Distributed Ledger Request Rate Management with LSTM Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Cloud service providers face challenges in determining whether requests to increase a client's maximum request rate are legitimate and necessary, as they lack information about the client's trustworthiness and actual requirements, leading to potential denial of service attacks and inefficient resource allocation.
Innovation Solution
A system that trains a machine learning model using historical data to predict a target maximum request rate, combined with a distributed ledger like blockchain for validating and recording modifications, employs an LSTM model to analyze patterns and trends, ensuring that only valid requests are processed, thereby managing request rates effectively.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a fixed maximum request rate is assigned to a client, then denial of service attacks are prevented, but trusted clients cannot scale their requests when legitimately needed
Solution Approach 1:
The patent implements dynamic request rate adjustment by transitioning from fixed rate limits to a machine learning-based system that continuously adapts maximum request rates based on client behavior patterns, trust scores, and actual usage needs, allowing the system to respond flexibly to changing conditions while maintaining security
Solution Approach 2:
The system incorporates feedback mechanisms where client request patterns, throughput rates, and behavioral data are continuously monitored and fed back into the machine learning model, which then adjusts maximum request rates accordingly, creating a closed-loop system that balances security with legitimate scaling needs
2Ease of operation
If manual approval processes are used for request rate increases, then control over request rates is maintained, but the process is inefficient and lacks information about client trustworthiness
Solution Approach 1:
The patent introduces a distributed ledger as an intermediary layer that stores and verifies client information, request patterns, and approval histories, providing both the manual approval process and automated machine learning model with reliable, shared information about client trustworthiness and actual requirements
Solution Approach 2:
The system enables self-service capabilities where clients can request rate increases through automated processes, and the machine learning model can automatically approve or deny requests based on analyzed patterns and pre-established criteria, reducing manual intervention while maintaining control through the distributed ledger's verification mechanisms
3Productivity
If request rate limits are strictly enforced, then resource allocation is controlled, but trusted clients experiencing legitimate increases cannot access additional resources
Solution Approach 1:
The patent dynamically changes the request rate parameter based on multiple factors including client trust scores, historical behavior patterns, current system load, and predicted future needs, allowing the system to optimize resource allocation by adjusting rates for different clients at different times rather than applying uniform limits
Data Source
AI summary
Techniques for managing maximum request rates to shared system resources are disclosed. A system applies a machine learning model, such as a long short-term memory (LSTM) recurrent neural network (RNN) type model to historical maximum request rate data to determine a target maximum request rate for a particular client and a particular period of time. The system obtains the historical maximum request rate data from a distributed ledger, such as a blockchain. System clients may record modifications to their maximum request rates in the blockchain. The system modifies the maximum request rates associated with the system clients authorized to access shared resources based on the modified maximum request rates contained in the new blocks added to the blockchain.