اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدData-driven Thermal Model Inference with ARMAX, in Smart Environments, based on Normalized Mutual Information
160
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Understanding the models that characterize the thermal dynamics in a smart building is important for the comfort of its occupants and for its energy optimization. A significant amount of research has attempted to utilize thermodynamics (physical) models for smart building control, but these approaches remain challenging due to the stochastic nature of the intermittent environmental disturbances. This paper presents a novel data-driven approach for indoor thermal model inference, which combines an Autoregressive Moving Average with eXogenous inputs model (ARMAX) with a Normalized Mutual Information scheme (NMI). Based on this information-theoretic method, NMI, causal dependencies between the indoor temperature and exogenous inputs are explicitly obtained as a guideline for the ARMAX model to find the dominating inputs. For validation, we use three datasets based on building energy systems-against which we compare our method to an autoregressive model with exogenous inputs (ARX), a regularized ARMAX model, and state-space models.
قيم البحث
اقرأ أيضاً
We consider a fundamental remote state estimation problem of discrete-time linear time-invariant (LTI) systems. A smart sensor forwards its local state estimate to a remote estimator over a time-correlated $M$-state Markov fading channel, where the p
acket drop probability is time-varying and depends on the current fading channel state. We establish a necessary and sufficient condition for mean-square stability of the remote estimation error covariance as $rho^2(mathbf{A})rho(mathbf{DM})<1$, where $rho(cdot)$ denotes the spectral radius, $mathbf{A}$ is the state transition matrix of the LTI system, $mathbf{D}$ is a diagonal matrix containing the packet drop probabilities in different channel states, and $mathbf{M}$ is the transition probability matrix of the Markov channel states. To derive this result, we propose a novel estimation-cycle based approach, and provide new element-wise bounds of matrix powers. The stability condition is verified by numerical results, and is shown more effective than existing sufficient conditions in the literature. We observe that the stability region in terms of the packet drop probabilities in different channel states can either be convex or concave depending on the transition probability matrix $mathbf{M}$. Our numerical results suggest that the stability conditions for remote estimation may coincide for setups with a smart sensor and with a conventional one (which sends raw measurements to the remote estimator), though the smart sensor setup achieves a better estimation performance.
In this paper, a data-driven approach to characterize influence in a power network is presented. The characterization is based on the notion of information transfer in a dynamical system. In particular, we use the information transfer based definitio
n of influence in a dynamical system and provide a data-driven approach to identify the influential state(s) and generators in a power network. Moreover, we show how the data-based information transfer measure can be used to characterize the type of instability of a power network and also identify the states causing the instability.
Conditional Mutual Information (CMI) is a measure of conditional dependence between random variables X and Y, given another random variable Z. It can be used to quantify conditional dependence among variables in many data-driven inference problems su
ch as graphical models, causal learning, feature selection and time-series analysis. While k-nearest neighbor (kNN) based estimators as well as kernel-based methods have been widely used for CMI estimation, they suffer severely from the curse of dimensionality. In this paper, we leverage advances in classifiers and generative models to design methods for CMI estimation. Specifically, we introduce an estimator for KL-Divergence based on the likelihood ratio by training a classifier to distinguish the observed joint distribution from the product distribution. We then show how to construct several CMI estimators using this basic divergence estimator by drawing ideas from conditional generative models. We demonstrate that the estimates from our proposed approaches do not degrade in performance with increasing dimension and obtain significant improvement over the widely used KSG estimator. Finally, as an application of accurate CMI estimation, we use our best estimator for conditional independence testing and achieve superior performance than the state-of-the-art tester on both simulated and real data-sets.
Growing amount of hydraulic fracturing (HF) jobs in the recent two decades resulted in a significant amount of measured data available for development of predictive models via machine learning (ML). In multistage fractured completions, post-fracturin
g production analysis reveals that different stages produce very non-uniformly due to a combination of geomechanics and fracturing design factors. Hence, there is a significant room for improvement of current design practices. The workflow is essentially split into two stages. As a result of the first stage, the present paper summarizes the efforts into the creation of a digital database of field data from several thousands of multistage HF jobs on wells from circa 20 different oilfields in Western Siberia, Russia. In terms of the number of points (fracturing jobs), the present database is a rare case of a representative dataset of about 5000 data points. Each point in the data base contains the vector of 92 input variables (the reservoir, well and the frac design parameters) and the vector of production data, which is characterized by 16 parameters, including the target, cumulative oil production. Data preparation has been done using various ML techniques: the problem of missing values in the database is solved with collaborative filtering for data imputation; outliers are removed using visualisation of cluster data structure by t-SNE algorithm. The production forecast problem is solved via CatBoost algorithm. Prediction capability of the model is measured with the coefficient of determination (R^2) and reached 0.815. The inverse problem (selecting an optimum set of fracturing design parameters to maximize production) will be considered in the second part of the study to be published in another paper, along with a recommendation system for advising DESC and production stimulation engineers on an optimized fracturing design.
The proposed pruning strategy offers merits over weight-based pruning techniques: (1) it avoids irregular memory access since representations and matrices can be squeezed into their smaller but dense counterparts, leading to greater speedup; (2) in a
manner of top-down pruning, the proposed method operates from a more global perspective based on training signals in the top layer, and prunes each layer by propagating the effect of global signals through layers, leading to better performances at the same sparsity level. Extensive experiments show that at the same sparsity level, the proposed strategy offers both greater speedup and higher performances than weight-based pruning methods (e.g., magnitude pruning, movement pruning).
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
