SimPl: A Simulation Platform for Elastic Load-Balancing in a Distributed Spatial Cache Overlay

Location-based services (LBS) have to cope with increasing query loads at their data tier. Yet, the data access patterns of LBS typically possess spatial locality. Therefore, a dedicated spatial cache which provides efficient access to the data currently needed may considerably reduce this load. To ensure high throughput throughout the entire execution, previous work introduced an elastic load-balancing mechanism for multiple cache nodes that collaborate in a distributed spatial cache overlay. However, calibrating such a load-balancing mechanism is a non-trivial task, as several parameters influence such a system. We demonstrate a simulation platform (SimPl) for elastic load-balancing. SimPl enables a network administrator to set up several overlay topologies and calibrate their system parameters using different spatial data access patterns. A live visualization of the simulated overlay enables intuitive comparison of overlay topologies and their load-balancing abilities.