposed supply chain optimization is in the range of 5% to 10%, which is a game-changer for large manufacturers. The confluence of Big Data, HPC, and Supply Chain Optimization is at the center of our innovative approach and our project will be the first one to do this. The proposed solution is also expected to result in reduced energy dependence, reduced emissions, and reduction in traffic congestion (via optimal routing of vehicles). It is intended to increase the global competitiveness of the manufacturing sector and lead to job creation in the US.

Phase II

Contract Number: ----------
Start Date: ----    Completed: ----
Phase II year
2014
Phase II Amount
$1,000,000
Todays approaches to production planning and inventory management in a distribution network for large industrial gases and chemicals manufacturers are based on static snap-shot data and are not suitable for real-time use in tactical demand fulfillment. Companies have yet to harness the potential of powerful new computing technologies to find solutions for energy and other costly inefficiencies persisting in their supply chains many of which must be solved in real-time. This project addresses DOEs interest in turnkey solutions advancing the use of HPC in manufacturing and is intended to result in increased supply chain efficiency, reduced costs, and job creation. The overall objective is to develop a next generation production planning and distribution optimization algorithm together with a data-integration platform to provide timely and accurate data required for the optimization model. We take a two-pronged approach to address the problem: (1) leverage HPC technology to parallelize and rapidly solve the production planning and distribution problem and (2) leverage Big Data technology on a HPC platform to address the required data-integration. Phase I R & amp;D resulted in (1) a comprehensive model formulation that provides vehicle routing, production optimization and inventory optimization simultaneously and (2) a Big Data analytics framework to support the generation of the required input data. We demonstrated that using HPC, we can achieve 1080- times faster performance (vs. non-HPC implementation) without loss of optimality, thus proving feasibility of our innovation. We used industrial data and benchmarking to prove optimality and scalability. Our results were reviewed by several prospective customers and we received encouraging feedback (see support letters). We plan to build on the formulations and the test-bed created in Phase I and improve our algorithms. Our research activities will also focus on overcoming challenges including scalability of the solution, data security, and total cost of ownership. Our target is to be ready by the end of Phase II with a prototype turnkey application running on a hosted-HPC infrastructure, which allows us to start commercialization of our product as a service over the Internet to a variety of customers. Commercial Applications and Other

Benefits:
The envisioned software system will be used to obtain optimal production planning and distribution at multi-product, multi-depot manufacturing companies which utilize many fleets of vehicles. It is expected to result in significant efficiencies and reductions in energy and other operating costs. It is intended to increase the global competitiveness of the U.S. manufacturing sector and result in job creation.