Search

Current methods to determine the energy efficiency of buildings require on-site visits of certified energy auditors which makes the process slow, costly, and geographically incomplete. To accelerate the identification of promising retrofit targets on a large scale, we propose to estimate building energy efficiency from widely available and remotely sensed data sources only, namely street view, aerial view, footprint, and satellite-borne land surface temperature (LST) data. After collecting data for almost 40,000 buildings in the United Kingdom, we combine these data sources by training multiple end-to-end deep learning models with the objective to classify buildings as energy efficient (EU rating A-D) or inefficient (EU rating E-G). After evaluating the trained models quantitatively as well as qualitatively, we extend our analysis by studying the predictive power of each data source in an ablation study. We find that the end-to-end deep learning model trained on all four data sources achieves a macro-averaged F1 score of 64.64% and outperforms the k-NN and SVM-based baseline models by 14.13 to 12.02 percentage points, respectively. Thus, this work shows the potential and complementary nature of remotely sensed data in predicting energy efficiency and opens up new opportunities for future work to integrate additional data sources.

The learning process of classical machine learning algorithms is tuned by hyperparameters that need to be customized to best learn and generalize from an input dataset. In recent years, Quantum Machine Learning (QML) has been gaining traction as a possible application of quantum computing which may provide quantum advantage in the future. However, quantum versions of classical machine learning algorithms introduce a plethora of additional parameters and circuit variations that have their own intricacies in being tuned. In this work, we take the first steps towards Automated Quantum Machine Learning (AutoQML). We propose a concrete description of the problem, and then develop a classical-quantum hybrid cloud architecture that allows for parallelized hyperparameter exploration and model training. As an application use-case, we train a quantum Generative Adversarial neural Network (qGAN) to generate energy prices that follow a known historic data distribution. Such a QML model can be used for various applications in the energy economics sector., Comment: 8 pages, to appear in QSA 2022 (IEEE ICSA 2022)

We consider how the outputs of the Kadison transitivity theorem and Gelfand-Naimark-Segal construction may be obtained in families when the initial data are varied. More precisely, for the Kadison transitivity theorem, we prove that for any nonzero irreducible representation $(\mathcal{H}, \pi)$ of a $C^*$-algebra $\mathfrak{A}$ and $n \in \mathbb{N}$, there exists a continuous function $A:X \rightarrow \mathfrak{A}$ such that $\pi(A(\mathbf{x}, \mathbf{y}))x_i = y_i$ for all $i \in \{1, \ldots, n\}$, where $X$ is the set of pairs of $n$-tuples $(\mathbf{x}, \mathbf{y}) \in \mathcal{H}^n \times \mathcal{H}^n$ such that the components of $\mathbf{x}$ are linearly independent. Versions of this result where $A$ maps into the self-adjoint or unitary elements of $\mathfrak{A}$ are also presented. Regarding the Gelfand-Naimark-Segal construction, we prove that given a topological $C^*$-algebra fiber bundle $p:\mathfrak{A} \rightarrow Y$, one may construct a topological fiber bundle $\mathscr{P}(\mathfrak{A}) \rightarrow Y$ whose fiber over $y \in Y$ is the space of pure states of $\mathfrak{A}_y$ (with the norm topology), as well as bundles $\mathscr{H} \rightarrow \mathscr{P}(\mathfrak{A})$ and $\mathscr{N} \rightarrow \mathscr{P}(\mathfrak{A})$ whose fibers $\mathscr{H}_\omega$ and $\mathscr{N}_\omega$ over $\omega \in \mathscr{P}(\mathfrak{A})$ are the GNS Hilbert space and closed left ideal, respectively, corresponding to $\omega$. When $p:\mathfrak{A} \rightarrow Y$ is a smooth fiber bundle, we show that $\mathscr{P}(\mathfrak{A}) \rightarrow Y$ and $\mathscr{H}\rightarrow \mathscr{P}(\mathfrak{A})$ are also smooth fiber bundles; this involves proving that the group of $*$-automorphisms of a $C^*$-algebra is a Banach-Lie group. In service of these results, we review the geometry of the topology and pure state space. A simple non-interacting quantum spin system is provided as an example.

