•Review of applications of transfer learning (TL) for smart buildings.•Identification of main application areas of TL in smart buildings.•Insights on the most-effective TL techniques for each ...application area.•Discussion on current research gaps and future opportunities.
Display omitted
Smart buildings play a crucial role toward decarbonizing society, as globally buildings emit about one-third of greenhouse gases. In the last few years, machine learning has achieved a notable momentum that, if properly harnessed, may unleash its potential for advanced analytics and control of smart buildings, enabling the technique to scale up for supporting the decarbonization of the building sector. In this perspective, transfer learning aims to improve the performance of a target learner exploiting knowledge in related environments. The present work provides a comprehensive overview of transfer learning applications in smart buildings, classifying and analyzing 77 papers according to their applications, algorithms, and adopted metrics. The study identified four main application areas of transfer learning: (1) building load prediction, (2) occupancy detection and activity recognition, (3) building dynamics modeling, and (4) energy systems control. Furthermore, the review highlighted the role of deep learning in transfer learning applications that has been used in more than half of the analyzed studies. The paper also discusses how to integrate transfer learning in a smart building’s ecosystem, identifying, for each application area, the research gaps and guidelines for future research directions.
Demand Response (DR) programs represent an effective way to optimally manage building energy demand while increasing Renewable Energy Sources (RES) integration and grid reliability, helping the ...decarbonization of the electricity sector. To fully exploit such opportunities, buildings are required to become sources of energy flexibility, adapting their energy demand to meet specific grid requirements. However, in most cases, the energy flexibility of a single building is typically too small to be exploited in the flexibility market, highlighting the necessity to perform analysis at a multiple-building scale. This study explores the economic benefits associated with the implementation of a Reinforcement Learning (RL) control strategy for the participation in an incentive-based demand response program of a cluster of commercial buildings. To this purpose, optimized Rule-Based Control (RBC) strategies are compared with a RL controller. Moreover, a hybrid control strategy exploiting both RBC and RL is proposed. Results show that the RL algorithm outperforms the RBC in reducing the total energy cost, but it is less effective in fulfilling DR requirements. The hybrid controller achieves a reduction in energy consumption and energy costs by respectively 7% and 4% compared to a manually optimized RBC, while fulfilling DR constraints during incentive-based events.
The imperative to reduce emissions to counteract climate change has led to the use of renewables progressively in more areas. Looking at district heating, there is a growing interest in coupling ...current production systems and carbon-neutral technologies. This paper presents a methodology to support decision making about carbon-neutral technologies for district heating. The process is organized in two stages, the first one aims at optimizing the different carbon-neutral technologies according to an objective function and assess uncertainties and dependencies. In the second stage, the alternatives are evaluated using Stochastic Multicriteria Acceptability Analysis (SMAA), a simulation-based method specifically designed to consider imprecise information. The methodology was applied to a case-study in Torino, Italy, which simulates the city district heating network at a smaller scale, with the aim to explore strategies for replacing gas boiler with more sustainable technologies. According to preference information provided by decision makers, the most preferred alternative resulted in the introduction of a solar heat plant combined with an increase size of daily heat storage. Solar heat can benefit from incentives while reducing operational costs and emissions, maximizing the use of carbon-neutral heat thanks to the storage.
In dilated cardiomyopathy (DCM), where the heart muscle becomes stretched and thin, heart failure (HF) occurs, and the cardiomyocytes suffer from an energetic inefficiency caused by an abnormal ...cardiac metabolism. Although underappreciated as a potential therapeutic target, the optimal metabolic milieu of a failing heart is still largely unknown and subject to debate. Because glucose naturally has a lower P/O ratio (the ATP yield per oxygen atom), the previous studies using this strategy to increase glucose oxidation have produced some intriguing findings. In reality, the vast majority of small-scale pilot trials using trimetazidine, ranolazine, perhexiline, and etomoxir have demonstrated enhanced left ventricular (LV) function and, in some circumstances, myocardial energetics in chronic ischemic and non-ischemic HF with a reduced ejection fraction (EF). However, for unidentified reasons, none of these drugs has ever been tested in a clinical trial of sufficient size. Other pilot studies came to the conclusion that because the heart in severe dilated cardiomyopathy appears to be metabolically flexible and not limited by oxygen, the current rationale for increasing glucose oxidation as a therapeutic target is contradicted and increasing fatty acid oxidation is supported. As a result, treating metabolic dysfunction in HF may benefit from raising ketone body levels. Interestingly, treatment with sodium-glucose cotransporter-2 inhibitors (SGLT2i) improves cardiac function and outcomes in HF patients with or without type 2 diabetes mellitus (T2DM) through a variety of pleiotropic effects, such as elevated ketone body levels. The improvement in overall cardiac function seen in patients receiving SGLT2i could be explained by this increase, which appears to be a reflection of an adaptive process that optimizes cardiac energy metabolism. This review aims to identify the best metabolic therapeutic approach for DCM patients, to examine the drugs that directly affect cardiac metabolism, and to outline all the potential ancillary metabolic effects of the guideline-directed medical therapy. In addition, a special focus is placed on SGLT2i, which were first studied and prescribed to diabetic patients before being successfully incorporated into the pharmacological arsenal for HF patients.
