Purpose-The purpose of this paper is to describe a real-world system developed for a large food distribution company which requires forecasting demand for thousands of products across multiple warehouses. The number of different time series that the system must model and predict is on the order of 10 5. The study details the system's forecasting algorithm which efficiently handles several difficult requirements including the prediction of multiple time series, the need for a continuously self-updating model, and the desire to automatically identify and analyze various time series characteristics such as seasonal spikes and unprecedented events. Design/methodology/approach-The forecasting algorithm makes use of a hybrid model consisting of both statistical and heuristic techniques to fulfill these requirements and to satisfy a variety of business constraints/rules related to over-and under-stocking. Findings-The robustness of the system has been proven by its heavy and sustained use since being adopted in November 2009 by a company that serves 91 percent of the combined populations of Australia and New Zealand. Originality/value-This paper provides a case study of a real-world system that employs a novel hybrid model to forecast multiple time series in a non-static environment. The value of the model lies in its ability to accurately capture and forecast a very large and constantly changing portfolio of time series efficiently and without human intervention.
Purpose
– The purpose of this paper is to explore a real world vehicle routing problem (VRP) that has multi-depot subcontractors with a heterogeneous fleet of vehicles that are available to pickup/deliver jobs with varying time windows and locations. Both the overall job completion time and number of drivers utilized are analyzed for the automated job allocations and manual job assignments from transportation field experts.
Design/methodology/approach
– A nested genetic algorithm (GA) is used to automate the job allocation process and minimize the overall time to deliver all jobs, while utilizing the fewest number of drivers – as a secondary objective.
Findings
– Three different real world data sets were used to compare the results of the GA vs transportation field experts’ manual assignments. The job assignments from the GA improved the overall job completion time in 100 percent (30/30) of the cases and maintained the same or fewer drivers as BS Logistics (BSL) in 47 percent (14/30) of the cases.
Originality/value
– This paper provides a novel approach to solving a real world VRP that has multiple variants. While there have been numerous models to capture a select number of these variants, the value of this nested GA lies in its ability to incorporate multiple depots, a heterogeneous fleet of vehicles as well as varying pickup times, pickup locations, delivery times and delivery locations for each job into a single model. Existing research does not provide models to collectively address all of these variants.
Modern missions of government and private organizations rely on computer networks to operate. As evidenced by several well-publicized cyber breaches, these missions are under attack. Several cyber defensive measures have been proposed to mitigate this threat, some are meant to protect individual hosts on the network, and others are designed to protect the network at large. From a qualitative perspective, these mitigations seem to improve security, but there is no quantitative assessment of their effectiveness with respect to a complete network system and a cyber-supported mission for which the network exists. The purpose of this paper is to examine network-level cyber defensive mitigations and quantify their impact on network security and mission performance. Testing such mitigations in an live network environment is generally not possible due to the expense, and thus a modeling and simulation approach is utilized. Our approach employs a modularized hierarchical simulation framework to model a complete cyber system and its relevant dynamics at multiple scales. We conduct experiments that test the effectiveness of network-level mitigations from the perspectives of security and mission performance. Additionally, we introduce a novel, unified metric for mitigation effectiveness that takes into account both of these perspectives and provides a single measurement that is convenient and easily accessible to security practitioners.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.