In recent years, researchers in the area of Computational Creativity have studied the human creative process proposing different approaches to reproduce it with a formal procedure. In this paper, we introduce a model for the generation of literary rhymes in Spanish, combining structures of language and neural network models %(\textit{Word2vec}).%, into a structure for semantic assimilation. The results obtained with a manual evaluation of the texts generated by our algorithm are encouraging., Comment: 7 pages, 2 figures

This work aims to evaluate the ability that both probabilistic and state-of-the-art vector space modeling (VSM) methods provide to well known machine learning algorithms to identify social network documents to be classified as aggressive, gender biased or communally charged. To this end, an exploratory stage was performed first in order to find relevant settings to test, i.e. by using training and development samples, we trained multiple algorithms using multiple vector space modeling and probabilistic methods and discarded the less informative configurations. These systems were submitted to the competition of the ComMA@ICON'21 Workshop on Multilingual Gender Biased and Communal Language Identification., Comment: 6 pages

We propose a Hybrid classical-quantum Autoencoder (HAE) model, which is a synergy of a classical autoencoder (AE) and a parametrized quantum circuit (PQC) that is inserted into its bottleneck. The PQC augments the latent space, on which a standard outlier detection method is applied to search for anomalous data points within a classical dataset. Using this model and applying it to both standard benchmarking datasets, and a specific use-case dataset which relates to predictive maintenance of gas power plants, we show that the addition of the PQC leads to a performance enhancement in terms of precision, recall, and F1 score. Furthermore, we probe different PQC Ans\"atze and analyse which PQC features make them effective for this task., Comment: 17 pages, 11 figures

With the increase of intermittent renewable generation resources feeding into the electrical grid, Distribution System Operators (DSOs) must find ways to incorporate these new actors and adapt the grid to ensure stability and enable flexibility. Dividing the grid into logical clusters entails several organization and technical benefits, helping overcome these challenges.However, finding the optimal grid partitioning remains a challenging task due to its complexity. At the same time, a new technology has gained traction in the last decades for its promising speed-up potential in solving non-trivial combinatorial optimization problems: quantum computing. This work explores its application in Graph Partitioning using electrical modularity. We benchmarked several quantum annealing and hybrid methods on IEEE well-known test cases. The results obtained for the IEEE 14-bus test case show that quantum annealing DWaveSampler brings equal solutions or, for the optimal number partitions, a 1% improvement. For the more significant test cases, hybrid quantum annealing shows a relative error of less than 0.02% compared to the classical benchmark and for IEEE 118-bus test case shows time performance speed-up. The increment in performance would enable real time planning and operations of electrical grids in real time. This work intends to be the first step to showcase the potentials of quantum computing towards the modernization and adaption of electrical grids to the decentralized future of energy systems., Comment: 7 pages, 5 figures, conference

In this work, we aim to solve a practical use-case of unsupervised clustering which has applications in predictive maintenance in the energy operations sector using quantum computers. Using only cloud access to quantum computers, we complete a thorough performance analysis of what some current quantum computing systems are capable of for practical applications involving non-trivial mid-to-high dimensional datasets. We first benchmark how well distance estimation can be performed using two different metrics based on the swap-test, using angle and amplitude data embedding. Next, for the clustering performance analysis, we generate sets of synthetic data with varying cluster variance and compare simulation to physical hardware results using the two metrics. From the results of this performance analysis, we propose a general, competitive, and parallelized version of quantum $k$-means clustering to avoid some pitfalls discovered due to noisy hardware and apply the approach to a real energy grid clustering scenario. Using real-world German electricity grid data, we show that the new approach improves the balanced accuracy of the standard quantum $k$-means clustering by $67.8\%$ with respect to the labeling of the classical algorithm.

This paper is concerned with the physics of parametrized gapped quantum many-body systems, which can be viewed as a generalization of conventional topological phases of matter. In such systems, rather than considering a single Hamiltonian, one considers a family of Hamiltonians that depend continuously on some parameters. After discussing the notion of phases of parametrized systems, we formulate a bulk-boundary correspondence for an important bulk quantity, the Kapustin-Spodyneiko higher Berry curvature, first in one spatial dimension and then in arbitrary dimension. This clarifies the physical interpretation of the higher Berry curvature, which in one spatial dimension is a flow of (ordinary) Berry curvature. In d dimensions, the higher Berry curvature is a flow of (d-1)-dimensional higher Berry curvature. Based on this, we discuss one-dimensional systems that pump Chern number to/from spatial boundaries, resulting in anomalous boundary modes featuring isolated Weyl points. In higher dimensions, there are pumps of the analogous quantized invariants obtained by integrating the higher Berry curvature. We also discuss the consequences for parametrized systems of Kitaev's proposal that invertible phases are classified by a generalized cohomology theory, and emphasize the role of the suspension isomorphism in generating new examples of parametrized systems from known invertible phases. Finally, we present a pair of general quantum pumping constructions, based on physical pictures introduced by Kitaev, which take as input a d-dimensional parametrized system, and produce new (d+1)-dimensional parametrized systems. These constructions are useful for generating examples, and we conjecture that one of the constructions realizes the suspension isomorphism in a generalized cohomology theory of invertible phases., Comment: 35 pages, 11 figures. v2: references added