•LSTM models and DRL provide an effective data-driven district energy management.•The proposed approach reduces computational cost compared to a forward modelling.•The coordinated management achieves ...23% of peak reduction compared to baseline RBC.•The DRL controller is capable to optimize comfort, cost and peaks at district level.
Demand side management at district scale plays a crucial role in the energy transition process, being an ideal candidate to balance the needs of both users and grid, by managing the volatility of renewable sources and increasing energy flexibility. The presented study aims to explore the benefits of a coordinated approach for the energy management of a cluster of buildings to optimise the electrical demand profiles and provide services to the grid without penalising indoor comfort conditions. The proposed methodology makes use of a fully data-driven control scheme which exploits Long Short-Term Memory (LSTM) Neural Networks, and Deep Reinforcement Learning (DRL). A simulation environment is introduced to train a DRL controller to manage the operation of heat pumps and chilled and domestic hot water storage for a cluster of four buildings. LSTM models are trained with synthetic data set created in EnergyPlus and are integrated into simulation environment to evaluate the indoor temperature dynamics in each building. The developed DRL controller is tested against a manually optimised Rule Based Controller (RBC). Results show that the DRL algorithm is able to reduce the overall cluster electricity costs, while decreasing the peak energy demand by 23% and the Peak to Average Ratio (PAR) by 20%, without penalizing indoor temperature control.
Aims
Aortic stenosis (AS) and cardiac amyloidosis (CA) are typical diseases of the elderly. Up to 16% of older adults with severe AS referred to transcatheter aortic valve replacement (TAVR) have a ...concomitant diagnosis of CA. CA‐AS population suffers from reduced functional capacity and worse prognosis than AS patients. As the prognostic impact of TAVR in patients with CA‐AS has been historically questioned and in light of recently published evidence, we aim to provide a comprehensive synthesis of the efficacy and safety of TAVR in CA‐AS patients.
Methods and results
We performed a systematic review and meta‐analysis of studies: (i) evaluating mortality with TAVR as compared with medical therapy in CA‐AS patients and (ii) reporting complications and clinical outcomes of TAVR in CA‐AS patients as compared with patients with AS alone. A total of seven observational studies were identified: four reported mortality with TAVR, and four reported complications and clinical outcomes after TAVR of patients with CA‐AS compared with AS alone patients. In patients with CA‐AS, the risk of mortality was lower with TAVR (n = 44) as compared with medical therapy (n = 36) odds ratio (OR) 0.23, 95% confidence interval (CI) 0.07–0.73, I2 = 0%, P = 0.001, number needed to treat = 3. The safety profile of TAVR seems to be similar in patients with CA‐AS (n = 75) as compared with those with AS alone (n = 536), with comparable risks of stroke, vascular complications, life‐threatening bleeding, acute kidney injury, and 30 day mortality, although CA‐AS was associated with a trend towards an increased risk of permanent pacemaker implantation (OR 1.76, 95% CI 0.91–4.09, I2 = 0%, P = 0.085). CA is associated with a numerically higher rate of long‐term mortality and rehospitalizations following TAVR in patients with CA‐AS as compared with those with AS alone.
Conclusions
TAVR is an effective and safe procedure in CA‐AS patients, with a substantial survival benefit as compared with medical therapy, and a safety profile comparable with patients with AS alone except for a trend towards higher risk of permanent pacemaker implantation.
Recommended therapy for calcific degenerative aortic stenosis (AS) is still aortic valve replacement (AVR), either transcatheter or surgical, since no conclusive efficacy has been determined in ...slowing the degenerative process by medical therapy.
