We propose new mechanisms that can be used by a demand response aggregator to flexibly shift the charging of electric vehicles (EVs) to times where cheap but intermittent renewable energy is in high supply. Here, it is important to consider the constraints and preferences of EV owners, while eliminating the scope for strategic behaviour. To achieve this, we propose, for the first time, a generic class of incentive mechanisms for settings with both varying marginal electricity costs and multidimensional preferences. We show these are dominant strategy incentive compatible, i.e., EV owners are incentivised to report their constraints and preferences truthfully. We also detail a specific instance of this class, show that it achieves ≈98% of the optimal in realistic scenarios and demonstrate how it can be adapted to trade off efficiency with profit.

Non-Intrusive Load Monitoring (NILM) uses one smart meter at the power feed to disaggregate the states of a set of appliances. Multiple NILM meters are deployed to achieve high monitoring accuracy in large-scale power systems. Our work studies the tradeoff between monitoring accuracy and meter deployment, in a quantitative and extensible way. In particular, we introduce a clearness function as an abstract indicator of expected monitoring accuracy given any NILM method, and then showcase two concrete constructions. With the notation of a clearness function, we propose solutions to the smart meter deployment problem (SMDP), that is, the problem of finding a deployment scheme with minimum number of meters while attaining a required monitoring accuracy. Theoretically, SMDP is shown NP-hard and a polynomial-time approximation scheme (PTAS) is proposed in this paper. For evaluation, we show that our proposed scheme is efficient and effective in terms of approximation ratio and running time. On real and simulated datasets, our proposed framework achieves a higher monitoring accuracy at a much lower cost, outperforming common baseline algorithms.

As cloud computing gains in popularity, understanding the patterns and structure of its loads is increasingly important in order to drive effective resource allocation, scheduling and pricing decisions. These efficiency increases are then associated with a reduction in the data center environmental footprint. Existing models have only treated a single resource type, such as CPU, or memory, at a time. We offer a sophisticated machine learning approach to capture the joint-distribution. We capture the relationship among multiple resources by carefully fitting both the marginal distributions of each resource type as well as the non-linear structure of their correlation via a copula distribution. We investigate several choices for both models by studying a public data set of Google data-center usage. We show the Burr XII distribution to be a particularly effective choice for modeling the marginals and the Frank copula to be the best choice for stitching these together into a joint distribution. Our approach offers a significant fidelity improvement and generalizes directly to higher dimensions. In use, this improvement will translate directly to reductions in energy consumption.

Building on the successful applications of Stackelberg Security Games (SSGs) to protect infrastructure, researchers have begun focusing on applying game theory to green security domains such as protection of endangered animals and fish stocks. Previous efforts in these domains optimize defender strategies based on the standard Stackelberg assumption that the adversaries become fully aware of the defender's strategy before taking action. Unfortunately, this assumption is inappropriate since adversaries in green security domains often lack the resources to fully track the defender strategy. This paper (i) introduces Green Security Games (GSGs), a novel game model for green security domains with a generalized Stackelberg assumption; (ii) provides algorithms to plan effective sequential defender strategies --- such planning was absent in previous work; (iii) proposes a novel approach to learn adversary models that further improves defender performance; and (iv) provides detailed experimental analysis of proposed approaches.

Smart grids enhance power grids by integrating electronic equipment, communication systems and computational tools. In a smart grid, consumers can insert energy into the power grid. We propose a new energy management system (called RLbEMS) that autonomously defines a policy for selling or storing energy surplus in smart homes. This policy is achieved through Batch Reinforcement Learning with historical data about energy prices, energy generation, consumer demand and characteristics of storage systems. In practical problems, RLbEMS has learned good energy selling policies quickly and effectively. We obtained maximum gains of 20.78% and 10.64%, when compared to a Naive-greedy policy, for smart homes located in Brazil and in the USA, respectively. Another important result achieved by RLbEMS was the reduction of about 30% of peak demand, a central desideratum for smart grids.

