Context-Aware Framework for Performance Tuning via Multi-action Evaluation

Context-aware systems perform adaptive changes in several ways. One way is for the system developers to encompass all possible context changes in a context-aware application and embed them into the system. However, this may not suit situations where the system encounters unknown contexts. In such cases, system inferences and adaptive learning are used whereby the system executes one action and evaluates the outcome to self-adapts/self-learns based on that. Unfortunately, this iterative approach is time-consuming if high number of actions needs to be evaluated. By contrast, our framework for context-aware systems finds the best action for unknown context through concurrent multi-action evaluation and self-adaptation which reduces significantly the evolution time in comparison to the iterative approach. In our implementation we show how the context-aware multi-action system can be used for a context-aware evaluation for database performance tuning.