Societal Implicit Memory and his Speed on Tracking Extrema in Dynamic
Environments using Self-Regulatory Swarms,
final draft submitted to Journal of Systems Architecture, Special issue on
Nature Inspired Applied Systems, Elsevier, 2006.
Authors: Vitorino Ramos, Carlos Fernandes, Agostinho C. Rosa.

http://alfa.ist.utl.pt/~cvrm/staff/vramos/Vramos-NIAS06.pdf

Abstract: In order to overcome difficult dynamic optimization and
environment extrema tracking problems, we propose a Self-Regulated Swarm
(SRS) algorithm which hybridizes the advantageous characteristics of Swarm
Intelligence as the emergence of a societal environmental memory or
cognitive map via collective pheromone laying in the landscape (properly
balancing the exploration/exploitation nature of the search strategy), with
a simple Evolutionary mechanism that through a direct reproduction
procedure linked to local environmental features is able to self-regulate
the above exploratory swarm population, speeding it up globally. In order
to test his adaptive response and robustness, we have recurred to different
dynamic multimodal complex functions as well as to Dynamic Optimization
Control (DOC) problems. Measures were made for different dynamic settings
and parameters such as, environmental upgrade frequencies, landscape
changing speed severity, type of dynamic (linear or circular), and to
dramatic changes on the algorithmic search purpose over each test
environment (e.g. shifting the extrema). Finally, comparisons were made
with traditional Genetic Algorithms (GA), Bacterial foraging algorithms
(BFOA), as well as with more recent Co-Evolutionary approaches. SRS, were
able to demonstrate quick adaptive responses, while outperforming the
results obtained by the other approaches. Additionally, some successful
behaviors were found: SRS was able not only to achieve quick adaptive
responses, as to maintaining a number of different solutions, while
adapting to new unforeseen extrema; the possibility to spontaneously create
and maintain different subpopulations on different peaks, emerging
different exploratory corridors with intelligent path planning
capabilities; the ability to request for new agents over dramatic changing
periods, and economizing those foraging resources over periods of
stabilization. Finally, results prove that the present SRS collective swarm
of bio-inspired agents is able to track about 65% of moving peaks traveling
up to ten times faster than the velocity of a single ant composing that
precise swarm tracking system. This emerged behavior is probably one of the
most interesting ones achieved by the present work.

~ v. ramos [http://alfa.ist.utl.pt/~cvrm/staff/vramos/]