A cloud scheduler assisted by a fuzzy affinity-aware engine

Recent advances on declarative paradigms have introduced expressive resources based on fuzzy logic. These are very useful for increasing the flexibility of the so-called fuzzy logic programming paradigm, resulting in highly expressive languages where the treatment of uncertainty and approximate reasoning is performed in a natural, efficient way. Therefore, making it extremely useful for decision-making scenarios dealing with high levels of uncertainty. One such scenario is capacity management in cloud environments, where the amount of resources that users will request is unknown and can vary significantly over time, usually leading to poor resource utilization. Overbooking techniques allow cloud providers to increase utilization, but the risk of degrading application performance due to exhausting resources also increases as applications need to share the servers. Fuzzy logic programming can be used to decide how cloud applications should be co-located with each other, minimizing the interference among them. Therefore, we propose a new scheduling mechanism based on fuzzy logic cores clustering, and applications-cores affinity estimation to decide which applications to co-locate reducing the interference. An experimental evaluation confirms that our affinity-aware fuzzy logic assisted scheduler minimizes the interference among applications, enabling a more safe overbooking and consequently higher cloud provider revenue.