Water Rights Allocation Optimization Using Regret Theory
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for initial water rights allocation are inefficient in managing limited water resources, leading to conflicts among water use departments, as they rely heavily on prior knowledge and fail to account for complex multi-objective decision-making in high-dimensional spaces, resulting in suboptimal solutions that do not consider fairness and ecological benefits.
Innovation Solution
An initial allocation optimization method based on regret theory, using data from regional societies, economies, and water conservancy, with objective functions for maximum social, economic, and ecological benefits, and a multi-objective optimization algorithm like NSGA-II to determine Pareto frontiers and calculate regret metrics for selecting the best allocation scheme.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional multi-objective decision-making methods transform multiple objectives into single objectives through prior knowledge, then a unique optimal scheme can be provided, but the solution is highly dependent on accuracy of prior knowledge and may not account for complex multi-objective decision-making in high-dimensional spaces
Solution Approach 1:
The patent transforms the decision-making approach by changing the parameter representation from single-objective values to multi-dimensional utility functions. Each water use department is assigned a utility function with multiple parameters (economic benefit, social benefit, ecological benefit) that are optimized simultaneously through the genetic algorithm, eliminating dependency on prior knowledge for parameter transformation.
Solution Approach 2:
The patent introduces a regret theory-based utility function as an intermediary between the multi-objective optimization problem and the final decision. This utility function mediates the trade-offs between conflicting objectives by quantifying the regret of not selecting the optimal scheme, allowing the system to handle complex multi-objective decisions without relying on external prior knowledge.
2Productivity
If intelligent optimization algorithms directly solve multi-objective Pareto Frontier, then various schemes on Pareto Frontier can be obtained, but it is almost impossible to find Pareto frontier completely in a complex multi-objective high-dimensional space
Solution Approach 1:
The patent extracts the essential decision-making criterion from the complete Pareto frontier by introducing a regret-based utility function. Instead of requiring complete exploration of the high-dimensional Pareto frontier, the method extracts the key information needed for decision-making (the regret of not selecting each scheme) and uses this to identify the optimal allocation without exhaustive search.
Solution Approach 2:
The patent changes the optimization parameter from minimizing multiple objectives simultaneously to minimizing a single regret-based utility function. This parameter transformation converts the complex multi-objective problem into a single-objective optimization that can be efficiently solved by genetic algorithms while maintaining reliability in high-dimensional spaces.
3Measurement precision
If absolute rational decision-making method pursues an only optimal solution, then a theoretical optimal scheme can be found, but the initial optimization allocation of water rights is closer to a bounded rational decision-making problem where decision makers seek a satisfactory scheme
Solution Approach 1:
The patent introduces a regret theory-based utility function as an intermediary that bridges absolute rational decision-making and bounded rational decision-making. This utility function calculates the regret for each Pareto scheme by comparing it with the optimal scheme, providing a satisfactory solution that is both theoretically sound and acceptable to decision-makers with limited rationality.
Solution Approach 2:
The patent transforms the decision criterion from pursuing a single theoretical optimal solution to minimizing regret across multiple Pareto schemes. This parameter change allows the system to provide solutions that are both precise (based on mathematical optimization) and operationally acceptable (by quantifying and minimizing decision-makers' regret).
Data Source
AI summary
The disclosure relates to a water resource planning method. An objective is to provide an initial allocation optimization method of water rights based on regret theory. A technical scheme is as follows: the initial allocation optimization method of water rights based on regret theory includes following steps: S1, basic data set preparation: collecting relevant data of regional society, economy, water conservancy and agriculture; S2, objective function setting: considering economic, social and ecological values of water resources utilization, determining three objective functions of maximum social benefit, maximum economic benefit and maximum ecological benefit; S3, constraint condition setting: a supply and demand balance constraint of a water resource and a water demand constraint of a water use department; S4, multi-objective optimization algorithm: using a second generation non-dominated sorting genetic algorithm (NSGA-II) as the multi-objective optimization algorithm; and S5, initial allocation scheme of water rights based on regret theory.