In this paper, we address the challenge of predicting optimal comfort temperatures of individual users of a smart heating system. At present, such systems use simple models of user comfort when deciding on a set point temperature. These models generally fail to adapt to an individual user’s preferences, resulting in poor estimates of a user’s preferred temperature. To address this issue, we propose a personalised thermal comfort model that uses a Bayesian network to learn and adapt to a user’s individual preferences. Through an empirical evaluation based on the ASHRAE RP-884 data set, we show that our model is consistently 17.5- 23.5% more accurate than current models, regardless of environmental conditions and the type of heating system used. Our model is not limited to a single metric but can also infer information about expected user feedback, optimal comfort temperature and thermal sensitivity at the same time, which can be used to reduce energy used for heating with minimal comfort loss.

We describe an unconventional line of attack in our quest to teach machines how to rap battle by improvising hip hop lyrics on the fly, in which a novel recursive bilingual neural network, TRAAM, implicitly learns soft, context-dependent generalizations over the structural relationships between associated parts of challenge and response raps, while avoiding the exponential complexity costs that symbolic models would require. TRAAM learns feature vectors simultaneously using context from both the challenge and the response, such that challenge-response association patterns with similar structure tend to have similar vectors. Improvisation is modeled as a quasi-translation learning problem, where TRAAM is trained to improvise fluent and rhyming responses to challenge lyrics. The soft structural relationships learned by our TRAAM model are used to improve the probabilistic responses generated by our improvisational response component.

Abstract artists use non-figurative elements (i.e. colours, lines, shapes, and textures) to convey emotions and often rely on the titles of their various compositions to generate (or enhance) an emotional reaction in the audience. Several psychological works observed that the metadata (i.e., titles, description and/or artist statements) associated with paintings increase the understanding and the aesthetic appreciation of artworks. In this paper we explore if the same metadata could facilitate the computational analysis of artworks, and reveal what kind of emotional responses they awake. To this end, we employ computer vision and sentiment analysis to learn statistical patterns associated with positive and negative emotions on abstract paintings. We propose a multimodal approach which combines both visual and metadata features in order to improve the machine performance. In particular, we propose a novel joint flexible Schatten p-norm model which can exploit the sharing patterns between visual and textual information for abstract painting emotion analysis. Moreover, we conduct a qualitative analysis on the cases in which metadata help improving the machine performance.

In this paper we introduce our haiku generator, which, in contrast to other systems, is not restricted to limited classic vocabulary sets and preserves a classic style without becoming too random and abstract because it performs a semantic integrity check using the Internet. Moreover, it is able to analyze blog entry input and, by using nouns and adjectives for web-mining, to stay on topic and still preserve kigo, traditional seasonal words used in Japanese poetry. The haiku generator utilizes grammar templates automatically generated from poems written by Japanese poets and a lexicon of 2,473 kigo words from an online haiku repository. In addition to generating haiku poems, it can output them vocally together with related sound effects and images retrieved from the WWW. Our experiments demonstrate that the proposed system generates high-quality haikus and that using content-related input and multimedia-rich output is effective for increasing users' satisfaction. We have performed impression evaluation experiments and confirmed that our method is especially useful for generating haikus with higher depth and sound-sharpness, which are two very important categories in professional evaluation of Japanese poetry. Next, haikus generated using the proposed method were evaluated by blog authors and blog readers and again, the proposed method outperformed the baseline. We also measured how the presence or absence of multimedia output influenced the evaluation. While using both vocal output and an image achieved higher scores than text alone, there were cases in which some combinations of effects were evaluated higher than all the effects used together. With our original approach to generating poetry, we wish to show the importance of new media and possibilities that are arising from the utilization of the "wisdom of (web-)crowds" in order to achieve higher standards for AI-generated art.

We address the problem of generating all possible palindromes from a corpus of Ngrams. Palindromes are texts that read the same both ways. Short palindromes ("race car") usually carry precise, significant meanings. Long palindromes are often less meaningful, but even harder to generate. The palindrome generation problem has never been addressed, to our knowledge, from a strictly combinatorial point of view. The main difficulty is that generating palindromes require the simultaneous consideration of two inter-related levels in a sequence: the "character" and the "word" levels. Although the problem seems very combinatorial, we propose an elegant yet non-trivial graph structure that can be used to generate all possible palindromes from a given corpus of Ngrams, with a linear complexity. We illustrate our approach with short and long palindromes obtained from the Google Ngram corpus. We show how we can control the semantics, to some extent, by using arbitrary text corpora to bias the probabilities of certain sets of words. More generally this work addresses the issue of modelling human virtuosity from a combinatorial viewpoint, as a means to understand human creativity.