18131323. REINFORCEMENT LEARNING FOR CONTROLLING SOFTWARE UPDATE TIMING simplified abstract (Microsoft Technology Licensing, LLC)

REINFORCEMENT LEARNING FOR CONTROLLING SOFTWARE UPDATE TIMING

Organization Name

Microsoft Technology Licensing, LLC

Inventor(s)

Dhirendra Kumar Bhupati of Sammamish WA (US)

Johnny Sterling Campbell of Woodinville WA (US)

REINFORCEMENT LEARNING FOR CONTROLLING SOFTWARE UPDATE TIMING - A simplified explanation of the abstract

This abstract first appeared for US patent application 18131323 titled 'REINFORCEMENT LEARNING FOR CONTROLLING SOFTWARE UPDATE TIMING

The abstract describes a software update distribution service that utilizes reinforcement learning to determine optimal times for downloading and installing software updates on client computing devices within an enterprise.

• The software update distribution service leverages reinforcement learning, a specific type of machine learning algorithm.
• The service aims to learn the best times to download and install software updates to achieve predefined goals for the enterprise or group of client computing devices.
• A software-based agent learns to minimize penalties by performing software update activities at specific times based on a weighted combination of metrics.
• Metrics include factors like the impact of software update timing on network traffic and power consumption.
• The service aims to optimize the software update process for efficiency and effectiveness.

Potential Applications: - Enterprise software management - IT infrastructure optimization - Network traffic management

Problems Solved: - Inefficient software update distribution - Suboptimal timing for software updates - High network traffic and power consumption due to software updates

Benefits: - Improved software update efficiency - Reduced network congestion and power consumption - Enhanced overall system performance

Commercial Applications: Optimizing software update distribution for large enterprises can lead to cost savings, improved productivity, and better resource management in IT departments.

Questions about the technology: 1. How does reinforcement learning improve the software update process? Reinforcement learning helps the software agent learn optimal times for software updates based on various metrics, leading to more efficient distribution.

2. What are the key benefits of using reinforcement learning in software update distribution? Reinforcement learning can help minimize penalties associated with software update timing, leading to improved network efficiency and reduced power consumption.

Original Abstract Submitted

Described herein is a software update distribution service that leverages reinforcement learning—a specific type machine learning algorithm—to discover or learn optimal times (e.g., a schedule) to download software updates and to install software updates for software applications installed on a group of client computing devices of a specific enterprise, in order to achieve one of several predefined goals or objectives selected for the specific enterprise, or for the specific group of client computing devices. Using reinforcement learning, a software-based agent learns to perform activities relating to software updates at specific times that minimize a penalty, wherein the penalty is derived based on a weighted combination of metrics, some of which relate to the impact of software update timing on network traffic and power consumption.