Charging Base Battery Forecasting for Future Renewable Energy Rate
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems cannot accurately predict the amount of renewable energy held by a storage battery in a charging station at a future time, leading to potential discrepancies between user expectations and actual availability.
Innovation Solution
An information processing method that acquires the remaining power amount and actual charging and discharging values of a storage battery, predicts the necessary power amount and renewable energy power amount based on these values, and outputs a renewable energy rate at a designated time, incorporating factors like purchase plans and weather conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If only current renewable energy rate is provided, then current storage battery renewable energy status is known, but future renewable energy availability cannot be predicted
Solution Approach 1:
The system performs preliminary prediction of future renewable energy rates by acquiring historical charging/discharging data and weather information, then uses machine learning models to forecast future renewable energy availability before the user makes charging decisions. This allows users to plan charging in advance based on predicted future rates rather than only current status.
2Measurement precision
If detailed prediction calculations are performed, then prediction accuracy is improved, but system complexity increases
Solution Approach 1:
The system introduces a server as an intermediary that performs complex machine learning predictions and calculations. The server acts as a mediator between the charging station and user terminal, handling all sophisticated prediction algorithms, data processing, and model training remotely. This allows the user terminal to remain simple while still providing accurate predictions through the server's computational power.
3Reliability
If multiple factors are considered in prediction, then prediction comprehensiveness is improved, but data processing complexity increases
Solution Approach 1:
The machine learning model is designed as a universal prediction system that can handle multiple types of input data (historical charging/discharging patterns, weather conditions, time of day, day of week) and produce comprehensive future renewable energy rate predictions. The single model performs multiple functions including pattern recognition, trend analysis, and forecasting across different time horizons, reducing the need for separate specialized systems for each factor.
Data Source
AI summary
This server acquires the remaining power amount of a storage battery possessed by a charging base, a designated time from the present onward, a first actual value that is the actual value of charging power to the storage battery by a renewable energy, and a second actual value that is the actual value of discharge power from the storage battery, predicts, on the basis of the remaining power amount of the storage battery and the second actual value, a necessary power amount that is the charge amount of the storage battery in a period from the present to the designated time, predicts, on the basis of the first actual value, a renewable energy amount that is a power amount by the renewable energy among the necessary power amount, and outputs the renewable energy rate of the storage battery at the designated time on the basis of the renewable energy amount.