Lempel-Ziv Complexity for Dynamic Server Load Balancing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for dynamic load-balancing in remote-hosted operations (RHO) systems fail to consistently and reliably identify optimal resource utilization on long timescales, leading to inefficient resource allocation and potential Service Level Agreement (SLA) violations, resulting in increased total cost of ownership (TCO) and suboptimal performance.
Innovation Solution
The implementation of a method that dynamically reconfigures client and resource allocations using historical load measurements and Lempel-Ziv Complexity analysis to predict and rank feasible client-set/resource-set combinations, optimizing resource utilization and ensuring SLA compliance by continuously measuring and rebalancing loads across servers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If ad hoc load-balancing methods are used to assign client sets to servers, then the system can operate with simple state-less balancing, but the resource utilization is suboptimal and TCO increases
Solution Approach 1:
The patent implements dynamic state-aware load balancing that adapts to changing client load patterns over time. The system continuously monitors historical loads and uses Lempel-Ziv complexity to identify optimal client sets, transitioning from static ad hoc balancing to dynamic optimization that responds to temporal variations in resource demands.
Solution Approach 2:
The patent introduces Lempel-Ziv complexity as a new parameter for measuring and comparing load patterns. By transforming load time series into complexity metrics, the system can objectively evaluate and select optimal client set assignments, moving beyond subjective ad hoc decisions to quantifiable parameter-based optimization.
2Productivity
If state-aware load-balancing is implemented to maximize resource utilization, then TCO decreases, but the system complexity increases
Solution Approach 1:
The patent replaces complex manual or heuristic load balancing mechanisms with an automated algorithmic approach based on Lempel-Ziv complexity calculation. This substitution transforms the load balancing process from ad hoc decision-making to a systematic computational method that objectively identifies optimal assignments.
Solution Approach 2:
The patent introduces Lempel-Ziv complexity as an intermediary metric that bridges the gap between raw load data and optimization decisions. This intermediary transformation simplifies the comparison of complex load patterns into a single comparable value, making the optimization process more manageable and systematic.
3Reliability
If historical load measurements are analyzed to predict future loads, then SLA compliance improves, but the measurement and analysis overhead increases
Solution Approach 1:
The patent performs preliminary analysis of historical load data to establish baseline patterns and complexity metrics before making allocation decisions. By pre-processing and storing load historical data and pre-calculating Lempel-Ziv complexity values, the system reduces real-time analysis requirements and speeds up allocation decisions while maintaining SLA compliance.
Solution Approach 2:
The patent implements periodic load analysis at appropriate intervals rather than continuous analysis. The system updates client set assignments based on historical load patterns at strategic time points, balancing the need for SLA compliance with the cost of continuous measurement and reoptimization.
Data Source
AI summary
Optimal assignment of clients to client-sets, resources to resource-sets, and client-sets to resource-sets in a server farm allows for periodic re-balancing of the load as client usership and concurrent-user activity fluctuate. Unique combinations of clients are generated as candidate client-sets, and historical load measurements for clients in each candidate client-set are summed. Summed loads for the candidate client-sets are compared against available resources of resource-sets. An objective function is employed to identify optimal assignment of clients to client-sets, resources to resource-sets, and client-sets to resource-sets.