MURAL - Maynooth University Research Archive Library

    24-Hour Electrical Load Data - A Time Series or a Set of Independent Points?

    Fay, Damien and Ringwood, John and Condon, Marissa and Kelly, Michael (2001) 24-Hour Electrical Load Data - A Time Series or a Set of Independent Points? In: Proceedings of the 7th International Conference on Engineering Applications of Neural Networks (EANN 2001), July 16-18 2001, Cagliari, Sardinia.

    [img] Download (395kB)

    Share your research

    Twitter Facebook LinkedIn GooglePlus Email more...

    Add this article to your Mendeley library


    The paper investigates whether a time series or a set of independent points is a more appropriate description of 24-hour Irish electrical load data. A set of independent points means that the load at each hour of the day is independent from the load at any other hour. The data is first split into 24 series, one for each hour of the day i.e. a 1am 2am 3am series etc. These are called parallel series. The linear cross-correlation's of the parallel series are used to indicate independence. While the loads at 9am and 6pm to 8pm appear independent the remaining loads are highly inter-correlated. This suggests that 24-hour electrical load data has a dual nature. Two techniques are used to test this hypothesis. The first technique models each parallel series using neural networks. This technique is found to be computationally expensive. The second technique uses a hybrid technique called the Multi Time Scale (MTS) technique. This models 24-hour electrical load data as a time series that can be adjusted by 5 parallel forecasts and a daily cumulative model. The results show that the MTS forecasts are superior to the parallel forecasts except for 9am and 6pm to 8pm. A composite model using neural networks for 9am and 6pm to 8pm and the MTS model elsewhere takes advantage of the dual nature of the data reducing error and computational expense.

    Item Type: Conference or Workshop Item (Paper)
    Keywords: Forecasting; electricity demand; time series; neural networks; principal component analysis; electrical load data;
    Academic Unit: Faculty of Science and Engineering > Electronic Engineering
    Item ID: 1967
    Depositing User: Professor John Ringwood
    Date Deposited: 01 Jun 2010 15:15
    Refereed: Yes
      Use Licence: This item is available under a Creative Commons Attribution Non Commercial Share Alike Licence (CC BY-NC-SA). Details of this licence are available here

      Repository Staff Only(login required)

      View Item Item control page


      Downloads per month over past year

      Origin of downloads