An official website of the United States government
Abstract In this work, we proposed a two‐stage stochastic programming model for a four‐echelon supply chain problem considering possible disruptions at the nodes (supplier and facilities) as well as the connecting transportation modes and operational uncertainties in form of uncertain demands. The first stage decisions are supplier choice, capacity levels for manufacturing sites and warehouses, inventory levels, transportation modes selection, and shipment decisions for the certain periods, and the second stage anticipates the cost of meeting future demands subject to the first stage decision. Comparing the solution obtained for the two‐stage stochastic model with a multi‐period deterministic model shows that the stochastic model makes a better first stage decision to hedge against the future demand. This study demonstrates the managerial viability of the proposed model in decision making for supply chain network in which both disruption and operational uncertainties are accounted for.
more »
« less
Computational graph-based mathematical programming reformulation for integrated demand and supply models
As transportation systems grow in complexity, analysts need sophisticated tools to understand travelers’ decision-making and effectively quantify the benefits of the proposed strategies. The transportation community has developed integrated demand–supply models to capture the emerging interactive nature of transportation systems, serve diverse planning needs, and encompass broader solution possibilities. Recently, utilizing advances in Machine Learning (ML) techniques, researchers have also recognized the need for different computational models capable of fusing/analyzing different data sources. Inspired by this momentum, this study proposes a new modeling framework to analytically bridge travel demand components and network assignment models with machine learning algorithms. Specifically, to establish a consistent representation of such aspects between separate system models, we introduce several important mathematical programming reformulation techniques—variable splitting and augmented Lagrangian relaxation—to construct a computationally tractable nonlinear unconstrained optimization program. Furthermore, to find equilibrium states, we apply automatic differentiation (AD) to compute the gradients of decision variables in a layered structure with the proposed model represented based on computational graphs (CGs) and solve the proposed formulation through the alternating direction method of multipliers (ADMM) as a dual decomposition method. Thus, this reformulated model offers a theoretically consistent framework to express the gap between the demand and supply components and lays the computational foundation for utilizing a new generation of numerically reliable optimization solvers. Using a small example network and the Chicago sketch transportation network, we examined the convergency/consistency measures of this new differentiable programming-based optimization structure and demonstrated the computational efficiency of the proposed integrated transportation demand and supply models.
more »
« less
- Award ID(s):
- 1828010
- PAR ID:
- 10514490
- Publisher / Repository:
- Pergamon
- Date Published:
- Journal Name:
- Transportation Research Part C: Emerging Technologies
- Volume:
- 164
- Issue:
- C
- ISSN:
- 0968-090X
- Page Range / eLocation ID:
- 104671
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Optimal power management of battery energy storage systems (BESS) is crucial for their safe and efficient operation. Numerical optimization techniques are frequently utilized to solve the optimal power management problems. However, these techniques often fall short of delivering real-time solutions for large-scale BESS due to their computational complexity. To address this issue, this paper proposes a computationally efficient approach. We introduce a new set of decision variables called power-sharing ratios corresponding to each cell, indicating their allocated power share from the output power demand. We then formulate an optimal power management problem to minimize the system-wide power losses while ensuring compliance with safety, balancing, and power supply-demand match constraints. To efficiently solve this problem, a parameterized control policy is designed and leveraged to transform the optimal power management problem into a parameter estimation problem. We then implement the ensemble Kalman inversion to estimate the optimal parameter set. The proposed approach significantly reduces computational requirements due to 1) the much lower dimensionality of the decision parameters and 2) the estimation treatment of the optimal power management problem. Finally, we conduct extensive simulations to validate the effectiveness of the proposed approach. The results show promise in accuracy and computation time compared with explored numerical optimization techniques.more » « less
-
Computational advances along with the profound impact of uncertainty on power system investments have motivated the creation of power system planning frameworks that handle long-run uncertainty, large number of alternative plans, and multiple objectives. Planning agencies seek guidance to assess such frameworks. This article addresses this need in two ways. First, we augment previously proposed criteria for assessing planning frameworks by including new criteria such as stakeholder acceptance to make the assessments more comprehensive, while enhancing the practical applicability of assessment criteria by offering criterion-specific themes and questions. Second, using the proposed criteria, we compare two widely used but fundamentally distinct frameworks: an ‘agree-on-plans’ framework, Robust Decision Making (RDM), and an ‘agree-on-assumptions’ framework, centered around Stochastic Programming (SP). By comparing for the first time head-to-head the two distinct frameworks for an electricity supply planning problem under uncertainties in Bangladesh, we conclude that RDM relies on a large number of simulations to provide ample information to decision makers and stakeholders, and to facilitate updating of subjective inputs. In contrast, SP is a highly dimensional optimization problem that identifies plans with relatively good probability-weighted performance in a single step, but even with computational advances remains subject to the curse of dimensionality.more » « less
-
Idle vehicle relocation is crucial for addressing demand-supply imbalance that frequently arises in the ride-hailing system. Current mainstream methodologies - optimization and reinforcement learning - suffer from obvious computational drawbacks. Optimization models need to be solved in real-time and often trade off model fidelity (hence quality of solutions) for computational efficiency. Reinforcement learning is expensive to train and often struggles to achieve coordination among a large fleet. This paper designs a hybrid approach that leverages the strengths of the two while overcoming their drawbacks. Specifically, it trains an optimization proxy, i.e., a machine-learning model that approximates an optimization model, and then refines the proxy with reinforcement learning. This Reinforcement Learning from Optimization Proxy (RLOP) approach is computationally efficient to train and deploy, and achieves better results than RL or optimization alone. Numerical experiments on the New York City dataset show that the RLOP approach reduces both the relocation costs and computation time significantly compared to the optimization model, while pure reinforcement learning fails to converge due to computational complexity.more » « less
-
Space mission planning and spacecraft design are tightly coupled and need to be considered together for optimal performance; however, this integrated optimization problem results in a large-scale Mixed-Integer Nonlinear Programming (MINLP) problem, which is challenging to solve. In response to this challenge, this paper proposes a new solution approach to this MINLP problem by iterative solving a set of coupled subproblems via the augmented Lagrangian coordination approach following the philosophy of Multi-disciplinary Design Optimization (MDO). The proposed approach leverages the unique structure of the problem that enables its decomposition into a set of coupled subproblems of different types: a Mixed-Integer Quadratic Programming (MIQP) subproblem for mission planning and one or more Nonlinear Programming (NLP) subproblem(s) for spacecraft design. Since specialized MIQP or NLP solvers can be applied to each subproblem, the proposed approach can efficiently solve the otherwise intractable integrated MINLP problem. An automatic and effective method to find an initial solution for this iterative approach is also proposed so that the optimization can be performed without the need for a user-defined initial guess. In the demonstration case study, a human lunar exploration mission sequence is optimized with a subsystem-level parametric spacecraft design model. Compared to the state-of-the-art method, the proposed formulation can obtain a better solution with a shorter computational time even without parallelization. For larger problems, the proposed solution approach can also be easily parallelizable and thus is expected to be further advantageous and scalable.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1016/j.trc.2024.104671
