Leveraging Fog Computing for Geographically Distributed Smart Cities

Recently, the emergence of smart cities (SC), where data streams come from various geographically distributed places, has posed new challenges. Cloud Computing provides excellent services for smart cities, such as powerful computation and storage. However, processing the geographically distributed data using cloud computing only is not an ideal solution in some cases. Additionally, moving all the big raw data to the remote cloud is another challenge for cloud computing since there will be shortcomings in terms of delay and high bandwidth consumption. A solution that allows fog-to-cloud or fog-to-fog communication can address these limitations as fogs are typically located locally near the data sources. However, the questions related to the efficient frameworks design, workload distribution, cost, and various key technologies and communication challenges remain. To this end, this research investigates the impact of fog, employing our proposed architecture, on the efficient utilization and management of resources in highly distributed systems through experiments. The comparison showed that fog computing reduces the cost in terms of time and resource utilization. Additionally, the collaboration of autonomous agents locally (within one fog) or globally (across multiple fogs and cloud) supports scalability and automation. It also facilitates large-scale data processing across various real-world distributed locations.