Advanced analytics through fpga based query processing and deep reinforcement learning
- Autores: Gorker Alp Malazgirt
- Directores de la Tesis: Adrián Cristal Kestelman (dir. tes.)
- Lectura: En la Universitat Politècnica de Catalunya (UPC) ( España ) en 2019
- Idioma: español
- Tribunal Calificador de la Tesis: Abraham Mendelson (presid.), Marc Casas Guix (secret.), Ivan Ratkovic (voc.)
- Programa de doctorado: Programa de Doctorado en Arquitectura de Computadores por la Universidad Politécnica de Catalunya
- Materias:
- Texto completo no disponible (Saber más ...)
- Resumen
Today, vast streams of structured and unstructured data have been incorporated in databases, and analytical processes are applied to discover patterns, correlations, trends and other useful relationships that help to take part in a broad range of decision-making processes. The amount of generated data has grown very large over the years, and conventional database processing methods from previous generations have not been sufficient to provide satisfactory results regarding analytics performance and prediction accuracy metrics. Thus, new methods are needed in a wide array of fields from computer architectures, storage systems, network design to statistics and physics.
This thesis proposes two methods to address the current challenges and meet the future demands of advanced analytics. First, we present AxleDB, a Field Programmable Gate Array based query processing system which constitutes the frontend of an advanced analytics system. AxleDB melds highly-efficient accelerators with memory, storage and provides a unified programmable environment. AxleDB is capable of offloading complex Structured Query Language queries from host CPU. The experiments have shown that running a set of TPC-H queries, AxleDB can perform full queries between 1.8x and 34.2x faster and 2.8x to 62.1x more energy efficient compared to MonetDB, and PostgreSQL on a single workstation node.
Second, we introduce TauRieL, a novel deep reinforcement learning (DRL) based method for combinatorial problems. The design idea behind combining DRL and combinatorial problems is to apply the prediction capabilities of deep reinforcement learning and to use the universality of combinatorial optimization problems to explore general purpose predictive methods. TauRieL utilizes an actor-critic inspired DRL architecture that adopts ordinary feedforward nets. Furthermore, TauRieL performs online training which unifies training and state space exploration. The experiments show that TauRieL can generate solutions two orders of magnitude faster and performs within 3% of accuracy compared to the state-of-the-art DRL on the Traveling Salesman Problem while searching for the shortest tour. Also, we present that TauRieL can be adapted to the Knapsack combinatorial problem. With a very minimal problem specific modification, TauRieL can outperform a Knapsack specific greedy heuristics.
