The present study explores the use of clustering techniques for the design and implementation of a demand response (DR) program for commercial and residential prosumers. The goal of the program is to alter the consumption behavior of the prosumers pertaining to a distributed energy community in Italy. This aggregation aims to: a) minimize the reverse power flow at the primary substation, that occurs when generation from solar panels in the local grid exceeds consumption, and b) shave the system wide peak demand, that typically occurs during the hours of late afternoon. Regarding the clustering stage, three popular machine learning algorithms for electrical load clustering are employed -namely k-means, k-medoids and an agglomerative hierarchical clustering- alongside two different distance measures -namely euclidean and constrained dynamic time warping (DTW). We evaluate the methods using multiple validation metrics including a novel metric -namely peak performance score (PPS)- that we propose in the context of this study. The best model is employed to divide daily prosumer load profiles into clusters and each cluster is analyzed in terms of load shape, mean entropy, and load type distribution. These characteristics are then used to distinguish the clusters that have the potential to serve the optimization objectives by matching them to appropriate DR schemes including time of use (TOU), critical peak pricing (CPP), and real-time pricing (RTP). The results of this study can be useful for network operators, utilities, and aggregators that aim to develop targeted DR programs for groups of prosumers within flexible energy communities.
相關內容
Federated Machine Learning (FL) has received considerable attention in recent years. FL benchmarks are predominantly explored in either simulated systems or data center environments, neglecting the setups of real-world systems, which are often closely linked to edge computing. We close this research gap by introducing FLEdge, a benchmark targeting FL workloads in edge computing systems. We systematically study hardware heterogeneity, energy efficiency during training, and the effect of various differential privacy levels on training in FL systems. To make this benchmark applicable to real-world scenarios, we evaluate the impact of client dropouts on state-of-the-art FL strategies with failure rates as high as 50%. FLEdge provides new insights, such as that training state-of-the-art FL workloads on older GPU-accelerated embedded devices is up to 3x more energy efficient than on modern server-grade GPUs.
We aim to maximize the energy efficiency, gauged as average energy cost per job, in a large-scale server farm with various storage or/and computing components modeled as parallel abstracted servers. Each server operates in multiple power modes characterized by potentially different service and energy consumption rates. The heterogeneity of servers and multiple power modes complicate the maximization problem, where optimal solutions are generally intractable. Relying on the Whittle relaxation technique,we resort to a near-optimal, scalable job-assignment policy. Under a mild condition related to the service and energy consumption rates of the servers, we prove that our proposed policy approaches optimality as the size of the entire system tends to infinity; that is, it is asymptotically optimal. For the nonasymptotic regime, we show the effectiveness of the proposed policy through numerical simulations, where the policy outperforms all the tested baselines, and we numerically demonstrate its robustness against heavy-tailed job-size distributions.
Principal component analysis (PCA) is one of the most popular methods for dimension reduction. In light of the rapidly growing large-scale data in federated ecosystems, the traditional PCA method is often not applicable due to privacy protection considerations and large computational burden. Algorithms were proposed to lower the computational cost, but few can handle both high dimensionality and massive sample size under the distributed setting. In this paper, we propose the FAst DIstributed (FADI) PCA method for federated data when both the dimension $d$ and the sample size $n$ are ultra-large, by simultaneously performing parallel computing along $d$ and distributed computing along $n$. Specifically, we utilize $L$ parallel copies of $p$-dimensional fast sketches to divide the computing burden along $d$ and aggregate the results distributively along the split samples. We present FADI under a general framework applicable to multiple statistical problems, and establish comprehensive theoretical results under the general framework. We show that FADI enjoys the same non-asymptotic error rate as the traditional PCA when $Lp \ge d$. We also derive inferential results that characterize the asymptotic distribution of FADI, and show a phase-transition phenomenon as $Lp$ increases. We perform extensive simulations to show that FADI substantially outperforms the existing methods in computational efficiency while preserving accuracy, and validate the distributional phase-transition phenomenon through numerical experiments. We apply FADI to the 1000 Genomes data to study the population structure.
Predicting the performance of highly configurable software systems is the foundation for performance testing and quality assurance. To that end, recent work has been relying on machine/deep learning to model software performance. However, a crucial yet unaddressed challenge is how to cater for the sparsity inherited from the configuration landscape: the influence of configuration options (features) and the distribution of data samples are highly sparse. In this paper, we propose an approach based on the concept of 'divide-and-learn', dubbed $DaL$. The basic idea is that, to handle sample sparsity, we divide the samples from the configuration landscape into distant divisions, for each of which we build a regularized Deep Neural Network as the local model to deal with the feature sparsity. A newly given configuration would then be assigned to the right model of division for the final prediction. Experiment results from eight real-world systems and five sets of training data reveal that, compared with the state-of-the-art approaches, $DaL$ performs no worse than the best counterpart on 33 out of 40 cases (within which 26 cases are significantly better) with up to $1.94\times$ improvement on accuracy; requires fewer samples to reach the same/better accuracy; and producing acceptable training overhead. Practically, $DaL$ also considerably improves different global models when using them as the underlying local models, which further strengthens its flexibility. To promote open science, all the data, code, and supplementary figures of this work can be accessed at our repository: //github.com/ideas-labo/DaL.
