Adaptive Resource Control Research Articles

Complex interplay of R&D, advertising and exports in USA manufacturing firms: differential effects of capabilities

PurposeThis study aims to explore the dynamic interplay of key resources (i.e. research and development (R&D), advertising and exports) in affecting the performance of USA manufacturing firms. Specifically, the authors examine the dynamic impact of joint resources and predict differential effect scales contingent on firm capabilities.Design/methodology/approachThis study presents a combined multiple regression analysis (MRA)-multilayer perceptron (MLP) neural network modeling and investigates the complex interlinkage of capabilities, resources and performance. As an innovative approach, the MRA-MLP model investigates the effect of capabilities under the combinatory deployment of joint resources.FindingsThis study finds that the impact of joint resources and synergistic rents is not uniform but rather distinctive according to the combinatory conditions and that the pattern is further shaped by firm capabilities. Accordingly, besides signifying the contingent aspect of capabilities across a range of resource combinations, the result also shows that managerial sophistication in adaptive resource control is more than a managerial ethos.Practical implicationsThe proposed analytic process provides scientific decision support tools with control mechanisms with respect to deploying multiple resources and setting actionable goals, thereby presenting pragmatic benchmarking options to industry managers.Originality/valueUsing the theoretical underpinnings of the resource-based view (RBV) and resource orchestration, this study advances knowledge about the complex interaction of key resources by presenting a salient analytic process. The empirical design, which portrays holistic interaction patterns, adds to the uniqueness of this study of the complex interlinkages between capabilities, resources and shareholder value.

Adaptive Control in CNC Sheet Metal Processing

Three different and complementary ways of adaptive control are presented, each working on a different time scale. All three of them are made possible due to evolutions and developments in CNC controls. The first and most popular way of adaptive control is adaptive process control. Since the process variables in sheet metal equipment change significantly in milliseconds, the control loop must also perform on a sub second time scale. The second adaptive loop is adaptive production control. Modern CNC controls know what they are manufacturing and talk with higher production software. Instead of just executing a planning that came top down, the CNC has enough knowledge of its environment that it can propose an intelligent job sequence and hence react more effectively on unforeseen situations. These adaptive loops perform on a time scale of hours and days. The third adaptive loop is adaptive resource control. To produce sheet metal parts, we need several kinds of resources: human resources, material, consumables, energy and equipment. CNC sheet metal equipment is a considerable investment. However most production managers do not know how effective their resources are being used. By applying the principles of overall equipment effectiveness, we can close the resource control loop. This loop performs on a time scale of weeks and months.

What does control theory bring to systems research?

Feedback mechanisms can help today's increasingly complex computer systems adapt to changes in workloads or operating conditions. Control theory offers a principled way for designing feedback loops to deal with unpredictable changes, uncertainties, and disturbances in systems. We provide an overview of the joint research at HP Labs and University of Michigan in the past few years, where control theory was applied to automated resource and service level management in data centers. We highlight the key benefits of a control-theoretic approach for systems research, and present specific examples from our experience of designing adaptive resource control systems where this approach worked well. In addition, we outline the main limitations of this approach, and discuss the lessons learned from our experience.

Adaptive control of virtualized resources in utility computing environments

Data centers are often under-utilized due to over-provisioning as well as time-varying resource demands of typical enterprise applications. One approach to increase resource utilization is to consolidate applications in a shared infrastructure using virtualization. Meeting application-level quality of service (QoS) goals becomes a challenge in a consolidated environment as application resource needs differ. Furthermore, for multi-tier applications, the amount of resources needed to achieve their QoS goals might be different at each tier and may also depend on availability of resources in other tiers. In this paper, we develop an adaptive resource control system that dynamically adjusts the resource shares to individual tiers in order to meet application-level QoS goals while achieving high resource utilization in the data center. Our control system is developed using classical control theory, and we used a black-box system modeling approach to overcome the absence of first principle models for complex enterprise applications and systems. To evaluate our controllers, we built a testbed simulating a virtual data center using Xen virtual machines. We experimented with two multi-tier applications in this virtual data center: a two-tier implementation of RUBiS, an online auction site, and a two-tier Java implementation of TPC-W. Our results indicate that the proposed control system is able to maintain high resource utilization and meets QoS goals in spite of varying resource demands from the applications.

AQUILA: adaptive resource control for QoS using an IP-based layered architecture

Support for quality of service is an essential component of the next-generation Internet. The European research project AQUILA is committed to defining a DiffServ-based architecture for delivering on-demand QoS to requesting applications. Focal characteristics of the proposed solution are backward compatibility to the existing Internet and scalability to very large networks. To achieve such goals, AQUILA implements an overlaid distributed control layer, the resource control layer, implementing a novel mechanism for dynamic control of intradomain resources, the dynamic resource pool. On the interdomain aspects, the AQUILA architecture extends the BGRP framework for the aggregation of interdomain reservations to overcome scalability issues. This article describes the general AQUILA architecture, with a special focus on the DRP and BGRP mechanisms.