Energy-efficient Query Processing in Web Search Engines

By | September 3, 2018

ABSTRACT:

Web search engines are made by thousands out of query processing nodes, i.e., servers committed to processing client questions. Such numerous servers expend a lot of vitality, for the most part, responsible to their CPUs, however, they are important to guarantee low latencies since clients expect sub-second reaction times (e.g., 500 ms). In any case, clients can scarcely see reaction times that are quicker than their desires.

Subsequently, we propose the Predictive Energy Saving Online Scheduling Algorithm (PESOS) to choose the most suitable CPU recurrence to process a question on a for each center premise. PESOS goes for process inquiries by their due dates, and use abnormal state planning data to lessen the CPU energy utilization of a query processing node. PESOS constructs its choice in light of question productivity indicators, assessing the handling volume and preparing time of an inquiry.

We tentatively assess PESOS upon the TREC ClueWeb09B gathering and the MSN2006 inquiry log. Results demonstrate that PESOS can lessen the CPU energy utilization of a question preparing hub up to _48% contrasted with a system running at most extreme CPU center recurrence. PESOS beats additionally the best in class contender with a _20% vitality sparing, while the contender requires a fine parameter tuning and it might acquires in wild inactivity infringement.

DOWNLOAD: Energy-efficient Query Processing in Web Search Engines

Leave a Reply

Your email address will not be published. Required fields are marked *