A Compound Optimization Greedy Strategy with Reverse Correction Mechanism

Greedy strategy is an algorithm thinking with local optimization as the core idea, but only when the problem has no after-effect, the global optimization can be achieved. Therefore, greedy strategy is not the first choice for researchers to solve the problem. Based on the greedy strategy, this paper adds the mechanism of reverse correction thinking, transfers the local optimal solution to the global optimal solution, and puts forward a compound optimal greedy strategy integrating reverse correction thinking. Based on the actual application scenario of blood robot operating costs, the overall “simple greedy strategy model” is constructed and tested based on the greedy strategy as the main modeling basis according to the application needs. On this basis, the interaction relationship between local optimal solutions is deeply analyzed, and the reverse correction mechanism is integrated to optimize the system through the two steps of reverse allocation and reverse merge repair. Gradually improve the model to get the optimized “reverse modified greedy strategy model”, the algorithm can effectively reduce the operating cost. On this basis, in order to test the optimization effect, the effectiveness and stability of the reverse correction mechanism were verified by modifying some parameters of the application scene and randomly generating multiple arrays for re-test, etc., and new parameters were selected to re-run the application scene, and satisfactory verification results were obtained. Compared with other modeling ideas of the same topic, this model weakens the expression of the overall function and emphasizes the change relationship and action mechanism between data, and obtains better operation results. Greedy strategy is very conducive to the analysis of the relationship between requirements, constraints and variables. According to the actual application needs, combined with the mathematical analysis method, the reverse correction mechanism is added to the greedy strategy modeling. In the demand sequence test of 100 groups of simulation, the maximum saving rate can be close to 1.6%, while the lowest saving rate is less than 0.6%, and the average saving rate is 0.9677%. It can save tens of thousands of operating costs for application scenarios.