Using predictive analytics to determine expected use patterns of vehicles to recapture under-utilized computational resources of vehicles
AssigneeToyota Motor North America, Inc.
InventorShingo Sugimoto
Life of this patent
Estimating the term…
Abstract
A distributed computing network includes one or more vehicles, each vehicle configured to act as a node in the distributed computing network, and a remote server including a processor and a memory module storing one or more non-transient processor-readable instructions that when executed by the processor cause the remote server to establish a data connection with the one or more vehicles, predict a pattern-of-use of the one or more vehicles, determine a predicted current use of the one or more vehicles, and allocate a computational task to the one or more vehicles based on the predicted pattern-of-use and the predicted current use.
Claims23
A distributed computing network comprising:
- one or more vehicles, each vehicle configured to act as a node in the distributed computing network;
- and
- a remote server comprising a processor and a memory module storing one or more non-transitory processor-readable instructions that when executed by the processor cause the remote server to:
- establish a data connection with the one or more vehicles;
- predict a pattern-of-use of the one or more vehicles;
- determine a predicted current use of the one or more vehicles based on a current status of the one or more vehicles;
- and
- allocate a computational task to the one or more vehicles based on the predicted pattern-of-use and the predicted current use,
- wherein the predicted current use of the one or more vehicles is determined based on a period of time the one or more vehicles is expected to remain stationary at an expected location, and
- wherein the remote server assigns a portion of the computational task proportional to the period of time the vehicle is expected to remain stationary at the expected location.
A vehicle configured to act as a node in a distributed computing network, the vehicle comprising:
- network interface hardware;
- a processor;
- and
- a memory module storing non-transitory processor-readable instructions that when executed by the processor cause the vehicle to:
- establish a communicative connection with a remote server;
- predict a pattern-of-use;
- predict a current use based on a current status of the vehicle;
- transmit the predicted pattern-of-use and the predicted current use to the remote server;
- and
- receive a computational task from the remote server based on the predicted pattern-of-use and the predicted current use,
- wherein the predicted current use of the vehicle is determined based on a period of time the vehicle is expected to remain stationary at an expected location, and
- wherein the remote server assigns a portion of the computational task proportional to the period of time the vehicle is expected to remain stationary at the expected location.
A method of allocating computational tasks in a distributed computing network comprising a remote server communicatively coupled between a grid computing network and one or more vehicles acting as nodes in the network, the method comprising:
- establishing, by the remote server, a data connection with the one or more vehicles;
- predicting, by the remote server, a pattern-of-use of the one or more vehicles;
- predicting, by the remote server, a current use of the one or more vehicles based on a current status of the one or more vehicles;
- and
- allocating, by the remote server, a computational task to the one or more vehicles based on the predicted pattern-of-use and the predicted current use,
- wherein the predicted current use of the one or more vehicles is determined based on a period of time the one or more vehicles is expected to remain stationary at an expected location, and
- wherein the remote server assigns a portion of the computational task proportional to the period of time the vehicle is expected to remain stationary at the expected location.
Dependencies are inferred from the claim text.