Payman Jula

Coordinated Multistage Scheduling of Parallel Batch-Processing Machines Under Multiresource Constraints

Motivated by scheduling challenges of burn-in ovens in back-end semiconductor manufacturing, we propose a linear-programming-based algorithm, an integer-programming-based algorithm, and a heuristic-based algorithm to schedule nonhomogenous parallel batch machines with nonidentical job sizes and incompatible job families. We consider the common scheduling of consecutive steps that are linked together through secondary scarce resources. Our approach addresses the availability and compatibility of several resources required to make each process possible. The algorithms strive to meet short-term production targets expressed by product and step. The algorithms are shown to be effective and computationally efficient for this purpose. Taken together with previously developed methodology for the practical translation of target output schedules into short-term local production targets, this article suggests how a complex supply chain manufacturing system can be efficiently and effectively managed by decentralized local scheduling algorithms striving to meet short-term production targets that in turn ensure maintenance of an appropriate dynamic profile across production steps for work-in-process.

Bi-criteria appointment scheduling of patients with heterogeneous service sequences

We address scheduling of different patient type with stochastic service times.Different heterogeneous service sequences in multi-stage facilities are considered.We minimize the waiting time of patients and the completion time of the facility.Mathematical programming, simulation, and multiobjective tabu search are used in this work.We provide a real industrial case-study and analyze the results. This article addresses the challenges of scheduling patients with stochastic service times and heterogeneous service sequences in multi-stage facilities, while considering the availability and compatibility of resources with presence of a variety of patient types. The proposed method departs from existing literature by optimizing the scheduling of patients by integrating mathematical programming, simulation, and multiobjective tabu search methods to achieve our bi-objectives of minimizing the waiting time of patients and the completion time of the facility. Through intensive testing, the performance of the proposed approach is analyzed in terms of the solution quality and computation time, and is compared with the performance of the well-known method, Non-Dominated Sorting Genetic Algorithm (NSGA-II). The proposed method is then applied to actual data of a case study operating department in a major Canadian hospital and promising results have been observed. Based on this study, insights are provided for practitioners.

Design of a reliable multi-modal multi-commodity model for hazardous materials transportation under uncertainty

In this paper, we propose a new mathematical model for designing a reliable hazardous material (HAZMAT) transportation network (RHTND) on the basis of hub location topology under uncertainties, in which hub nodes may be disrupted by external events, as well as HAZMATs incidents. Hub locations and HAZMAT transportation routes using different transportation modes are simultaneously optimized to obtain minimum risk of incidents. A mixed integer nonlinear programing model is developed. To cope with the uncertainties in the model, we provide a solution framework based on an integration of the well-known chance-constrained programing with a possibilistic programing approach. Small size problems are solved to optimality. In order to solve large size instances, a meta-heuristic algorithm was applied and its performance is evaluated in comparison with a new lower bound approach through analysis of a real case-study of a HAZMAT transportation network.

Coordinating decentralized local schedulers in complex supply chain manufacturing

Motivated by scheduling challenges in back-end semiconductor manufacturing, we propose a framework to oversee and integrate local decentralized scheduling algorithms utilized in complex supply chain manufacturing networks. We fill the gap between higher-level production planning and lower-level scheduling by establishing short-term production targets and priority scores for each product at each step in the system. Given a target output schedule, target cycle times for each step, the process and product structure, and initial WIP status, short-term production targets for each product/step are set. These targets can be used to evaluate the system performance and guide decentralized schedulers to control the system so as to achieve desirable outputs in dynamic environments.

Coordinated scheduling of a single machine with sequence-dependent setup times and time-window constraints

In this paper we consider the selection and scheduling of several jobs on a single machine with sequence-dependent setup times and strictly enforced time-window constraints on the start times of each job. We demonstrate how to develop network-based algorithms to sustain the desired work in process (WIP) profile in a manufacturing environment. Short-term production targets are used to coordinate decentralised local schedulers and to make the objectives of specific areas in line with the chain objectives. A wide range of test problems with two different network structures are simulated. The effectiveness, efficiency, and robustness of the proposed algorithms are analysed and compared with an exhaustive search approach.

Continuous-time algorithms for scheduling a single machine with sequence-dependent setup times and time window constraints in coordinated chains

In this paper we address the problem of selecting and scheduling several jobs on a single machine with sequence-dependent setup times and strictly enforced time window constraints on the start time of each job. We use short-term production targets to coordinate decentralised local schedulers and to make the objectives of specific areas in line with the chain objectives by maintaining a desired work in process profile in manufacturing environments. The existing literature in this domain is based on discrete-time approaches. We depart from prior approaches by considering continuous time. We introduce a two-step mathematical programming model based on disjunctive constraints to solve small problems to optimality, and propose an insertion-based heuristic to solve large-scale instances. We provide several variations of the insertion heuristic based on different score functions. The primary objective of these approaches is to maximise the total defined score for jobs while satisfying production targets for families of jobs in each shift. Further, our models minimise the maximum completion time of all selected jobs. The effectiveness, efficiency, and robustness of the proposed algorithms are analysed and compared with the existing literature.

Design of a pharmaceutical supply chain network under uncertainty considering perishability and substitutability of products

We propose a new analytical model for pharmaceutical supply chain network design.Considering products perishability, substitutability and quantity discount.Introducing a novel robust possibilistic optimization approach.Providing a case study to show the application of the model in industry. This paper proposes a mathematical model for the network design of a pharmaceutical supply chain. The two objective functions of the presented model seek to minimize the total cost and the maximum unmet demand. We depart from the existing literature by considering products shelf-life, substitutability and quantity discount, while addressing uncertainties in costs and demand. In doing so, a novel robust possibilistic optimization approach is introduced and its performance is analyzed. Finally, a case study is provided and its proposed optimal network is discussed.

Performance Bound on Ergodic Capacity of MIMO Beam-Forming in Indoor Multi-Path Channels

This paper aims to characterize the ergodic capacity of multiple input multiple output (MIMO) antenna beam-forming in indoor multi-path propagation environments. Using Double-Directional Cluster-Ray (DDCR) channel models, the second order statistics of the strongest eigen-mode of the channel is analyzed. An upper bound on the ergodic capacity of the MIMO beam-forming is derived and the impact of channel propagation parameters, such as cluster/ray arrival rates and power decay profiles, on this upper bound is investigated. The theoretical results are subsequently applied to estimate the capacity of the next generation very high throughput WLAN at the 60 GHz frequency band.

Statistical Characterization of Power Amplifier Nonlinearity at 60 GHz: MIMO Beam-forming Analysis

This paper presents an analytical framework to model and characterize the power amplifier nonlinearity at 60 GHz. Using extension of Bussgang theorem, we propose a closed form expression for the variance of power amplifier nonlinearity noise as a function of the power amplifier output backoff. The variance is subsequently used to estimate the capacity of MIMO beam-forming subject to the power amplifier nonlinearity at the transmitter.