A decision-support system for smarter city planning and management

  • Authors:

  • Y.-K. Juan;L. Wang;J. Wang;J. O. Leckie;K.-M. Li

  • Affiliations:

  • School of Economics and Management, Tongji University, Shanghai, China and Department of Architecture, National Taiwan University of Science and Technology, Taipei, Taiwan;School of Business, China University of Political Science and Law, Beijing, China;Center for Sustainable Development and Global Competitiveness, Stanford University, Stanford, CA;Department of Civil and Environmental Engineering, Stanford University, Stanford, CA;China International Engineering Consulting Corporation, Beijing, China

  • Venue:
  • IBM Journal of Research and Development
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

Urbanization and globalization have had a profound impact on city development during the last ten years. Rapid technological advancements and the emphasis on sustainability provide city planners and managers with more opportunities and challenges than ever before. A city--composed of various operational systems, networks, infrastructures, and environments--can be improved and optimized through the application of advanced technology solutions. A smart city is one that utilizes self-managing autonomic technologies to identify its functions and promote prosperity and sustainability. This kind of city involves one of the most promising city development strategies worldwide. This paper develops a decision-support system that both assesses multidimensional levels of "smartness" for the current solutions of a city to environmental problems and recommends an optimal set of improvement strategies. The development of smartness assessment is based on the notion of a self-managing autonomic system defined by IBM. A hybrid approach called GAA* combines an A* graph search algorithm with genetic algorithms and is used to analyze all possible improvement strategies and tradeoffs, balancing required budgets, expected benefits, and upgradeable adaptive levels to determine optimal solutions. Two decision scenarios are introduced to validate proposed strategies provided by the decision system.