Akhilesh Yadav
ABSTRACT
Within the present research study, a comparative evaluation of two different approaches for the development of a deep learning-based algorithm for the targeted detection of four selected electricity appliances in dairy farms is presented and discussed. Via a multilayer deep neural network based on the sequence-to-sequence (S2S) methodology, the algorithm allows to identify the state of the appliances according to the device-specific power signature by reading the daily load profile for the total power consumption. According to preliminary results, the multi-layer One-Directional Convolution Layer-Bidirectional GRU Recurrent Neural Network (1DConv-BRNN) model showed better performance, compared to a Long Short-Term Memory (LSTM)-based deep neural networks.
- Michael Kelly. 2018. Germany moving ahead with smart meter rollout plans (2018). Retrieved May 20, 2020 from https://www.smart-energy.com/magazine-article/germany-moving-ahead-smart-meter-rollout-plans/.Google Scholar
- Bundesministeriums für Wirtschaft und Energie. 2018. Barometer Digitalisierung der Energiewende (2018). Ein neues Denken und Handeln für die Digitalisierung der Energiewende. Bundesministeriums für Wirtschaft und Energie.Google Scholar
- Padraig Scully. 2019. Smart Meter Market Report 2019-2024. IOT Analytics.Google Scholar
- Oliver Parson, Grant Fisher, April Hersey, Nipun Batra, Jack Kelly, Amarjeet Singh, William Knottenbelt, and Alex Rogers. 2015. Dataport and NILMTK: A building data set designed for non-intrusive load monitoring. IEEE Global Conference on Signal and Information Processing (GlobalSIP). IEEE, 210--214. DOI: https://doi.org/10.1109/GlobalSIP.2015.7418187.Google ScholarCross Ref
- Jack Daniel Kelly. 2017. Disaggregation of Domestic Smart Meter Energy Data. Ph.D. Dissertation. University of London, University of London Imperial College of Science, Technology and Medicine Department of Computing.Google Scholar
- Dr. Stefan. Neser, Josef Neiber, Josef Niedermeier, Manfred Götz, Ludwig Kraus, and Prof. K.-H. Pettinger. 2014. Energieverbrauch im Milchviehbetrieb - Effizienz und Einsparpotential. Retrieved August 22, 2020 from https://www.lfl.bayern.de/publikationen/informationen/065687/index.php.Google Scholar
- Kunjin Chen, Qin Wang, Ziyu He, Kunlong Chen, Jun Hu, and Jinliang He. 2018. Convolutional sequence to sequence non-intrusive load monitoring. In the Journal of Engineering, 17, 1860--1864. DOI: https://doi.org/10.1049/joe.2018.8352.Google ScholarCross Ref
- Maria Kaselimi, Eftychios Protopapadakis, Athanasios Voulodimos, Nikolaos Doulamis, and Anastasios Doulamis. 2019. Multi-Channel Recurrent Convolutional Neural Networks for Energy Disaggregation. In IEEE Access 7, 81047--81056. DOI: https://doi.org/10.1109/ACCESS.2019.2923742.Google Scholar
- Jack Kelly and William Knottenbelt. 2015. Neural NILM: Deep Neural Networks Applied to Energy Disaggregation. In Proceedings of the 2nd ACM International Conference on Embedded Systems for Energy-Efficient Built Environments (BuildSys '15). Association for Computing Machinery, New York, NY, USA, 55--64. DOI: https://doi.org/10.1145/2821650.2821672Google ScholarDigital Library
- Jack Kelly and William Knottenbelt. 2015. The UK-DALE dataset, domestic appliance-level electricity demand and whole-house demand from five UK homes. In Scientific data 2, 150007 (2015). DOI: https://doi.org/10.1038/sdata.2015.7.Google ScholarCross Ref
- Pedro P. M. d. Nascimento, 2016. Applications of deep learning techniques on NILM. M.Sc. UFRJ: Universidade Federal do Rio de Janeiro, Brazil.Google Scholar
- Max A. Bramer, 2007. Principles of Data Mining. Springer, London.Google Scholar
Index Terms
- NILM based Energy Disaggregation Algorithm for Dairy Farms
Recommendations
Neural NILM: Deep Neural Networks Applied to Energy Disaggregation
BuildSys '15: Proceedings of the 2nd ACM International Conference on Embedded Systems for Energy-Efficient Built EnvironmentsEnergy disaggregation estimates appliance-by-appliance electricity consumption from a single meter that measures the whole home's electricity demand. Recently, deep neural networks have driven remarkable improvements in classification performance in ...
UNet-NILM: A Deep Neural Network for Multi-tasks Appliances State Detection and Power Estimation in NILM
NILM'20: Proceedings of the 5th International Workshop on Non-Intrusive Load MonitoringOver the years, an enormous amount of research has been exploring Deep Neural Networks (DNN), particularly Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) for estimating the energy consumption of appliances from a single point ...
Sliding Window Approach for Online Energy Disaggregation Using Artificial Neural Networks
SETN '18: Proceedings of the 10th Hellenic Conference on Artificial IntelligenceEnergy disaggregation is the process of extracting the power consumptions of multiple appliances from the total consumption signal of a building. Artificial Neural Networks (ANN) have been very popular for this task in the last decade. In this paper we ...
Comments