MO-NILM: A multi-objective evolutionary algorithm for NILM

MO-NILM: A multi-objective evolutionary algorithm for NILM classification

MO-NILM source code based on [1].

Some remarks:
1) This setup is used for Scenario 3 :MO-NILM2 (P, Q) in the article. you can use here 2 features ( in our case it is P,Q , but you can change it).
2) The code is based on PlatEMO, which is an open source MATLAB-based platform for evolutionary multi-objective optimization problems. If you use this code, you will have to cite PlatEMO [2].
3) In order to run the code you need to be in the '\AmpdsPQ' folder and run 'main_Ampds.m'.
4) in the function 'NSGAII_sim_Ampds.m' you will need to insert add_path (line 15) to the path of where the mainNsgaII_PQ.m is found ( should be 1 upper-folder)
5) The DATABASE is found in '\AmpdsPQ\36kSamplesDb'. With some review and reverse engineering you will be able to change it for your own DB. For each Mat file- first col is feature1(P), second col is feature2 (Q).

[1] Machlev, R., Belikov, J., Beck, Y., & Levron, Y. (2019). MO-NILM: A multi-objective evolutionary algorithm for NILM classification. Energy and Buildings, 199, 134-144.‏
[2] Tian, Y., Cheng, R., Zhang, X., & Jin, Y. (2017). PlatEMO: A MATLAB platform for evolutionary multi-objective optimization [educational forum]. IEEE Computational Intelligence Magazine, 12(4), 73-87.‏