ATM Sleep Interval Control via Bayesian User Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
ATMs experience high fault rates and maintenance costs due to frequent sleep state transitions caused by short sleep intervals during peak usage and excessive energy consumption during low usage periods due to long sleep intervals.
Innovation Solution
An energy-saving control method and device that uses a Bayesian prior probability model to predict user activity in different time periods, adjusting the sleep interval of ATMs based on these predictions to optimize power usage, preventing unnecessary wake-ups during high usage and reducing idle energy consumption during low usage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of energy
If the ATM is set to enter a sleep state after a short idle time, then energy consumption is reduced during low usage periods, but the ATM enters sleep and start states frequently during peak usage periods, resulting in high fault rates and maintenance costs
Solution Approach 1:
The patent implements dynamic adjustment of sleep interval parameters based on real-time user behavior patterns. The control unit continuously monitors usage data and adapts the sleep interval dynamically - using shorter intervals during peak periods and longer intervals during off-peak periods, transforming the static sleep setting into a dynamic, context-aware parameter that resolves the contradiction between energy saving and reliability
Solution Approach 2:
The system employs feedback mechanisms by monitoring actual usage patterns and adjusting sleep intervals accordingly. The control unit receives feedback from user transactions and modifies the sleep state timing based on observed behavior patterns, creating a closed-loop control system that optimizes both energy consumption and reliability through continuous adaptation
2Reliability
If the ATM is set to enter a sleep state after a long idle time, then fault rates and maintenance costs are reduced, but energy consumption increases during low usage periods
Solution Approach 1:
The system dynamically adjusts the sleep interval parameter based on time-of-day patterns and historical usage data. During off-peak periods when energy saving is prioritized, longer sleep intervals are applied, while during peak periods when reliability is critical, shorter intervals are automatically selected, allowing the system to adapt its behavior to different operational contexts
3Device complexity
If a fixed sleep interval is used for the ATM, then the control logic is simple, but the system cannot adapt to varying user activity patterns throughout the day, resulting in either excessive wake-ups or unnecessary energy consumption
Solution Approach 1:
The system performs preliminary analysis of user behavior patterns during setup and initialization phases, pre-calculating optimal sleep interval schedules for different time periods. This preliminary action allows the system to have sophisticated adaptability without requiring complex real-time computations, as the adaptive logic is prepared in advance based on historical and predicted usage patterns
Data Source
AI summary
Provided are an energy-saving control method and device for a self-service device. The method includes: acquiring to-be-learned sample information from historical usage data of users of the self-service device, where the sample information indicates the number of users which use the self-service device in each of different sub-periods of a period of time; learning the to-be-learned sample information by using a preset Bayesian prior probability model, to obtain a learning result; updating the Bayesian prior probability model based on the learning result; predicting the number of users in each of sub-periods of a preset period of time by using the updated Bayesian prior probability model, to obtain the predicted number of users at the self-service device; and modifying a sleep interval of the self-service device in each of the sub-periods based on the predicted number of users.