Blockchain UTXO Selection Using Congestion And Fee Forecasts

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional UTXO selection methods in blockchain transactions do not consider external factors, leading to inefficiencies such as sub-optimal transaction fees, loss of assets, and excessive network costs due to indiscriminate selection and lack of consideration for future transaction requirements and network congestion.

Innovation Solution

A computer system uses machine learning models to predict future transaction costs and transaction sizes based on network congestion and historical data, optimizing UTXO selection by considering network traffic and future transaction patterns to minimize costs and reduce UTXO inflation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of energy

If conventional UTXO selection methods are used that indiscriminately choose UTXOs without considering future requirements, then transaction completion is achieved, but transaction fees are sub-optimal and assets are lost due to dust outputs

Engineering Contradiction:

Improvetransaction feesVSAvoidUTXO selection strategy

Core Design Contradiction:

Loss of energyVSDevice complexity

Solution Approach 1:

The system performs preliminary actions by predicting future transaction requirements and network conditions before selecting UTXOs. The machine learning models forecast future transaction patterns, fees, and network congestion levels, allowing the system to proactively choose UTXO combinations that will remain optimal across multiple future transactions rather than just the current one.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements feedback mechanisms by continuously monitoring actual transaction outcomes and comparing them with predictions. The machine learning models are trained on historical transaction data and continuously updated based on actual network conditions and fee structures, allowing the system to adapt and improve its UTXO selection strategy over time based on real-world performance feedback.

Inventive Principle:

Principle #23Feedback

2Reliability

If a large number of UTXOs are selected to perform transactions during high network traffic, then transaction requirements are satisfied, but network costs become excessive

Engineering Contradiction:

Improvetransaction completionVSAvoidnetwork costs

Core Design Contradiction:

ReliabilityVSLoss of energy

Solution Approach 1:

The system applies dynamics by making UTXO selection adaptive to changing network conditions. The machine learning models continuously predict network congestion levels and transaction fee trends, allowing the system to dynamically adjust its UTXO selection strategy based on current and forecasted network states rather than using a static selection approach.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system changes parameters by selecting different UTXO combinations based on predicted network conditions. When network congestion is predicted to increase, the system may choose to consolidate smaller UTXOs into larger ones or select fewer, larger UTXOs to minimize the number of transactions required. The selection criteria and optimization parameters are adjusted based on forecasted fee structures and network traffic patterns.

Inventive Principle:

Principle #35Parameter changes

3Productivity

If UTXO selection is evaluated on a per-transaction basis without considering future requirements, then individual transactions are completed, but UTXO inflation occurs and assets are lost

Engineering Contradiction:

Improvetransaction processing efficiencyVSAvoidUTXO count

Core Design Contradiction:

ProductivityVSQuantity of substance

Solution Approach 1:

The system performs preliminary analysis of future transaction requirements using machine learning predictions. Before completing the current transaction, the system forecasts upcoming transactions and their requirements, then selects UTXOs that will satisfy both current and future needs, preventing the fragmentation that leads to UTXO inflation and dust outputs.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system ensures continuity of useful action by maintaining an optimal UTXO set for a sequence of transactions rather than treating each transaction independently. The machine learning models predict future transaction patterns and the system continuously manages the UTXO portfolio to ensure that UTXOs remain usable and valuable for upcoming transactions, preventing waste and inflation.

Inventive Principle:

Principle #20Continuity of useful action

Data Source

PatentUS12572932B2Systems and methods for blockchain network traffic management using automatic coin selection

Publication Date: 2026.03.10 CITIBANK N A

AI summary

A computer can monitor network traffic on a blockchain computing network. The computer can determine a current level of network congestion on the blockchain computing network. The computer can execute a first machine learning model that predicts a timeseries of future transaction costs based on historical data and the current level network congestion level of the blockchain computing network. The computer can also execute a second machine learning model to predict a timeseries of future transaction sizes and UTXO types for the distributed ledger-based account based on historical transaction data. The computer can select one or more UTXOs to use to complete the transaction of the transaction request. The computer can append a block instance containing an identification of the selected one or more UTXOs to the blockchain to complete the transaction.