Detailed Programme

Evolutionary Algorithms in Energy Applications

Along with the worldwide incentive to reduce fossil and nuclear based power generation, the number of distributed generators and other forms of distributed energy resources which are installed in power networks has been steadily increasing over the last years. This increased integration has triggered a transformation of the energy system and challenges the conventional operation of these networks.

On a network level, this transformation requires new control and communication approaches, to guarantee the security of energy supplies as well as an optimal exploitation of available resources. On a generator level, advanced control strategies as well as morphological optimization (e.g., tuning of wind-blade design) can help to assure an optimal performance of the generator.

EvoEnergy is intended as a platform for new, innovative computational intelligence and nature-inspired techniques in the domain of energy-related optimization research. We seek contributions ranging from new control concepts for decentralized generation, strategies for their coordination in the network to the morphological optimization of distributed generators.

Topics of interest include, but are not limited to, any of the following:


Accepted papers will appear in the proceedings of EvoStar, published in a volume of the Springer Lecture Notes in Computer Science, which will be available at the Conference.Submissions must be original and not published elsewhere. The submissions will be peer reviewed by at least three members of the program committee. The authors of accepted papers will have to improve their paper on the basis of the reviewers comments and will be asked to send a camera ready version of their manuscripts. At least one author of each accepted work has to register for the conference and attend the conference and present the work.The reviewing process will be double-blind, please omit information about the authors in the submitted paper.

Submission Details

Submissions must be original and not published elsewhere. They will be peer reviewed by members of the program committee. The reviewing process will be double-blind, so please omit information about the authors in the submitted paper.

Submit your manuscript in Springer LNCS format.

Please provide up to five keywords in your Abstract

Page limit: 12 pages to http://myreview.csregistry.org/evoapps14/.


Submission deadline: 1 November 2013 11 November 2013
Notification: 06 January 2014
Camera ready: 01 February 2014
EvoENERGY: 23-25 April 2014


Further information on the conference and co-located events can be
found in: http://www.evostar.org

Programme Committee

EvoENERGY Programme

Thursday 24 April

Thurs 0930-1110  EvoENERGY 
Chair:  Paul Kaufmann

Customizable Energy Management in Smart Buildings using Evolutionary Algorithms     Florian Allerding, Ingo Mauser, Hartmut Schmeck
Various changes in energy production and consumption lead to new challenges for design and control mechanisms of the energy system. In particular, the intermittent nature of power generation from renewables asks for significantly increased load flexibility to support local balancing of energy demand and supply. This paper focuses on a flexible, generic energy management system for Smart Buildings in real-world applications, which is already in use in households and office buildings. The major contribution is the design of a "plug-and-play"-type Evolutionary Algorithm for optimizing distributed generation, storage and consumption using a sub-problem based approach. Relevant power consuming or producing components identify themselves as sub-problems by providing an abstract specification of their genotype, an evaluation function and a back transformation from an optimized genotype to specific control commands. The generic optimization respects technical constraints as well as external signals like variable energy tariffs. The relevance of this approach to energy optimization is evaluated in different scenarios. Results show significant improvements of self-consumption rates and reductions of energy costs.

Dynamic Programming Based Metaheuristic for Energy Planing Problems     Sophie Jacquin, Laetitia Jourdan, El-Ghazali Talbi
In this article, we propose DYNAMOP (DYNAmic program- ming using Metaheuristic for Optimization Problems) a new dynamic programming based on genetic algorithm to solve a hydro-scheduling problem. The representation which is based on a path in the graph of states of dynamic programming is adapted to dynamic structure of the problem and it allows to hybridize easily evolutionary algorithms with dynamic programming. DYNAMOP is tested on two case studies of hydro-scheduling problem with different price scenarios. Experiments indicate that the proposed approach performs considerably better than classical genetic algorithms and dynamic programming. Keywords : Genetic Algorithm, Dynamic Programming , Hybrid method, Hydro scheduling problem

Looking for Alternatives: Optimization of Energy Supply Systems without Superstructure     Mike Preuss, Philip Voll, André Bardow, Günter Rudolph
We investigate different evolutionary algorithm (EA) variants for structural optimization of energy supply systems and compare them with a deterministic optimization approach. The evolutionary algorithms enable structural optimization avoiding to use an underlying superstructure model. As result of the optimization, we are interested in multiple good alternative designs, instead of the one single best solution only. This problem has three levels: On the top level, we need to fix a structure; based on that structure, we then have to select facility sizes; finally, given the structure and equipment sizing, on the bottom level, the equipment operation has to be specified to satisfy given energy demands. In the presented optimization approach, these three levels are addressed simultaneously. We compare EAs acting on the top level (the lower levels are treated by a mixed-integer linear programming (MILP) solver) against an MILP-only-approach and are highly interested in the ability of both methods to deliver multiple different solutions and the time required for performing this task. Neither state-of-the-art EA for numerical optimization nor standard measures or visualizations are applicable to the problem. This lack of experience makes it difficult to understand why different EA variants perform as they do (e.g., for stating how different two structures are), we introduce a distance concept for structures. We therefore introduce a short code, and, based on this short code, a distance measure that is employed for a multidimensional scaling (MDS) based visualization. This is meant as first step towards a better understanding of the problem landscape. The algorithm comparison shows that deterministic optimization has advantages if we need to find the global optimum. In contrast, the presented EA variants reliably find multiple solutions very quickly if the required solution accuracy is relaxed. Furthermore, the proposed distance measure enables visualization revealing interesting problem properties.