Search

The heating, ventilation, and air-conditioning (HVAC) system account for substantial energy use in buildings, whereas a large group of occupants is still not actually feeling comfortable staying inside. This poses the issue of developing energy-efficient HVAC control, i.e., reduce energy use (cost) while simultaneously enhancing human comfort. This brief pursues the objective and studies the stochastic optimal HVAC control subject to uncertain thermal demand (i.e., the weather and occupancy). Particularly, we involve the elaborate predicted mean vote (PMV) thermal comfort model in the optimization. The problem is computationally challenging due to the nonlinear and nonanalytical constraints imposed by the system dynamics and PMV model. We make the following contributions to address it. First, we formulate the problem as a Markov decision process (MDP) which is a desirable modeling technique capable of handling the complexities. Second, we propose a gradient-based learning (GB-L) method for progressively learning a stochastic control policy off-line and store it for on-line execution. Third, we prove the learning method’s converge to the optimal policies theoretically, and its performance (i.e., energy cost, thermal comfort, and on-line computation) for HVAC control via simulations. The comparisons with the existing model predictive control based relaxation (MPC-R) method which is assumed with accurate future information and supposed to provide the near-optimal bounds show that though there exists some discount in energy cost reduction (i.e., 6.5%), the proposed method can enable efficient on-line implementation (less than 1 s) and provide a high probability of thermal comfort under uncertainties. [ABSTRACT FROM AUTHOR]

This article studies a scalable control method for multizone heating, ventilation, and air-conditioning (HVAC) systems to optimize the energy cost for maintaining thermal comfort (TC) and indoor air quality (IAQ) (represented by CO2) simultaneously. This problem is computationally challenging due to the complex system dynamics, various spatial and temporal couplings, as well as multiple control variables to be coordinated. To address the challenges, we propose a two-level distributed method (TLDM) with an upper level and lower level control integrated. The upper level computes zone mass flow rates for maintaining zone TC with minimal energy cost, and then, the lower level strategically regulates zone mass flow rates and the ventilation rate to achieve IAQ while preserving the near energy-saving performance of upper level. As both the upper and the lower level computation are deployed in a distributed manner, the proposed method is scalable and computationally efficient. The near-optimal performance of the method in energy cost saving is demonstrated through comparison with the centralized method. In addition, the comparisons with the existing distributed method show that our method can provide IAQ with only little increase of energy cost, while the latter fails. Moreover, we demonstrate that our method outperforms the demand-controlled ventilation (DCVs) strategies for IAQ management with about 8%–10% energy cost reduction. Note to Practitioners: The high portion of building energy consumption has motivated the energy saving for heating, ventilation, and air-conditioning (HVAC) systems. Concurrently, the living standards for indoor environment are rising among the occupants. Nevertheless, the status quo on improving building energy efficiency has mostly focused on maintaining thermal comfort (such as temperature), and the indoor air quality (IAQ) (usually represented by CO2 level) has been seldom incorporated. In our previous work with the similar setting, we observed that the CO2 levels will surge beyond tolerance during the high occupancy periods if only thermal comfort (TC) is considered for HVAC control. This deduces the IAQ and TC should be jointly considered while pursuing the energy cost saving target and thus studied in this article. This task is computationally cumbersome due to the complex system dynamics (thermal and CO2) and tight correlations among the different control components (variable air volume and fresh air damper). To cope with these challenges, this work develops a two-level distributed computation paradigm for HVAC systems based on problem structures. Specifically, the upper level control (ULC) first calculates zone mass flow rates for maintaining comfortable zone temperature with minimal energy cost, and then, the lower level strategically regulates the computed zone mass flow rates as well as ventilation rate to satisfy IAQ while preserving the near energy-saving performance of the ULC. As both the upper and lower level calculations can be implemented in a distributed manner, the proposed method is scalable to large multizone deployment. The method’s performance both in maintaining comfort (i.e., TC and IAQ) and energy cost saving is demonstrated via simulations in comparisons with the centralized method, the distributed token-based scheduling strategy, and the demand-controlled ventilation strategies. [ABSTRACT FROM AUTHOR]

