Cerberus

The bandwidth and latency requirements of modern datacenter applications have led researchers to propose various topology designs using static, dynamic demand-oblivious (rotor), and/or dynamic demand-aware switches. However, given the diverse nature of datacenter traffic, there is little consensus about how these designs would fare against each other. In this work, we analyze the throughput of existing topology designs under different traffic patterns and study their unique advantages and potential costs in terms of bandwidth and latency ''tax''. To overcome the identified inefficiencies, we propose Cerberus, a unified, two-layer leaf-spine optical datacenter design with three topology types. Cerberus systematically matches different traffic patterns with their most suitable topology type: e.g., latency-sensitive flows are transmitted via a static topology, all-to-all traffic via a rotor topology, and elephant flows via a demand-aware topology. We show analytically and in simulations that Cerberus can improve throughput significantly compared to alternative approaches and operate datacenters at higher loads while being throughput-proportional.

Taxi Utilization Rate Maximization by Dynamic Demand Prediction: A Case Study in the City of Chicago

The explosive popularity of transportation network companies (TNCs) in the last decade has imposed dramatic disruptions on the taxi industry, but not all the impacts are beneficial. For instance, studies have shown taxi capacity utilization rate is lower than 50% in five major U.S. cities. With the availability of taxi data, this study finds the taxi utilization rate is around 40% in June 2019 (normal scenario) and 35% in June 2020 (COVID 19 scenario) in the city of Chicago, U.S. Powered by recent advances in the deep learning of capturing non-linear relationships and the availability of datasets, a real-time taxi trip optimization strategy with dynamic demand prediction was designed using long short-term memory (LSTM) architecture to maximize the taxi utilization rate. The algorithms are tested in both scenarios—normal time and COVID 19 time—and promising results have been shown by implementing the strategy, with around 19% improvement in mileage utilization rate in June 2019 and 74% in June 2020 compared with the baseline without any optimizations. Additionally, this study investigated the impacts of COVID 19 on the taxi service in Chicago.

A differential game analysis on green technology innovation in a supply chain with information sharing of dynamic demand

PurposeThe objective of this paper is to investigate the impact of the information sharing of the dynamic demand on green technology innovation and profits in supply chain from a long-term perspective.Design/methodology/approachThe authors consider a supply chain consisting of a manufacturer and a retailer. The retailer has access to the information of dynamic demand of the green product, whereas the manufacturer invests in green technology innovation. Differential game theory is adopted to establish three models under three different scenarios, namely (1) decentralized decision without information sharing of dynamic demand (Model N-D), (2) decentralized decision with information sharing of dynamic demand (Model S-D) and (3) centralized decision with information sharing of dynamic demand (Model S-C).FindingsThe optimal equilibrium results show that information sharing of dynamic demand can improve the green technology innovation level and increase the green technology stocks only in centralized supply chain. In the long term, the information sharing of dynamic demand can make the retailer more profitable. If the influence of green technology innovation on green technology stocks is great enough or the cost coefficient of green technology innovation is small enough, the manufacturer and decentralized supply chain can benefit from information sharing. In centralized supply chain, the value of demand information sharing is greater than that of decentralized supply chain.Originality/valueThe authors used game theory to investigate demand information sharing and the green technology innovation in a supply chain. Specially, the demand information is dynamic, which is a variable that changes over time. Moreover, our research is based on a long-term perspective. Thus, differential game is adopted in this paper.

Dynamic Demand and Pricing Inventory Model for Non-Instantaneous Deteriorating Items

In this model, an inventory model for deteriorating products with dynamic demand is developed under time-dependent selling price. The selling price is supposed to be a time-dependent function of initial price of the products and the permissible discount rate at the time of deterioration. The object is sold with the constant rate in the absence of deterioration and is the exponential function of discount rate at the time; deterioration takes place. Here, the demand not only dependent on the selling price but also on the cumulative demand that represents the saturation and diffusion effect. First, an inventory model is formulated to characterize the profit function. The Classical optimization algorithm is used to solve the optimization problem. The objective is to maximize the total profit of the retailers with respect to the initial selling price and cycle time. Concavity of the objective function is discussed through graphs. At last, a sensitivity analysis is performed by changing inventory parameters and their impact on the decision variables i.e. (initial price, cycle time) together with the profit function.