Search

Summarization: Reliable, non-intrusive, short-term (of up to 12 h ahead) prediction of a building's energy demand is a critical component of intelligent energy management applications. A number of such approaches have been proposed over time, utilizing various statistical and, more recently, machine learning techniques, such as decision trees, neural networks and support vector machines. Importantly, all of these works barely outperform simple seasonal auto-regressive integrated moving average models, while their complexity is significantly higher. In this work, we propose a novel low-complexity non-intrusive approach that improves the predictive accuracy of the state-of-the-art by up to ∼10%. The backbone of our approach is a K-nearest neighbours search method, that exploits the demand pattern of the most similar historical days, and incorporates appropriate time-series pre-processing and easing. In the context of this work, we evaluate our approach against state-of-the-art methods and provide insights on their performance. Presented on: Advances in Building Energy Research

The magnitude of soil settlement depends on several variables such as the compression index, Cc, and recompression index, Cr, which are determined by a consolidation test. This laboratory test is time consuming and labor intensive, thus efforts to correlate the compressibility indexes and soil index properties have been made. In this study, soil compressibility prediction models are enhanced by the support vector machine (SVM) algorithm, and the performances of those correlations are tested via field verification in terms of settlement calculation. The field verification portion of the study consists of identifying sites with borings, consolidation tests, and measured settlement from overlying load. Soil layers, within the influence zone of settlement, are tested to obtain soil index parameters. Once a complete soil profile has been established, a series of settlement analyses were performed. Settlement predictions were made based on both predicted and measured Cr for each soil layer. An additional settlement prediction was made using a rule of thumb equating Cc to Cr. The predicted settlements were then compared to the measured settlement taken in close proximity. Upon conclusion, using the Cr and Cc correlations provides comparable settlement predictions compared to measured settlement and the predicted Cr (using a correlation from predicted Cc) exhibits the strongest settlement predictions. The predicted settlements are lower than the measured settlements for both site locations. This leads one to believe that the influence zone of settlement may be deeper than originally considered.

Today’s energy market is increasingly integrating time-varying tariffs, peak demand charges, and/or export tariffs. In this context, intelligent charging scheduling can considerably reduce the plug-in electric vehicle (PEV) charging cost. This is especially the case as more and more PEVs are charged in buildings that are also equipped with grid-connected intermittent energy resources (IERs) (e.g., photovoltaic systems and wind turbine generators). In this work, we propose a novel and complete intelligent PEV charging scheduling system (tailored for domestic settings) that can account for peak demand charges, time-varying tariffs, and/or export tariffs, appropriately considering both potential IER generation and the rest of a building’s consumption. The backbone of our approach builds on adaptive model predictive control, and includes an efficient depth-first-search-based PEV charging planning algorithm that we propose. Importantly, our approach does not rely on a simplified linear modeling of the charging dynamics, which is a typical and limiting assumption of such systems. We evaluate our approach with real data, considering both solar and wind IER generation capacity, to show that it can reduce the cost of charging by up to ∼ 45% and ∼ 35% in the United States and the United Kingdom domestic settings, respectively, compared to standard PEV charging practices.

Datasets with outliers pose a serious challenge in regression analysis. In this paper, a new regression method called relaxed support vector regression (RSVR) is proposed for such datasets. RSVR is based on the concept of constraint relaxation which leads to increased robustness in datasets with outliers. RSVR is formulated using both linear and quadratic loss functions. Numerical experiments on benchmark datasets and computational comparisons with other popular regression methods depict the behavior of our proposed method. RSVR achieves better overall performance than support vector regression (SVR) in measures such as RMSE and $$R^2_{adj}$$ while being on par with other state-of-the-art regression methods such as robust regression (RR). Additionally, RSVR provides robustness for higher dimensional datasets which is a limitation of RR, the robust equivalent of ordinary least squares regression. Moreover, RSVR can be used on datasets that contain varying levels of noise.

Datasets with significantly larger number of features, compared to samples, pose a serious challenge in supervised learning. Such datasets arise in various areas including business analytics. In this paper, a new binary classification method called constrained subspace classifier (CSC) is proposed for such high dimensional datasets. CSC improves on an earlier proposed classification method called local subspace classifier (LSC) by accounting for the relative angle between subspaces while approximating the classes with individual subspaces. CSC is formulated as an optimization problem and can be solved by an efficient alternating optimization technique. Classification performance is tested in publicly available datasets. The improvement in classification accuracy over LSC shows the importance of considering the relative angle between the subspaces while approximating the classes. Additionally, CSC appears to be a robust classifier, compared to traditional two step methods that perform feature selection and classification in two distinct steps.

Sparse Proximal Support Vector Machines is an embedded feature selection method.sPSVMs removes more than 98% of features in many high dimensional datasets.An efficient alternating optimization technique is proposed.sPSVMs induces class-specific local sparsity. Classification of High Dimension Low Sample Size (HDLSS) datasets is a challenging task in supervised learning. Such datasets are prevalent in various areas including biomedical applications and business analytics. In this paper, a new embedded feature selection method for HDLSS datasets is introduced by incorporating sparsity in Proximal Support Vector Machines (PSVMs). Our method, called Sparse Proximal Support Vector Machines (sPSVMs), learns a sparse representation of PSVMs by first casting it as an equivalent least squares problem and then introducing the l1-norm for sparsity. An efficient algorithm based on alternating optimization techniques is proposed. sPSVMs remove more than 98% of features in many high dimensional datasets without compromising on generalization performance. Stability in the feature selection process of sPSVMs is also studied and compared with other univariate filter techniques. Additionally, sPSVMs offer the advantage of interpreting the selected features in the context of the classes by inducing class-specific local sparsity instead of global sparsity like other embedded methods. sPSVMs appear to be robust with respect to data dimensionality. Moreover, sPSVMs are able to perform feature selection and classification in one step, eliminating the need for dimensionality reduction on the data. To that end, sPSVMs can be used for preprocessing free classification tasks.

The magnitude of the overall settlement depends on several variables such as the compression index, Cc, and recompression index, Cr, which are determined by a consolidation test; however, t...

This is a follow-up sensitivity study on r-mode gravitational wave signals from newborn neutron stars illustrating the applicability of machine learning algorithms for the detection of long-lived gravitational-wave transients. In this sensitivity study we examine three machine learning algorithms (MLAs): artificial neural networks (ANNs), support vector machines (SVMs) and constrained subspace classifiers (CSCs). The objective of this study is to compare the detection efficiency that MLAs can achieve with the efficiency of conventional detection algorithms discussed in an earlier paper. Comparisons are made using 2 distinct r-mode waveforms. For the training of the MLAs we assumed that some information about the distance to the source is given so that the training was performed over distance ranges not wider than half an order of magnitude. The results of this study suggest that machine learning algorithms are suitable for the detection of long-lived gravitational-wave transients and that when assuming knowledge of the distance to the source, MLAs are at least as efficient as conventional methods., Comment: Accepted for publication in Physical Review D