Datasets in the real world are often complex and to some degree hierarchical, with groups and sub-groups of data sharing common characteristics at different levels of abstraction. Understanding and uncovering the hidden structure of these datasets is an important task that has many practical applications. To address this challenge, we present a new and general method for building relational data trees by exploiting the learning dynamics of the Restricted Boltzmann Machine (RBM). Our method is based on the mean-field approach, derived from the Plefka expansion, and developed in the context of disordered systems. It is designed to be easily interpretable. We tested our method in an artificially created hierarchical dataset and on three different real-world datasets (images of digits, mutations in the human genome, and a homologous family of proteins). The method is able to automatically identify the hierarchical structure of the data. This could be useful in the study of homologous protein sequences, where the relationships between proteins are critical for understanding their function and evolution.
Extreme value theory (EVT) provides an elegant mathematical tool for statistical analysis of rare events. Typically, when data are collected from multiple clusters, analysts want to preserve cluster information, such as region, period, and group. To consider large-sized cluster information in extreme value analysis, we incorporate the mixed effects model (MEM) into the regression technique in EVT. In the field of small area estimation, it is well known that the MEM is an important tool for providing reliable estimates of large-sized clusters with small sample sizes. In the context of EVT for rare event analysis, the sample size of extreme value data for each cluster is often small. Therefore, the MEM may contribute to improving the predictive accuracy of extreme value analysis. This motivates us to verify the effectiveness of the MEM in EVT through theoretical studies and numerical experiments, including its application to the risk assessment of heavy rainfall in Japan.
Smart buildings are increasingly using Internet of Things (IoT)-based wireless sensing systems to reduce their energy consumption and environmental impact. As a result of their compact size and ability to sense, measure, and compute all electrical properties, Internet of Things devices have become increasingly important in our society. A major contribution of this study is the development of a comprehensive IoT-based framework for smart city energy management, incorporating multiple components of IoT architecture and framework. An IoT framework for intelligent energy management applications that employ intelligent analysis is an essential system component that collects and stores information. Additionally, it serves as a platform for the development of applications by other companies. Furthermore, we have studied intelligent energy management solutions based on intelligent mechanisms. The depletion of energy resources and the increase in energy demand have led to an increase in energy consumption and building maintenance. The data collected is used to monitor, control, and enhance the efficiency of the system.
Deep learning have achieved promising results on a wide spectrum of AI applications. Larger datasets and models consistently yield better performance. However, we generally spend longer training time on more computation and communication. In this survey, we aim to provide a clear sketch about the optimizations for large-scale deep learning with regard to the model accuracy and model efficiency. We investigate algorithms that are most commonly used for optimizing, elaborate the debatable topic of generalization gap arises in large-batch training, and review the SOTA strategies in addressing the communication overhead and reducing the memory footprints.
A community reveals the features and connections of its members that are different from those in other communities in a network. Detecting communities is of great significance in network analysis. Despite the classical spectral clustering and statistical inference methods, we notice a significant development of deep learning techniques for community detection in recent years with their advantages in handling high dimensional network data. Hence, a comprehensive overview of community detection's latest progress through deep learning is timely to both academics and practitioners. This survey devises and proposes a new taxonomy covering different categories of the state-of-the-art methods, including deep learning-based models upon deep neural networks, deep nonnegative matrix factorization and deep sparse filtering. The main category, i.e., deep neural networks, is further divided into convolutional networks, graph attention networks, generative adversarial networks and autoencoders. The survey also summarizes the popular benchmark data sets, model evaluation metrics, and open-source implementations to address experimentation settings. We then discuss the practical applications of community detection in various domains and point to implementation scenarios. Finally, we outline future directions by suggesting challenging topics in this fast-growing deep learning field.
Federated learning (FL) is an emerging, privacy-preserving machine learning paradigm, drawing tremendous attention in both academia and industry. A unique characteristic of FL is heterogeneity, which resides in the various hardware specifications and dynamic states across the participating devices. Theoretically, heterogeneity can exert a huge influence on the FL training process, e.g., causing a device unavailable for training or unable to upload its model updates. Unfortunately, these impacts have never been systematically studied and quantified in existing FL literature. In this paper, we carry out the first empirical study to characterize the impacts of heterogeneity in FL. We collect large-scale data from 136k smartphones that can faithfully reflect heterogeneity in real-world settings. We also build a heterogeneity-aware FL platform that complies with the standard FL protocol but with heterogeneity in consideration. Based on the data and the platform, we conduct extensive experiments to compare the performance of state-of-the-art FL algorithms under heterogeneity-aware and heterogeneity-unaware settings. Results show that heterogeneity causes non-trivial performance degradation in FL, including up to 9.2% accuracy drop, 2.32x lengthened training time, and undermined fairness. Furthermore, we analyze potential impact factors and find that device failure and participant bias are two potential factors for performance degradation. Our study provides insightful implications for FL practitioners. On the one hand, our findings suggest that FL algorithm designers consider necessary heterogeneity during the evaluation. On the other hand, our findings urge system providers to design specific mechanisms to mitigate the impacts of heterogeneity.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191