Call for Competition on Evolutionary Computation in the Energy Domain: Operation and Planning Applications

GECCO 2023 & IEEE CEC 2023 (Joint competition)

1-5 July – Chicago, USA (CEC 2023) | 15-19 July – Lisbon, Portugal (GECCO 2023)

Organized by ISEP and UNESP

ISEP: Fernando Lezama, João Soares, José Almeida, Bruno Canizes, Zita Vale

UNESP: Leonardo H. Macedo, Gabriel Puerta, Ruben Romero

Competition Outline

Following the success of the previous editions at IEEE PES-GM, CEC, GECCO, and WCCI, we are launching another challenging edition of the competition at major conferences in the field of computational intelligence and power systems. This GECCO 2023 competition proposes two tracks in the energy domain:

Track 1) Risk-based optimization of aggregators’ day-ahead energy resource management (ERM) considering the uncertainty of high penetration of distributed energy resources (DER). This testbed represents a centralized day-ahead ERM in a smart grid with a 13-bus distribution network using a 15-scenario case study with 3 scenarios considering extreme events (high impact and low probability). A conditional value-at-risk (CVaR) mechanism is used to measure the risk associated with extreme events for a confidence level (α) of 95%. We also add some restrictions to the initialization of solutions and allowed repairs and tweak-heuristics.

Track 2) Transmission Network Expansion Planning: Long-term transmission network expansion planning (TNEP) is a classic problem in power systems. The objective is to find the optimal expansion plan that identifies the transmission lines that must be installed in the system to allow a proper operation within a predefined planning horizon with the lowest investment cost. The optimal expansion plan should define where and how many lines should be installed. A nonconvex mixed-integer nonlinear programming formulation is used to model the problem. The Northeast Brazilian transmission system is considered a case study. Note: Both tracks are developed under the same framework as past competitions.

Competition goals

The competition has been held since 2017 at major conferences (the first competition was launched at IEEE PES GM) – Website:

Using the same framework, we have implemented several benchmark problems over the years. This year, we are keeping the 2022 track related to energy resource management considering risk measurement tools (a more recent problem in the energy domain) and also including a second track related to the planning of transmission systems.


– Participants will propose and implement metaheuristic algorithms (e.g., evolutionary algorithms, swarm intelligence, estimation of distribution algorithms, etc.) to solve any of the two-track problems in the energy domain. It will be considered independent entries for each track, i.e., two independent tracks.

– The organizers provide a framework (Download codes), implemented in MATALAB© 2018a 64 bits, in which participants can easily test their algorithms (we also provide a differential evolution algorithm implementation as an example). The guidelines (Download) include the necessary information to understand the problems, how the solutions are represented, and how the fitness function is evaluated. Those elements are common for all participants.

– Because the proposed algorithms may have different population sizes and run for a variable number of iterations, each trial allows a maximum number of “function evaluations”, namely 5000 for track 1 and 20,000 for track 2. The convergence properties of the algorithms are not a qualification criterion for this competition.

– 20 independent trials should be performed in the framework by each participant.

How to submit an entry

– The winner will be the participant with the minimum ranking index in each independent track, calculated as the average value over the 20 trials of the expected fitness value plus the standard deviation. We will make an independent rank for each track (i.e., we will have a winner for each track).

– Each participant is kindly requested to put the text files corresponding to the final results (see guideline document), as well as the implementation files (codes), obtained by using a specific optimizer, into a zipped folder named (e.g.,

The zipped folder must be summited to;,
by 30 June 2023 (anywhere on Earth)

Important Remarks

– Notice that submission of papers or assistance to CEC and GECCO by competition participants is not mandatory.

– You can submit a paper to the special session on Evolutionary Algorithms for Complex Optimization in the Energy Domain (CEC). Submit it here – select the SS name “Evolutionary Algorithms for Complex Optimization in the Energy Domain” as the primary subject area.

– You are also welcome to submit short descriptions of your algorithms and results as 2-page papers to be included in the GECCO Companion. This is voluntary — The submission deadline is April 2023. Submit it here (Competition Entry Submissions)


We are glad to announce that our competition will offer an IEEE Computational Intelligence Society (CIS) prize of 500 $ for the participant with the best normalized average rank of the two tracks. Also, an honorable mention will be given to the winner of each track. Good luck, and stay tuned. Thanks!

Submit your results by June 1 June 30th (extended) 2023 (anywhere on earth)

Further related bibliography

  • [1] F., Lezama, J. Soares, Z. Vale, J. Rueda, S. Rivera, & I. Elrich, 2017 IEEE Competition on modern heuristic optimizers for smart grid operation: Testbeds and results. Swarm and evolutionary computation, 44, 420-427, 2019
  • [2] F. Lezama, J. Soares, P. Hernandez-Leal, M. Kaisers, T. Pinto, and Z. Vale, Local Energy Markets: Paving the Path Towards Fully Transactive Energy Systems, IEEE Transaction on Power Systems, IEEE (2018).
  • [3] Joao Soares, Bruno Canizes, M. A. Fotouhi Gazvhini, Zita Vale, and G. K. Venayagamoorthy, “Two-stage Stochastic Model using Benders’ Decomposition for Large-scale Energy Resources Management in Smart grids,” IEEE Transactions on Industry Applications, 2017.
  • [4] F. Lezama, J. Soares, E. Munoz de Cote, L. E. Sucar, and Z. Vale, “Differential Evolution Strategies for Large-Scale Energy Resource Management in Smart Grids,” in GECCO ’17: Genetic and Evolutionary Computation Conference Companion Proceedings, 2017. 
  • [5] Joao Soares, Mohammad Ali Fotouhi Ghazvini, Marco Silva, Zita Vale, “Multi-dimensional signaling method for population-based metaheuristics: Solving the large-scale scheduling problem in smart grids”, Swarm and Evolutionary Computation, 2016.
  • [6] Joao Soares, Hugo Morais, Tiago Sousa, Zita Vale, Pedro Faria, “Day-ahead resource scheduling including demand response for electric vehicles”, IEEE Transactions on Smart Grid 4 (1), 596-605, 2013.
  • [7] F. Lezama, J. Soares, B. Canizes, Z. Vale, Z., Flexibility management model of home appliances to support DSO requests in smart grids. Sustainable Cities and Society, 55, 102048, 2020.


Logos 2021