TY - CHAP A1 - Lang, Christian A1 - Steinborn, Florian A1 - Steffens, Oliver A1 - Lang, Elmar Wolfgang T1 - Electricity Load Forecasting - An Evaluation of Simple 1D-CNN Network Structures T2 - International Conference on Time Series and Forecasting (ITISE 2019), Proceedings of Papers Vol. 2, 25-27 September 2019, Granada (Spain) N2 - This paper presents a convolutional neural network (CNN)which can be used for forecasting electricity load profiles 36 hours intothe future. In contrast to well established CNN architectures, the inputdata is one-dimensional. A parameter scanning of network parameters isconducted in order to gain information about the influence of the kernelsize, number of filters, and dense size. The results show that a goodforecast quality can already be achieved with basic CNN architectures.The method works not only for smooth sum loads of many hundredconsumers, but also for the load of apartment buildings KW - energy load forecasting KW - STLF KW - neural networks KW - CNN KW - con-volutional networks Y1 - 2019 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:898-opus4-16649 UR - https://arxiv.org/abs/1911.11536 UR - http://itise.ugr.es/ITISE2019_vol2.pdf SN - 978-84-17970-78-9 SP - 797 EP - 806 ER - TY - CHAP A1 - Lang, Christian A1 - Steinborn, Florian A1 - Steffens, Oliver A1 - Lang, Elmar Wolfgang ED - Valenzuela, O. ED - Rojas, F. ED - Herrera, L.J. ED - Pomares, H. ED - Rojas, I. T1 - Applying a 1D-CNN Network to Electricity Load Forecasting T2 - Theory and Applications of Time Series Analysis N2 - This paper presents a convolutional neural network (CNN) which can be used for forecasting electricity load profiles 36 hours into the future. In contrast to well established CNN architectures, the input data is one-dimensional. A parameter scanning of network parameters is conducted in order to gain information about the influence of the kernel size, number of filters and number of nodes. Furthermore, different dropout methods are applied to the CNN and are evaluated. The results show that a good forecast quality can already be achieved with basic CNN architectures, the dropout improves the forecast. The method works not only for smooth sum loads of many hundred consumers, but also for the load of single apartment buildings. KW - Energy load forecasting KW - STLF KW - Neural networks KW - CNN KW - Convolutional networks Y1 - 2020 U6 - https://doi.org/10.1007/978-3-030-56219-9_14 SP - 205 EP - 218 PB - Springer ER -