Here are introductions, articles, Matlab-codes, and documentations of Prediction Evolution Algorithm.
The grey prediction evolution algorithm (GPE) [3] proposed by Zhongbo Hu et.al (2020) is a stochastic optimization algorithm with strong exploration capability. The algorithm considers the population sequence of evolutionary algorithms as a time series, and then uses the grey model (GM(1,1)) to predict offspring individuals. So far, the relevant researches are mainly carried out from the following aspects: (I) Employ different grey prediction models to construct other versions of GPEs, such as grey prediction evolution algorithm based on even difference grey model (GPEed)[1], multivariable grey prediction evolution algorithm (MGPE)[4], and grey prediction evolution algorithm based on accelerated even grey model (GPEae)[7]. (II) Introduce evolutionary strategies to improve GPEs, such as grey prediction evolution algorithm based on topological opposition-based learning (TOGPE) [5] and non-equidistant grey prediction evolution algorithm (NeGPE) [9,11]. (III) Construct adaptive GPE algorithms [10]. (IV) Apply GPEs to solve particular application problems, such as multiobjective grey prediction evolution algorithm for environmental/economic dispatch problem (MOGPE) [6], multimodal multiobjective optimization (MMGPE)[2], automated test case generation for path coverage (GPE-IS) [8], community group buying [12] and unit commitment problem [13]. The GPE algorithms are the first kind of prediction-based evolution algorithms.
[1] Zhongbo Hu*, Cong Gao, Qinghua Su. A Novel Evolutionary Algorithm Based on Even Difference Grey Model, Expert Systems with Applications, 2021, 176, 114898. https://doi.org/10.1016/j.eswa.2021.114898. Corresponding Mat.Code: GPEAed-matlab
[2] Ting Zhou, Zhongbo Hu*, Quan Zhou, Shixiong Yuan. A novel grey prediction evolution algorithm for multimodal multiobjective optimization, Engineering Applications of Artificial Intelligence, 2021, 104173. https://doi.org/10.1016/j.engappai.2021.104173. Corresponding Mat.Code: GPEfMMO-matlab.
[3] Zhongbo Hu*, Xinlin Xu, Qinghua Su, et.al. Grey prediction evolution algorithm for global optimization, Applied Mathematical Modelling, 2020, 79, 145โ160. https://doi.org/10.1016/j.apm.2019.10.026. Corresponding Mat.Code: GPA(1,1)-matlab.
[4] Xinlin Xu, Zhongbo Hu*, Qinghua Su, et.al. Multivariable grey prediction evolution algorithm: A new metaheuristic, Applied Soft Computing, 2020, 89, 106086. https://doi.org/10.1016/j.asoc.2020.106086. Corresponding Mat.Code: MGPA_CEC_matlab.
[5] Canyun Dai, Zhongbo Hu*, Zheng Li, et.al. An improved grey prediction evolution algorithm based on Topological Opposition-based learning, IEEE Access, vol. 8, pp. 30745-30762, 2020. https://doi.org/10.1109/ACCESS.2020.2973197.
[6] Zhongbo Hu*, Zheng Li, Canyun Dai, et.al. Multiobjective grey prediction evolution algorithm for environmental/economic dispatch problem, IEEE Access, vol. 8, pp. 84162-84176, 2020. https://doi.org/10.1109/ACCESS.2020.2992116. Corresponding Mat.Code: MOGPEA_Matlab.
[7] Gao Cong, Zhongbo Hu*, Zenggang Xiong, Qinghua Su. Grey Prediction Evolution Algorithm Based on Accelerated Even Grey Model, IEEE Access, vol. 8, pp. 107941-107957, 2020. https://doi.org/10.1109/ACCESS.2020.3001194. Corresponding Mat.Code: GPEae-matlab.
[8] Gaocheng Cai, Qinghua Su*, Zhongbo Hu. Automated test case generation for path coverage by using grey prediction evolution algorithm with improved scatter search strategy, Engineering Application of Artificial Intelligence, 2021, 106, 104454. https://doi.org/10.1016/j.engappai.2021.104454 . Corresponding Jav.Code: GPEfPC.
[9] Xiyang Xiang, Qinghua Su*, Gang Huang, Zhongbo Hu. A simplified non-equidistant grey prediction evolution algorithm for global optimization, Applied Soft Computing, 2022, 125, 109081. https://doi.org/10.1016/j.asoc.2022.109081. Corresponding Mat. Code: NeGPE_CEC_matlab.
[10] Cong Gao, Zhongbo Hu*, Yongfei Miao, Xiaowei Zhang, Qinghua Su. Four adaptive grey prediction evolution algorithms with different types of parameters setting techniques. Soft Computing, 2022, 7. https://doi.org/10.1007/s00500-022-07228-z. Corresponding Mat. Code: aGPE_matlab.
[11] Xiyang Xiang, Qinghua Su*, Zhongbo. Non-equidistant grey prediction evolution algorithm: A mathematical model-based meta-heuristic technique. Swarm and Evolutionary Computation. 2023, 10.1016/j/swevo.2023.101276. Corresponding Mat. Code: NonGPE_CEC2019.
[12] Huimin Zhu, Xinping Xiao, Yuxiao Kang, Dekai Kong. Lead-lag grey forecasting model in the new community group buying retailing. Chaos, Solitons & Fractals, Volume 158, 2022, 112024. https://doi.org/10.1016/j.chaos.2022.112024. (Wuhan University of Technology)
[13] Wangyu Tong, Di Liu, Zhongbo Hu, Qinghua Su. Hybridizing genetic algorithm with grey prediction evolution algorithm for solving nunit commitment problem. 2023, Applied Intelligence, Accept. (Hubei University of Technology)
The linear prediction evolution algorithm (LPE)[1] proposed by Cong Gao, et.al (2021) regards the population series of evolutionary algorithms as a time series and uses a line expression generated by the linear least square fitting model to update individuals of each population.
[1] Cong Gao, Zhongbo Hu*, Wangyu Tong. Linear prediction evolution algorithm: a simplest evolutionary optimizer, Memetic Computing, 2021, 13, 319โ339. https://doi.org/10.1007/s12293-021-00340-x. Corresponding Mat.Code: LPE_matlab.