Developmental Genetic Programming Research Articles

Total Cray Valley and Gevo to further scale up development of renewable isoamylene from fusel oil

Contemporary embedded systems work in changing environments, some features (e.g., execution time, power consumption) of the system are often not completely predictable. Therefore, for systems with strong constraints, a worst-case design is applied. We observed that by enabling the self-adaptivity we may obtain highly optimized systems still guaranteeing the high quality of service. This paper presents a method of synthesis of real-time software for self-adaptive multicore systems. The method assumes that the system specification is given as a task graph. Then, the tasks are scheduled on a multicore architecture consisting of low-power and high-performance cores. We apply the developmental genetic programming to generate the self-adaptive scheduler and the initial schedule. The initial schedule is optimized, taking into consideration the power consumption, the real-time constraints as well as the self-adaptivity. The scheduler modifies the schedule during the system execution, whenever execution time of the recently finished task occurs other than assumed during the initial scheduling. We propose two models of self-adaptivity: self-optimization of power consumption and self-adaptivity of real-time scheduling. We present some experimental results for standard benchmarks, showing the advantages of our method in comparison with the worst case design used in existing approaches.

Synthesis of self-adaptable energy aware software for heterogeneous multicore embedded systems

Contemporary embedded systems work in changing environments, some features (e.g., execution time, power consumption) of the system are often not completely predictable. Therefore, for systems with strong constraints, a worst-case design is applied. We observed that by enabling the self-adaptivity we may obtain highly optimized systems still guaranteeing the high quality of service. This paper presents a method of synthesis of real-time software for self-adaptive multicore systems. The method assumes that the system specification is given as a task graph. Then, the tasks are scheduled on a multicore architecture consisting of low-power and high-performance cores. We apply the developmental genetic programming to generate the self-adaptive scheduler and the initial schedule. The initial schedule is optimized, taking into consideration the power consumption, the real-time constraints as well as the self-adaptivity. The scheduler modifies the schedule during the system execution, whenever execution time of the recently finished task occurs other than assumed during the initial scheduling. We propose two models of self-adaptivity: self-optimization of power consumption and self-adaptivity of real-time scheduling. We present some experimental results for standard benchmarks, showing the advantages of our method in comparison with the worst case design used in existing approaches.

Speeding up global optimization with the help of intelligent supervisors

It is shown in the paper that Developmental Genetic Programming is an efficient tool for evolutionary development of intelligent supervisors that solve an extension of Resource-Constrained Project Scheduling Problem. The extension assumes that resources are only partially available. It also assumes that renewable resources affect the project cost. The cost should be as low as possible and a deadline of the project must be met. This is apparent with regard to software houses and building enterprises. Computational experiments showed that supervisors find solutions of the problem much faster than other genetic approaches. A specific property of the supervisor is that it has various strategies of allocating the resources to the tasks. The supervisor uses the strategies in order to develop a procedure for producing the best schedule for the whole project. The analysis of the evolutionary process was performed and experimental results were compared with the optimal ones obtained by means of the exhaustive search method.

Practical and scalable evolution of digital circuits

This paper addresses the scalability problem prevalent in the evolutionary design of digital circuits and shows that Evolvable Hardware (EHW) can indeed be considered as a viable alternative design methodology for large and complex circuits. Despite the effort by the EHW community to overcome the scalability problems using both direct mapped techniques and developmental approaches, so far only small circuits have been evolved. This paper shows that, by partitioning a digital circuit and making use of a modular developmental approach, namely, the Modular Developmental Cartesian Genetic Programming (MDCGP) technique, it is indeed possible to evolve large circuits. As a proof of concept, a 5 × 5 multiplier is evolved for partition sizes of 32 and 64. It is shown that compared to the direct evolution technique, the MDCGP technique provides five times reduction in terms of evolution times, 6–56% reduction in area and improved fault tolerance. The technique is readily scalable and can be applied to even larger partition sizes, and also to sequential circuits, thus providing a promising path to evolve large and complex circuits.

Machine invention of quantum computing circuits by means of genetic programming

AbstractWe demonstrate the use of genetic programming in the automatic invention of quantum computing circuits that solve problems of potential theoretical and practical significance. We outline a developmental genetic programming scheme for such applications; in this scheme the evolved programs, when executed, build quantum circuits and the resulting quantum circuits are then tested for “fitness” using a quantum computer simulator. Using the PushGP genetic programming system and the QGAME quantum computer simulator we demonstrate the invention of a new, better than classical quantum circuit for the two-oracle AND/OR problem.

Introducing probabilistic adaptive mapping developmental genetic programming with redundant mappings

Developmental Genetic Programming (DGP) algorithms have explicitly required the search space for a problem to be divided into genotypes and corresponding phenotypes. The two search spaces are often connected with a genotype-phenotype mapping (GPM) intended to model the biological genetic code, where current implementations of this concept involve evolution of the mappings along with evolution of the genotype solutions. This work presents the Probabilistic Adaptive Mapping DGP (PAM DGP), a new developmental implementation that involves research contributions in the areas of GPMs and coevolution. The algorithm component of PAM DGP is demonstrated to overcome coevolutionary performance problems that are identified and empirically benchmarked against the latest competing algorithm that adapts similar GPMs. An adaptive redundant mapping encoding is then incorporated into PAM DGP for further performance enhancement. PAM DGP with two mapping types are compared to the competing Adaptive Mapping algorithm and Traditional GP in two medical classification domains, where PAM DGP with redundant encodings is found to provide superior fitness performance over the other algorithms through it's ability to explicitly decrease the size of the function set during evolution.