Reward-Aware Job Scheduling for Agricultural Machinery Sharing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The increasing costs of smart agricultural machinery and electrification pose challenges for initial investments in sharing services, necessitating improved utilization rates and productivity, while existing scheduling methods fail to adequately consider spatial, temporal, and uncertainty factors.
Innovation Solution
A schedule formulation aiding system that optimizes job execution plans using geographic information, resource information, and temporal reward distributions to select jobs resulting in higher rewards, considering uncertainties and spatial constraints.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If agricultural machinery sharing services are introduced to improve utilization rates, then productivity and resource efficiency are improved, but device complexity and operational planning difficulty increase due to multiple spatial, temporal, and uncertainty factors
Solution Approach 1:
The scheduling problem is segmented into multiple independent modules: spatial constraint satisfaction, temporal reward distribution optimization, uncertainty factor analysis, and job contract evaluation. Each module processes specific aspects separately before integrating results, reducing overall system complexity while maintaining comprehensive optimization capability
Solution Approach 2:
The system introduces a temporal reward distribution dimension that transforms traditional static scheduling into dynamic multi-dimensional optimization. By adding time-dependent reward values and temporal constraints to the scheduling model, the system optimizes across space, time, and reward dimensions simultaneously, improving productivity without proportionally increasing complexity
2Reliability
If comprehensive spatial and temporal constraints are considered in scheduling, then job execution quality and reward optimization are improved, but calculation time and processing complexity increase
Solution Approach 1:
The system performs preliminary filtering of job contracts based on spatial constraints and basic feasibility criteria before conducting detailed temporal optimization. By pre-processing and eliminating infeasible options early, the system reduces the search space for subsequent complex calculations, maintaining high execution quality while reducing overall computation time
Solution Approach 2:
The system dynamically adjusts optimization parameters and constraint weights based on problem characteristics and computational resources available. By changing parameters such as reward distribution functions, constraint strictness levels, and algorithmic depth, the system balances solution quality against calculation time requirements for different scheduling scenarios
3Productivity
If multiple job contracts with different temporal rewards are accepted, then total reward and productivity are improved, but scheduling difficulty and resource coordination complexity increase
Solution Approach 1:
The system implements feedback mechanisms that continuously evaluate the impact of accepting additional job contracts on overall scheduling feasibility and reward optimization. By providing real-time feedback on resource utilization, temporal conflicts, and reward projections, the system guides operators in making informed decisions about job contract acceptance, simplifying the operational complexity while maximizing total reward
Data Source
Figure 1
Figure 2
Figure 3
AI summary
In a schedule formulation aiding system, an input unit receives, for each of the plurality of jobs, an input of a job execution period serving as a temporal constraint in scheduling the jobs, geographic information indicating a position where the resource is used for the job, resource information related to a plurality of the resources for executing the job, and job information including a temporal reward distribution that is dependent on timing of job execution; a processing unit is configured to create a tentative job set enabling a job execution time required for execution of the jobs to fall within the job execution period, based on the job information and the resource information, and to determine a subset of jobs enabling greater reward to be achieved, based on the temporal reward distribution, the job execution period, the geographic information, and the resource information; and an output unit outputs the determined subset of jobs.