This paper studies an energy storage (ES) sharing model which is cooperatively invested by multiple buildings for harnessing on-site renewable utilization and grid price arbitrage. To maximize the economic benefits, we jointly consider the ES sizing, operation, and cost allocation via a coalition game formulation. Particularly, we study a fair ex-post cost allocation based on nucleolus which addresses fairness by minimizing the minimal dissatisfaction of all the players. To overcome the exponential computation burden caused by the implicit characteristic function, we employ a constraint generation technique to gradually approach the unique nucleolus by leveraging the sparse problem structure. We demonstrate both the fairness and computational efficiency of the method through case studies, which are not provided by the existing Shapley approach or proportional method. Particularly, only a small fraction of characteristic function (less than 1% for 20 buildings) is required to achieve the cost allocation versus the exponential information required by Shapley approach. Though there exists a minor increase of computation over the proportional method, the proposed method can ensure fairness while the latter fails in some cases. Further, we demonstrate both the building-wise and community-wise economic benefits are enhanced with the ES sharing model over the individual ES (IES) model. Accordingly, the overall value of ES is considerably improved (about 1.83 times). 1 The proportion of total electricity bill reduction relative to the ES capital cost. [ABSTRACT FROM AUTHOR]

Two key challenges lie in the facial attractiveness computation research: the lack of discriminative face representations, and the scarcity of sufficient and complete training data. Motivated by recent promising work in face recognition using deep neural networks to learn effective features, the first challenge is expected to be addressed from a deep learning point of view. A very deep residual network is utilized to enable automatic learning of hierarchical aesthetics representation. The inspiration to deal with the second challenge comes from the natural representation of the training data, where each training face can be associated with a label (score) distribution given by human raters rather than a single label (average score). This paper, therefore, recasts facial attractiveness computation as a label distribution learning problem. Integrating these two ideas, an end-to-end attractiveness learning framework is established. We also perform feature-level fusion by incorporating the low-level geometric features to further improve the computational performance. Extensive experiments are conducted on a standard benchmark, the SCUT-FBP dataset, where our approach shows significant advantages over the other state-of-the-art work. [ABSTRACT FROM AUTHOR]

Several factors contribute to individual variability in postoperative pain, therefore, individuals consume postoperative analgesics at different rates. Although many statistical studies have analyzed postoperative pain and analgesic consumption, most have identified only the correlation and have not subjected the statistical model to further tests in order to evaluate its predictive accuracy. In this study involving 3052 patients, a multistrategy computational approach was developed for analgesic consumption prediction. This approach uses data on patient-controlled analgesia demand behavior over time and combines clustering, classification, and regression to mitigate the limitations of current statistical models. Cross-validation results indicated that the proposed approach significantly outperforms various existing regression methods. Moreover, a comparison between the predictions by anesthesiologists and medical specialists and those of the computational approach for an independent test data set of 60 patients further evidenced the superiority of the computational approach in predicting analgesic consumption because it produced markedly lower root mean squared errors. [ABSTRACT FROM AUTHOR]

In a social network, even about the same information the excitement between different users are different. If we want to spread a piece of new information and maximize the expected total amount of excitement, which seed users should we choose? This problem indeed is substantially different from the renowned influence maximization problem and cannot be tackled using the existing approaches. In this paper, motivated by the demand in a few interesting applications, we model the novel problem of activity maximization, and tackle the problem systematically. We first analyze the complexity and the approximability of the problem. We develop an upper bound and a lower bound that are submodular so that the Sandwich framework can be applied. We then devise a polling-based randomized algorithm that guarantees a data dependent approximation factor. Our experiments on four real data sets clearly verify the effectiveness and scalability of our method, as well as the advantage of our method against the other heuristic methods. [ABSTRACT FROM PUBLISHER]

In this paper, we tackle a challenging problem inherent in a series of applications: tracking the influential nodes in dynamic networks. Specifically, we model a dynamic network as a stream of edge weight updates. This general model embraces many practical scenarios as special cases, such as edge and node insertions, deletions as well as evolving weighted graphs. Under the popularly adopted linear threshold model and independent cascade model, we consider two essential versions of the problem: finding the nodes whose influences passing a user specified threshold and finding the top-$k$ most influential nodes. Our key idea is to use the polling-based methods and maintain a sample of random RR sets so that we can approximate the influence of nodes with provable quality guarantees. We develop an efficient algorithm that incrementally updates the sample random RR sets against network changes. We also design methods to determine the proper sample sizes for the two versions of the problem so that we can provide strong quality guarantees and, at the same time, be efficient in both space and time. In addition to the thorough theoretical results, our experimental results on five real network data sets clearly demonstrate the effectiveness and efficiency of our algorithms. [ABSTRACT FROM PUBLISHER]