This paper offers a brief overview of molecular mechanisms leading to calcification of aortic valve. It is then focused on potential markers of disease progression, as observed in many observational studies. Finally it provides a comprehensive review of drugs already tested in in vitro and human studies in order to slow aortic valve stenosis process.
Despite research providing numerous molecular pathways underlying the calcification process, further efforts must be made to understand risk factors linked to disease progression. Some existing treatments that have already provided survival benefits in many features of cardiovascular diseases are currently being tested with promising results. In the near future new drugs acting on specific pathways by techniques such as monoclonal antibodies and RNA interference, are expected to provide better medical solutions for this ever growing number of patients.
Neurosurgical education should start during medical school to involve more students, favoring the recruitment of the most prepared and motivated ones and spreading this subject to the future medical ...generations. Despite multiple investigations, a dedicated educational plan does not exist. This study aims to assess the undergraduates' interests, needs, and perceptions of this subject.
The survey was structured to collect demographic data of the participants, and to explore their interest in neurosurgery, their consideration of its importance in medical school, their opinions about the role of this subject in medical education, their needs in this training, and, the usefulness of this subject for their future career.
A total of 156 students participated in the survey. Interest in neurosurgery was shown by 76 (48.7%) participants, however, this subject was also perceived as intimidating by 86 (55.1%). Attending the first 2 years of medical school (
< 0.02), previous interest in neuroscience (
< 0.01), and in a surgical subject (
< 0.01) were the factors associated with a greater interest in this subject. Neurosurgery should be included in all students' education, according to 117 (75.0%) participants and practical operating room training should involve all students, according to 96 (61.5%). The most effective learning methods were considered internship (134, 85.9%), followed by participation in meetings or seminars (113, 72.4%). Online seminars were considered useful by 119 participants (76.3%). Neurosurgery was assessed as a potentially interesting career by 99 students (63.5%), who also considered that it can increase their preparation for other subjects (116, 74.4%).
Neurosurgery was positively considered by medicals students, who, however, also perceived it as intimidating and hardly approachable. Demonstration that knowledge of neurosurgical concepts can improve their preparation also in general medical settings and, not only in the field of neuroscience, can be useful to promote their interest toward this subject. A combination of lectures and practical internships is considered an effective learning method, which can be fruitfully associated with new technologies.
Advanced control strategies can enable energy flexibility in buildings by enhancing on-site renewable energy exploitation and storage operation, significantly reducing both energy costs and ...emissions. However, when the energy management is faced shifting from a single building to a cluster of buildings, uncoordinated strategies may have negative effects on the grid reliability, causing undesirable new peaks.
To overcome these limitations, the paper explores the opportunity to enhance energy flexibility of a cluster of buildings, taking advantage from the mutual collaboration between single buildings by pursuing a coordinated approach in energy management.
This is achieved using Deep Reinforcement Learning (DRL), an adaptive model-free control algorithm, employed to manage the thermal storages of a cluster of four buildings equipped with different energy systems. The controller was designed to flatten the cluster load profile while optimizing energy consumption of each building. The coordinated energy management controller is tested and compared against a manually optimised rule-based one.
Results shows a reduction of operational costs of about 4%, together with a decrease of peak demand up to 12%. Furthermore, the control strategy allows to reduce the average daily peak and average peak-to-average ratio by 10 and 6% respectively, highlighting the benefits of a coordinated approach.
•A DRL controller was exploited to implement a coordinated energy management.•DRL control strategy was analysed from single building level up to cluster and grid level.•The DRL controller was compared to a manually optimised rule-based controller.•The coordinated management achieves cost (4%) and peak reduction (12%).
Display omitted
In recent years deep neural networks have been proposed as a lightweight data-driven model to capture high-dimensional, nonlinear physical processes to predict building thermal ...responses. However, the need of a large amount of data for the training process of deep neural networks clashes with the potential limited data availability in most existing or new buildings. Transfer learning aims to enhance the performance of a target learner exploiting knowledge from related and similar environments. This study conducted a suite of experiments that leveraged 250 data-driven models based on a synthetic dataset of a building archetype to study the influence of data availability, energy efficiency level, occupancy and climate for the transfer process of thermal dynamics. The performance of the transfer learning process was compared against a classical machine learning approach. The results suggest that building thermal dynamics can be effectively transferred under the same climatic conditions, increasing performance when dealing with different occupancy schedules, efficiency levels and low data availability. Furthermore, the paper compares the performance of both transfer learning and machine learning approaches in an online fashion, to support the implementation in real-world deployment.