Fuzzy inductive reasoning forecasting strategies able to cope with missing data: A smart grid application

Abstract

Dealing with missing data is of great practical and theoretical interest in forecasting applications. In this study, we deal with the problem of forecasting with missing data in smart grid and smart home applications, where the information from home area sensors and/or smart meters is sometimes missing, which may hinder or even prevent the forecasting of the next hours and days. In concrete, we focus in a Soft Computing technique called Fuzzy Inductive Reasoning (FIR) and its improved version that can cope with missing information in the forecasting process: flexible FIR. In this article eight different strategies for flexible FIR forecasting are defined and studied taking into account: causal relevance of input variables, consistency of predictions, inertia criterion and K-Nearest Neighbours. Furthermore, we evaluate the implications of prediction accuracy and number of registers predicted, when the number of Missing Values (MVs) in the training dataset is increased progressively. To this end, a real smart grid forecasting application, i.e. electricity load forecasting, has been chosen in this study. The results show that all eight strategies proposed are able to cope with MVs and take advantage of the inherent information in the data, with better results in those strategies making use of causal relevance. In addition, the robustness of flexible FIR and its eight strategies are proved taking into account that the percentage of registers predicted is on average 96.15% when the %MVs in training dataset was around 73%.

K Nearest Neighbour Optimal Selection in Fuzzy Inductive Reasoning for Smart Grid Applications

“…Recently, an improved version of Standard FIR called Flexible FIR Prediction has been demonstrated [15], which can cope with missing information in the input pattern as well as learn from instances with missing values in the behaviour matrix. An extended study of this improved version of FIR can be found in [16]. Moreover, comparisons of Standard, Flexible FIR and other statistical and AI techniques have been performed in [8][9] [15].…”

“…Similarly to [16], data of 3 buildings of the Universitat Politècnica de Catalunya (UPC) was obtained for this study, in order to have a training/test sample with high diversity of consumptions. They have different profiles of usage (teaching, library and administration building), belong to three different campuses and are located in different cities.…”

“…As it is explained in [16], the selection of the depth and number of variables is a crucial issue that can affect those methods that are more sensitive to the curse of dimensionality. It has been empirically determined, for electrical load consumption applications, that more than four variables and depths higher than 72 hours, do not increase significantly the quality of the FSP of FIR, whereas computational cost (in terms of time) does exponentially [15].…”

Recent Fuzzy Generalisations of Rough Sets Theory: A Systematic Review and Methodological Critique of the Literature

“…Before the data can be used to build the classification model and to classify the new instances, the data needs to be preprocessed. For example, there can be missing values [278][279][280][281] in the data that need to be imputed. Preprocessing can also be used to speed up or improve the classification process.…”

Processing missing power data in wireless sensor networks

“…In the power system test or the specific production operation, an obstruction may cause a temporary disconnection of the link, or data packet dropout in the process of data transmission [18]. For example, when the node capacity is exhausted, nodes cannot capture the power data and the data stored in the node cannot return in a timely manner.…”