# US 2021/0243696 A1 · Energy savings system based machine learning of wireless performance activity for mobile information handling system connected to plural wireless networks

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2021/0243696 A1
- Document ID: US20210243696A1
- Status: Published application
- Kind: A1
- Application number: 16/779,476
- Filed: 2020-01-31
- Published: 2021-08-05
- Earliest claimed: 2020-01-31
- Assignees: Dell Products L.P.
- Applicants: Dell Products, LP
- Inventors: Abu S. Sanaullah; Liam B. Quinn; Jace W. Files
- Web page: https://patentgrep.com/patent/US20210243696A1

## CPC

- H04W 52/0258: {controlling an operation mode according to history or models of usage information, e.g. activity schedule or time of day}
- G06N 3/084: Backpropagation, e.g. using gradient descent
- G06N 20/00: Machine learning
- H04W 52/0254: {detecting a user operation or a tactile contact or a motion of the device}
- H04W 52/0274: {by switching on or off the equipment or parts thereof}
- H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A mobile information handling system comprising a plurality of wireless network interface modules, a wireless network interface control system for controlling the plurality of wireless network interface modules, and a processor executing instructions of a wireless utilization machine learning inference modulator to receive iterative wireless utilization profiles indicating aggregated time and location profiles of wireless network utilization parameters and user configuration states of the information handling system for data needs including applications and hardware usage levels. The system to execute a machine learning process to determine a predictive time and date based plural wireless control setting index for adjusting control settings of the plural wireless network interface modules based on the received iterative wireless utilization profiles and to modify operation of some the plurality of wireless network interface modules based on the predictive time and date based plural wireless control setting index for an impending predictive time period.

## Claims

### Claim 1

A mobile information handling system comprising:
a processor, a memory, a power management system, and a plurality of wireless network interface modules for wireless connection to a plurality of wireless networks;
a wireless network interface control system for controlling the plurality of wireless network interface modules;
the processor executing instructions of a wireless utilization machine learning inference modulator to receive iterative wireless utilization profiles indicating aggregated time and location profiles of wireless network utilization parameters and the performance of each of the plurality wireless network interface modules; and
a sensor to receive input descriptive of the environment and location of the mobile information handling system for inclusion in the iterative wireless utilization profiles;
the processor reporting user configuration states for data needs including applications operating, and processing, port, battery, and memory hardware usage levels for inclusion in the iterative wireless utilization profiles;
the wireless utilization machine learning inference modulator to, upon execution of a machine learning process, determine a predictive time and date based plural wireless control setting index for adjusting control settings of the plural wireless network interface modules based on information associated with the received iterative wireless utilization profiles and updating the predictive time and date based plural wireless control setting index to a wireless recommendation history database; and
the wireless network interface control system accessing the predictive time and date based plural wireless control setting index correlating to a current calendar day, time and location to disable or leave enabled each of the plurality of wireless network interface modules.

### Claim 2 (depends on 1)

The mobile information handling system of claim 1, wherein the wireless utilization machine learning inference modulator to, upon execution of a machine learning process, determine a predictive time and date based plural wireless control setting index for adjusting the performance of the wireless network interface modules further based on a previously-determined predictive time and date based plural wireless control setting index from the wireless recommendation history database of time and date based plural wireless control settings corresponding to the time, day and location of the received iteration of the wireless utilization profiles.

### Claim 3 (depends on 1)

The mobile information handling system of claim 1, wherein the wireless network interface control module accessing the updated predictive time and date based plural wireless control setting index correlating to a current calendar, day, time and location disables a subset of the plurality wireless interface modules predicted to not be used.

### Claim 4 (depends on 1)

The mobile information handling system of claim 1, wherein the plurality wireless interface modules comprises:
a WiFi wireless interface module;
a 5G LTE wireless interface module; and
a Bluetooth wireless interface module.

### Claim 5 (depends on 1)

The mobile information handling system of claim 1, where the received iterative wireless utilization profiles indicating aggregated time and location profiles of wireless network utilization parameters, the performance of each of the plurality wireless network interface modules, and user configuration states for data needs includes reported available wireless networks corresponding with the plurality of wireless interface modules at the time and day of the received iterative wireless utilization profile.

### Claim 6 (depends on 1)

The mobile information handling system of claim 1, where the received iterative wireless utilization profiles indicating aggregated time and location profiles of wireless network utilization parameters, the performance of each of the plurality wireless network interface modules, and user configuration states for data needs includes reported current battery power states at the time and day of the received iterative wireless utilization profile.

### Claim 7 (depends on 1)

The mobile information handling system of claim 1, where the received iterative wireless utilization profiles indicating aggregated time and location profiles of wireless network utilization parameters, the performance of each of the plurality wireless network interface modules, and user configuration states for data needs includes reported wireless signal quality and bandwidth levels corresponding with the plurality of wireless interface modules at the time and day of the received iterative wireless utilization profile.

