Big data analytics for smart city: Methodologies and Applications
Emerging on-demand services, such as Uber and GoGoVan in Hong Kong, provide a platform for users to request services on the spot and for suppliers to meet such demand. Uber, for example, allows its users to call for taxies on demand through mobile apps. The demand is dispatched by Uber to the drivers, who decide whether or not to accept them. If multiple drivers are willing to serve, the order will be assigned to one of them according to pre-established policies. Future energy systems can also be considered as on-demand services, as multiple suppliers, including power stations, energy stores, and mobile charging stations, compete to satisfy energy demand from their customers. This project aims to study the fundamental problem of demand dispatching in these emerging on-demand services, with the objective of maximizing supplier profits and saving user costs.
Big data generated by heterogeneous sources in urban spaces would facilitate a better understanding of the citys operation, and new possibilities for optimization of the infrastructure.
In addition, such data provides enormous opportunities for the study of general social phenomena, such as entertainment patterns and human mobility.
In this project, we aim to propose new methodologies for big data processing and analytics in urban applications, which utilize urban big data to tackle the challenges cities faced like transportation, environment and energy problems.
Most exsiting big data analytics is performed within a single disciplinary. In practice, however, there are multiple disciplinaries inter-related with each other, e.g., various kinds of transportation systems, transportation and weather. Jointly analyzing multiple related disciplinaries can obtain new knowledge. In this project, we thus propose methodologies for cross-disciplinary bigdata analytis, and apply them to urban computing and social network analysis.