Summary
Finding the best solutions to complex problems often involves trying many options and learning from what works or doesn’t. The authors propose a new optimization method called CMDO that remembers the context in which search attempts succeed or fail and uses this memory to decide how to search next. Unlike prior methods, CMDO organizes experience in different types of memory and uses both positive and negative lessons to guide behavior. Tests show that this approach can lead to competitive or better results on standard optimization challenges and real data from solar panel modeling. The memory-driven search method changes how search tries are distributed and helps avoid repeating mistakes.
What this means in practice
- •For optimization engineers: Optimize complex engineering models by using past search context and outcomes to guide adaptive search strategies effectively.
- •For renewable energy technicians: Estimate photovoltaic system parameters more accurately from measured data using the new memory-based optimization approach.
Abstract
Population-based optimization methods often use previous search information through successful solutions, parameter adaptation, or operator performance, but they rarely retain the context in which a search behavior succeeded or failed. We introduce Cognitive Memory-Driven Optimization (CMDO), a derivative-free population-based optimizer that represents experience as the relationship between search context, search behavior, and observed outcome. CMDO organizes these experiences across working, episodic, and consolidated memory, retrieves them according to similarity with the current search state, and uses both positive and negative evidence to guide subsequent search. Retrieved experience does not replay previous candidate locations; instead, it selects search recipes that are reconstructed from the current population through exploratory, directed, and local search behaviors with adaptive search geometry. We evaluate CMDO on selected Blackbox Optimization Benchmarking test suite on COCO (BBOB/COCO) and Congress on Evolutionary Computation 2017 (CEC2017) problems against DE, CMA-ES, SHADE, GWO, HHO, and ORCA, and further study its application to seven-parameter photovoltaic model estimation using measured current--voltage data. The results show problem-dependent but competitive optimization performance, including the lowest median error among the compared methods on CEC2017 F10. More importantly, analysis of the search traces shows that context-dependent recall changes the distribution of executed search behaviors, while unsuccessful experiences remain available as negative evidence for later decisions, showing that accumulated experience directly influences subsequent search behavior. These results support the use of explicit context--behavior--outcome memory as an active mechanism for controlling population-based search.