### Claim 8

A method of modulating performance of a plurality of wireless network interface modules for a mobile information handling system for power efficiency, comprising:
receiving, at a processor executing instructions of a wireless utilization machine learning inference modulator, an iterative wireless utilization profile indicating aggregated time and location profiles of wireless network utilization parameters, the performance of each of the plurality wireless network interface modules, and user configuration states of the mobile information handling system for data needs; and
executing code instructions of a machine learning service of the wireless utilization machine learning inference modulator to determine a predictive time and date based plural wireless control setting index for predictively adjusting the performance of the wireless network interface modules during an impending predictive time period of wireless system utilization based on information associated with the received iterative wireless utilization profiles and updating the predictive time and date based plural wireless control setting index to a wireless recommendation history database;
accessing the predictive time and date based plural wireless control setting index correlating to a current calendar day, time of day and location pattern of the predictive time period by the wireless network interface control system; and
and predictively adjusting the control settings of at least one of the plurality of wireless network interface modules.

### Claim 9 (depends on 8)

The method of claim 8, further comprising:
receiving time and date based parameter data factors relating to time of day, day of the week, day of the month, day of the year, and time proximity to scheduled events of a user in the iterative wireless utilization profile; and
applying the machine learning service of the wireless utilization machine learning inference modulator to detect patterns of repeated wireless utilization and user configuration states of the mobile information handling system for data needs for classification and comparison with later received impending predictive time periods of wireless utilization.

### Claim 10 (depends on 8)

The method of claim 8, wherein predictively adjusting the control settings of at least one of the plurality of wireless network interface modules includes a disable instruction for the at least one wireless network interface module that is not predicted to be used during the predictive time period.

### Claim 11 (depends on 8)

The method of claim 8, wherein predictively adjusting the control settings of at least one of the plurality of wireless network interface modules includes a transmission power reduction instruction for the at least one wireless network interface module that is not predicted to be used at high data bandwidth during the predictive time period.

### Claim 12 (depends on 8)

The method of claim 8, wherein predictively adjusting the control settings of at least one of the plurality of wireless network interface modules includes a sleep mode instruction for the at least one wireless network interface module that is not predicted to be used during the predictive time period.

### Claim 13 (depends on 8)

The method of claim 8, further comprising:
sending notice via graphical user interface of predictive adjustment to the control settings of each of the plurality of wireless network interface modules.

### Claim 14 (depends on 13)

The method of claim 13, further comprising:
updating the stored predictive time and date based plural wireless control setting index with a user non-response or a user response providing an indication that the user declines the predictive adjustment to the control settings of each of the plurality of wireless network interface modules.

### Claim 15 (depends on 8)

The method of claim 8, wherein the plurality wireless interface modules comprises:
a WiFi wireless interface module; and
a plurality of 5G LTE wireless interface modules.

### Claim 16

A mobile information handling system comprising:
a processor, a memory, a power management system, and a plurality of wireless network interface modules for wireless connection to a plurality of wireless networks;
a wireless network interface control system for controlling the plurality of wireless network interface modules;
the processor executing instructions of a wireless utilization machine learning inference modulator to receive time and date based parameter data factors relating to time of day, day of the week, day of the month, day of the year, and time proximity to scheduled events of a user;
the wireless utilization machine learning inference modulator to apply a machine learning classification algorithm to match correlation of learned patterns in the time and date based parameter data factors of an impending predictive time period of wireless system utilization and select a matching previously determined predictive time and date based plural wireless control setting index for predictively adjusting the control settings of the plurality of wireless network interface modules during the impending predictive time period of wireless system utilization; and
the wireless utilization machine learning inference modulator accessing the matched predictive time and date based plural wireless control setting index correlating to a current calendar day, time and location of an impeding predictive time period to suggest to the user, via a graphical user interface, predictive adjustments to modify control settings of a subset of the plurality of wireless network interface modules to reduce energy consumption.

### Claim 17 (depends on 16)

The mobile information handling system of claim 16, further comprising:
a network interface control system to receive predictive adjustments to modify control settings of a subset of the plurality of wireless network interface modules to reduce energy consumption when a user confirms the suggested predictive adjustments to modify control settings of the subset of the plurality of wireless network interface modules; and
the network interface control system to disable the subset of the plurality of wireless network interface modules.

### Claim 18 (depends on 16)

The mobile information handling system of claim 16, wherein the wireless utilization machine learning inference modulator updates the predictive time and date based plural wireless control setting index at a wireless recommendation history database with data indicating a user's response of confirmation or denial of the suggested predictive adjustments to modify control settings of the subset of the plurality of wireless network interface modules.

### Claim 19 (depends on 16)

The mobile information handling system of claim 16, wherein the predictive time and date based plural wireless control setting index stored at a wireless recommendation history database is determined based on a machine learning service conducting repeated training via received iterative wireless utilization profiles indicating aggregated time and location profiles of wireless network utilization parameters, and user configuration states of the mobile information handling system for data needs during matched correlation to time and date learned patterns in the time and date based parameter data factors.

### Claim 20 (depends on 1)

The mobile information handling system of claim 1, wherein the plurality wireless interface modules comprises:
a WiFi wireless interface module; and
a plurality of 5G LTE wireless interface modules.
