Amazon Technologies, Inc.

Zachary Jared Wiggins

Paul William Berg

Christopher Lorenzo Dunn

Tristan Daniel Fries Wilson

Thomas Lowell Keller

Benjamin Warren Mercier

Diwakar Chakravarthy

Peter Varnum Commons

Alexander Julian Tribble

Paul Derek DeMarco

Tyson Christopher Trautmann

David Y Yamanoha

Alex Jennifer Tribble

Michael Luis Collado

Terence Smith

Paul Walker Mooring

Rohit Rangan

A first node can be selected as a target node, and a second node can be selected as a control to determine a performance limit associated with providing a service. A request for the service can be determined to be routed to the first node. A first indication of a first performance measurement associated with processing a first load by the first node can be received. A second indication of a second performance measurement associated with processing a second load by the second node can be received. A performance error of the first node can be determined based on the first performance measurement and the second performance measurement. The performance limit can be determined based on the performance error, and an action can be triggered based on the performance limit.

Real-time load limit measurement for a plurality of nodes

Techniques for improving communications efficiency between pairs of communication nodes running within a computer system are described herein. Potential locations for placing a communication node are evaluated using one or more fitness values wherein the fitness value is based at least in part on one or more system metrics associated with placing a communication node in the potential location. If an improved location is found based on the fitness value, the communication node may be migrated to the new location, thus improving system efficiency.

Moving nodes in a distributed system

This disclosure includes techniques for using distributed computing over a network to resolve difficult computational problems. Anonymization of the data allows computing devices in the distributed computing system to solve the computational problem without exposing private aspects of the data. Individual computing devices receive instructions and data that correspond to a piece of a larger computational problem. In one implementation, a user may request a webpage from a web server and receive the webpage along with commands in a scripting language that instructs the user's computer to process a piece of the larger computational problem. The web server may assign the piece of the problem to the user's computer based on processing capabilities of the user's computer. Combining solutions received from multiple distributed computing devices and reversing the anonymization process yields a solution to the computational problem.

Data anonymity and separation for user computation

A machine generated service cache that utilizes one or more machine learning classifiers is trained using service requests directed to a human-generated service and service responses generated by the human-generated service in response to the service requests. Once the machine generated service cache has been trained to a predetermined level of performance, the machine generated service cache can be utilized to process actual service requests directed to the human-generated service. The machine generated service cache might be utilized to process service requests for which it is not essential that the returned service response be identical to a response that would be generated by the human-generated service.

Machine generated service cache

Growing community of inventors

Seattle, WA, United States of America

Zachary Jared Wiggins