Method and system for generating multiple configurations for a solar power system

摘要

A configuration engine traverses sequential levels of a decision tree in order to iteratively refine a configuration for a solar power system. At each level of the decision tree, the configuration engine determines the outcome of a design decision based on computing the result of a value function. The configuration engine explores configurations that optimize the value function result compared to other configurations, and may also discard less optimal configurations. When a current configuration is considered less optimal than a previous configuration generated at a previous level, the configuration engine discards the current configuration and re-traverses the decision tree starting with the previous configuration.

主权项

1. A computer-implemented method for generating a solar power system configuration by traversing a decision tree that includes a sequence of levels, each level in the sequence of levels corresponding to a different design decision associated with the solar power system, the method comprising:
receiving via a communication path communicatively coupled to a computer system, site data that describes constraints associated with a target installation location for a solar power system; generating a processor of the computer system, an initial solar power system configuration based on the site data; generating the processor, the solar power system configuration by refining the initial solar power system configuration at each level in the sequence of levels while traversing the decision tree, wherein refining the initial solar power system configuration at a given level in the sequence of levels comprises determining an outcome to a design decision that is associated with the solar power system and corresponds to the given level by computing the result of a value function; generating the processor, N candidate solar power system configurations within a first level of the decision tree based on the initial solar power system configuration, wherein each of the N candidate solar power system configurations reflects a different outcome to a design decision that is associated with the solar power system and corresponds to the first level of the solar power system; computing using the processor, a value function result for each of the N candidate solar power system configurations; selecting using the processor, a first candidate solar power system configuration from the N candidate solar power system configurations by determining that a value function result associated with the first candidate solar power system configuration exceeds value function results associated with other candidate solar power system configurations in the N candidate solar power system configurations; generating using the processor, M candidate solar power system configurations within a second level of the decision tree based on the first candidate solar power system configuration, wherein each of the M candidate solar power system configurations reflects a different outcome to a design decision that is associated with the solar power system and corresponds to the second level of the solar power system; computing using the processor, a value function result for each of the M candidate solar power system configurations; and selecting using the processor, a second candidate solar power system configuration from the M candidate solar power system configurations by determining that a value function result associated with the second candidate solar power system configuration exceeds value function results associated with other candidate solar power system configurations in the M candidate solar power system configurations.